@article{ 
author = {bahrani, payam and MinaeiBidgoli, Behrouz and Parvin, Hamid and Mirzarezaee, Mitra and Keshavarz, Ahm},  
title = {An Ontological Hybrid Recommender System for Dealing with Cold Start Problem}, 
abstract ={Recommender systems that predict user ratings for a set of items are known as subset of information filtration systems. They help users find their favorite items from thousands of available items. One of the most important and challenging problems that recommendation systems suffer from is the problem of dispersion. This means that due to the scatter of data in the system, they are not able to find popular items with the desired reliability and accuracy. This is especially true when there are a large number of items and users in the system and the filled ratings are low. Another challenging problem that these systems suffer from is their scalability. One of the major problems with these systems is the cold start. This problem occurs due to the small number of items rated by the user, i.e. the scatter of users. This problem is divided into two categories: new user and new item. The main focus of this article is on the problem of the new user type. This problem occurs when a new user has just logged in and has not rated any item yet, or when the user has already logged in but has been less active in rating. The goal is to address these three challenges. In this study, an ontology-based hybrid recommender system is introduced in which ontology is used in the content-based filtering section, while the ontology structure is improved by the collaborative filtering section. In this paper, a new hybrid approach based on combining demographic similarity and cosine similarity between users is presented in order to solve the cold start problem of the new user type. Also, a new approach based on combining ontological similarity and cosine similarity between items is proposed to solve the cold start problem of the new item type. The main idea of the proposed method is to extend users’/items’ profiles based on different mechanisms to create higher-performance profiles for users/items. The proposed method is evaluated in a real data set, and experiments show that the proposed method performs better than the advanced recommender system methods, especially in the case of cold start.},  
Keywords = {Recommender System, Ontology, Profile Expansion, Hybrid Recommender System},
volume = {19},
Number = {1}, 
pages = {1-18}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.1.1},
url = {http://jsdp.rcisp.ac.ir/article-1-1199-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1199-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Sadr, Hossein and Pedram, Mir mohsen and Teshnehlab, Mohamm},  
title = {Efficient Method Based on Combination of Deep Learning Models for Sentiment Analysis of Text}, 
abstract ={People's opinions about a specific concept are considered as one of the most important textual data that are available on the web. However, finding and monitoring web pages containing these comments and extracting valuable information from them is very difficult. In this regard, developing automatic sentiment analysis systems that can extract opinions and express their intellectual process has attracted considerable attention in recent years. Sentiment analysis is considered as one of the most active research areas in the field of natural language processing which tries to classify a piece of text containing opinions based on its polarity and determine whether an expressed opinion about a specific topic, event or product is positive or negative. Since about a decade ago, many studies have been carried out to investigate the effects of traditional classification models, such as Support Vector Machine (SVM), Naïve Bayes, Logistic Regression, etc. in the task of sentiment analysis. Although machine learning models have achieved great success in this filed, they are still confronted with some limitations, notably manual feature engineering requirements. In other words, the classification performance of machine learning models is highly dependent on the extracted features and they play an important role in obtaining higher classification accuracy. To deal with these problems, deep learning models have been extensively employed as an alternative to traditional machine learning models and have achieved impressive results. It is worth mentioning that despite the remarkable performance of these methods, they are still confronted with some limitations and they are on their first steps of progress. Therefore, the goal of this paper is to propose a combinational deep learning model that can overcome their problems as well as utilizing their benefits. In this regard, an efficient method based on combination of convolutional and recursive neural networks is proposed in this paper that employs a generalized recursive neural network, where an intermediate feature is obtained by combining children's nodes, as an alternative of pooling layer in attention-based convolutional neural network with the aim of capturing long term dependencies and decreasing the loss of local information. Based on empirical results, the proposed method with the accuracy of 53.92% and 92.89% respectively on SST1 and SST2 datasets not only outperforms other existing models but also can be trained much faster.},  
Keywords = {Sentiment analysis, Deep Leaning, Convolutional neural network, Recursive neural network, Attention mechanism},
volume = {19},
Number = {1}, 
pages = {19-38}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.1.19},
url = {http://jsdp.rcisp.ac.ir/article-1-1060-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1060-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Pourali, Hadiseh and Omranpour, Hesam},  
title = {Ensemble Kernel Learning Model for Prediction of Time Series Based on the Support Vector Regression and Meta Heuristic Search}, 
abstract ={In this paper, a method is presented for predicting time series. Time series prediction is a process which predicted future system values based on information obtained from past and present data points. Time series prediction models are widely used in various fields of engineering, economics, etc. The main purpose of using different models for time series prediction is to make the forecast with the greatest accuracy. The model presented in this paper is based on the combination of kernels and support vector regression. Support vector regression is highly capable of solving function estimation problems by using its kernels, but kernels’ parameters need to be adjusted. First we have preprocessing phase which includes normalizing data and separating data for testing and training. In proposed model, ten different kernels were used. Five kernels were selected as the best kernels by trial and error and these kernels are applied to data. There probably is only a few of the kernels that are useful for the problem, and we are not aware of which kernels are useful for our problem so kernel outputs aggregate by applying a coefficient. This combination creates a new secondary space. The output is given to support vector regression to construct a model that predicts values exactly ɛ accurate, which means the predicted values do not deviate more than ɛ from the original data. This model predicts values by using a leave one out model. Each kernel has parameters that need to be set to optimum values in order to get the best results. Hence in the proposed model, the kernel parameters and their weights are learned by the Gray Wolf Optimizer. This optimizer has been able to provide appropriate answers to many problems, especially challenging problems and has a superior ability to solve the high-dimension problems. By running program in consecutive iterations and examining the different values of the parameters, the optimizer learns the best of them which prediction error has been reduced, and finally returns their best value. The proposed model is implemented on five standard time series and compared to other method, test based on the RMSE criterion for DJ time series, improved by 1.58 point, Radio time series, improved by 0.178 point, and Sunspot time series, improved by 1.709 point. Finally, we analyzed the results, Statistical evaluation by Wilcoxon Signed-Rank Test where the p value is very low compared to the proposed method and CNN-FCM, AR_ model per scale, Multiresolution AR model and ANN methods, slightly lower for Wavelet-HFCM and ANFIS methods and slightly lower than one for SAE-FCM method and at the end provide a relation to find the window size in the model by obtaining the average of peak differences, valley differences, and consecutive peak, and valley differences for the actual values of the training data in exchange for their sequence number in time series.},  
Keywords = {Time series prediction, Support vector regression, Ensemble kernel model, Optimization},
volume = {19},
Number = {1}, 
pages = {39-42}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.1.39},
url = {http://jsdp.rcisp.ac.ir/article-1-1162-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1162-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Dehghani, Abbas and RahimiZadeh, Keyv},  
title = {Design of a novel congestion-aware communication mechanism for wireless NoC in multicore systems}, 
abstract ={Network-on-Chip (NoC) has emerged as leading interconnection backbone to integrate numerous blocks in a single chip. Although it offers a high-performance communication infrastructure by using integrated switch-based networks, the possible performance improvement of a conventional NoC is restricted by multi-hop communications due to high transmission latency and power consumption incurred by the data transmission between two distant cores.  In order to mitigate this problem, wireless NoC (WNoC) architecture has proposed as an alternative solution to design flexible, low-power, and high bandwidth communication infrastructures for the future multicore platforms. It is necessary to mention that wire-based interconnections are still highly effective for short distances communications. Therefore, hybrid WNoC architectures are emerged as scalable communication structure to alleviate the deficits of traditional NOC architecture for the modern multicore systems. The hybrid WNoC architecture provides energy efficient, high data rate and flexible communications for NoC architectures. In these architectures, each wireless router is shared by a set of processing cores. However, sharing links between cores increases congestion in the network that limits the performance and scalability of NoCs and affects the system to work at less than its peak gain. Moreover, the congestion can heightens network inefficiency when the network is scaled to more nodes. In this paper, we propose a novel congestion-aware mesh-based WNoC architecture to address these issues. We consider optimization of the system cost and performance, simultaneously. For congestion control, it is recommended to include a multi-path routing. This means that several routes are calculated and recorded for each destination and finally the traffic load is distributed. Paths are selected based on their scores, which are obtained dynamically. When a path is used to transmit packets, the score of that path is reduced so that fewer packets are sent from that path and more scored paths are used. This approach aims to the distribution of traffic loads on the paths. The performance of the proposed architecture has been evaluated and compared with notable WNoC architectures through comprehensive simulations. The experimental results demonstrated the effectiveness of the proposed design under both synthetic and realistic traffic patterns in terms of network throughput, latency, and energy consumption.},  
Keywords = {Network on Chip, Wireless communications, Multicore, System-on-Chip, Congestion},
volume = {19},
Number = {1}, 
pages = {43-58}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.1.43},
url = {http://jsdp.rcisp.ac.ir/article-1-1077-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1077-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Rezvani, Mohsen and Fateh, Mansoor},  
title = {A High Capacity Email Steganography Scheme using Dictionary}, 
abstract ={The expansion of the use of information exchange space and public access to communication networks such as the Internet has led to the growing dependence of social institutions on the use of these networks. However, maintaining the security of information exchanged on networks is one of the most important challenges for users of these networks. One way to protect this data is to use private networks. But building these networks is not cost-effective in terms of time and cost. In contrast, the use of encryption techniques, access control mechanisms and data concealment are among the effective solutions for security in the information exchange space. Existing methods for hiding information can be divided into three categories: cryptography, watermarking and steganography. In cryptography, a simple text is converted into encrypted text, which, of course, requires a decryption operation as well as an encryption key. In general, cryptographic techniques suffer from two major problems. The first problem is the ban on the transmission of encrypted data in dictatorial regimes, and the second problem is that cryptographers pay attention to encrypted data and stop any secret communication. The second category of information hiding methods is watermarking. Watermarking techniques are commonly used to protect the copyright of a digital content and to deal with issues such as fraud, fraud and copyright infringement in the data transfer space. In steganography methods, the transfer of information takes place in a cover through public communication channels, and only the sender and receiver are aware of the existence of a secret message. Two aspects of steganography must be observed. The first aspect is that the cover and secret content look the same in the face of statistical attacks. The second aspect is that the process of hiding the secret message in the cover is such that there is no difference between the cover and the secret in terms of the human perceptual system. In fact, the accuracy of the transmission media is maintained. Steganography methods use image, video, protocol, audio, and text platforms to hide information. Steganography in the text is difficult due to very little local variation. Humans are very sensitive to textual changes. Hence it is difficult to spell in the text. However, due to the high use of text in digital media, the insensitivity of text to compression, the need for less memory to store and communicate more easily and faster, many methods for steganography have been introduced in it. In addition, text is still one of the major forms of communication available to the general public around the world. In this paper, we propose a new email steganography scheme using a dictionary-based compression. In the proposed scheme, a number of email addresses containing a hidden message will be generated using the submitted text. The submitted text is sent to the generated and recipient addresses at the same time. This does not reveal the identity of the recipient of the message, and only the recipient can extract secret message using other email addresses. In the proposed method, two steganography keys are used. Using these two keys increases the security level of the proposed method. Also, the capacity of the proposed method is unlimited, which of course is a great advantage in a steganography method. This unlimited capacity provides high security for the proposed method. Another advantage is that the proposed method is not limited to the type of the cover-text. Initially, the secret message is converted to a bit string by a dictionary. Then the operation of embedding the secret message in the recipient's addresses is done by the steganography keys. The efficiency of steganography algorithms depends on various factors such as lack of detection by the human eye, lack of detection by statistical methods, and capacity. The proposed method does not change the cover-text. Hence, this method is not detectable by humans or statistical methods. The capacity of the proposed method in this research is based on built-in email addresses. As the text of the message increases, the number of emails created increases too. Of course, this increase in the address of the emails created can lead to suspicion of the emails sent. Therefore, the parameter of the number of emails created is also important in the evaluation. In this paper, the efficiency of the proposed method is evaluated based on the two parameters and compared with existing methods. The results of this evaluation show that the proposed method, in addition to providing unlimited capacity in steganography, produces fewer email addresses generated as well as fewer message bits after compression.},  
Keywords = {Email Steganography, Dictionary, Capacity, Security},
volume = {19},
Number = {1}, 
pages = {59-74}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.1.59},
url = {http://jsdp.rcisp.ac.ir/article-1-1047-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1047-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {javadzadeh, fershteh and yaghoubi, mehdi and karbasi, soheil},  
title = {Concept drift detection in event logs using statistical information of variants}, 
abstract ={In recent years, business process management (BPM) has been highly regarded as an improvement in the efficiency and effectiveness of organizations. Extracting and analyzing information on business processes is an important part of this structure. But these processes are not sustainable over time and may change for a variety of reasons, such as the environment, human resources, capital market changes, seasonal, and climate changes. These changes in business processes are referred to as concept drift in event logs. The discovery of concept drifts is one of the challenges in business process management. These drifts may occur suddenly, gradually, periodically, or incrementally. This paper proposes an algorithm for identifying sudden concept drifts in event logs that are created by BPM. Each execution of the process instance follows a specific path in the process model called a trace, all traces that follow the same path in process model are called a variant. The proposed algorithm is based on the distribution of trace variants in the execution of processes. In this method, by moving two sliding windows on the event log, two feature vectors are derived from the two windows trace variants, these windows are named reference and detection windows. Then variants of the two windows are compared by applying statistical G-test and finally the drifts are identified.  In statistics, G-test is likelihood-ratio or maximum likelihood statistical significance test. Experiments on artificial databases show the correctness of the method and its superiority to the previous methods. In the proposed method, the detection accuracy is 0.06% better than state-of-the-art methods on average},  
Keywords = {Concept drift, event log, process mining, business processes, variant},
volume = {19},
Number = {1}, 
pages = {75-86}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.1.75},
url = {http://jsdp.rcisp.ac.ir/article-1-1051-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1051-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Alipour, Mir Mohammad and Abdolhosseinzadeh, Mohse},  
title = {A Multiagent Reinforcement Learning algorithm to solve the Community Detection Problem}, 
abstract ={Recent researches show that diverse systems in many different areas can be represented as complex networks. Examples of these include the Internet, social networks and so on. In each case, the system can be modeled as a complex and very large network consisting of a large number of entities and associations between them. Most of these networks are generally sparse in global yet dense in local. They have vertices in a group structure and the vertices within a group have higher density of edges while vertices among groups have lower density of edges. Such a structure is called community and is one of the important features of the network and is able to reveal many hidden characteristics of the networks. Today, community detection is used to improve the efficiency of search engines and discovery of terrorist organizations on the World Wide Web. Community detection is a challenging NP-hard optimization problem that consists of searching for communities. It is assumed that the nodes of the same community share some properties that enable the detection of new characteristics or functional relationships in a network. Although there are many algorithms developed for community detection, most of them are unsuitable when dealing with large networks due to their computational cost. Nowadays, multiagent systems have been used to solve different problems, such as constraint satisfaction problems and combinatorial optimization problems with satisfactory results. In this paper, a new multiagent reinforcement learning algorithm is proposed for community detection in complex networks. Each agent in the multiagent system is an autonomous entity with different learning parameters. Based on the cooperation among the learning agents and updating the action probabilities of each agent, the algorithm interactively will identify a set of communities in the input network that are more densely connected than other communities. In other words, some independent agents interactively attempt to identify communities and evaluate the quality of the communities found at each stage by the normalized cut as objective function; then, the probability vectors of the agents are updated based on the results of the evaluation. If the quality of the community found by an agent in each of the stages is better than all the results produced so far, then it is referred to as the successful agent and the other agents will update their probability vectors based on the result of the successful agent. In the experiments, the performance of the proposed algorithm is validated on four real-world benchmark networks: the Karate club network, Dolphins network, Political books network and College football network, and synthetic LFR benchmark graphs with scales of 1000 and 5000 nodes. LFR networks are suitable for systematically measuring the property of an algorithm. Experimental results show that proposed approach has a good performance and is able to find suitable communities in large and small scale networks and is capable of detecting the community in complex networks In terms of speed, precision and stability. Moreover, according to the systematic comparison of the results obtained by the proposed algorithm with four state-of-the-art community detection algorithms, our algorithm outperforms the these algorithms in terms of modularity and NMI; also, it can detect communities in small and large scale networks with high speed, accuracy, and stability, where it is capable of managing large-scale networks up to 5000 nodes.},  
Keywords = {Complex networks, Community detection, Multiagent systems, Reinforcement learning, Modularity Q},
volume = {19},
Number = {1}, 
pages = {87-100}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.1.87},
url = {http://jsdp.rcisp.ac.ir/article-1-1084-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1084-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {jafarabad, mohammad and Dianat, Rouhollah},  
title = {Relation extraction based on word embedding with Crowdsourcing Process}, 
abstract ={For data mining studies, due to the complexity of doing feature selection process in tasks by hand, we need to send some of labeling to the workers with crowdsourcing activities. The process of outsourcing data mining tasks to users is often handled by software systems without enough knowledge of the age or geography of the users' residence. We use convolutional neural network, for doing classification in six classes: USAGE, TOPIC, COMPARE, MODEL-FEATURE, RESULT and PART-WHOLE. This article extracts the data from the abstract of 450 scientific articles and it is a total of 835 relations. One hundred of these abstracts have been selected by the crowdsourcing. Classification results in this article have been done with a slight improvement in accuracy. In this study, we computed the classification results on a combination of vocabulary vectors with using of 450 abstract relation data (100 crowd source datasets with 350 standards). The results of the implementation of the classification algorithm give us performance improvement. This paper uses the population power to perform preparing data mining works. The proposed method by adding crowdsource data to the previous data was able to obtain better results rather than the top 5 methods.},  
Keywords = {Glove, Word2vec, Crowdsourcing, word embedding, classification},
volume = {19},
Number = {1}, 
pages = {101-110}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.1.101},
url = {http://jsdp.rcisp.ac.ir/article-1-1074-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1074-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Rezaei, Masoumeh and Rezaeian, Mehdi and Derhami, Vali},  
title = {A novel local feature descriptor using the Mercator projection for 3D object recognition}, 
abstract ={The processing of point clouds is one of the growing areas in machine vision. With the advent of inexpensive depth sensors, there has been a great interest in point clouds to detect three-dimensional objects. In general, 3D object recognition methods are alienated into two classes: local and global feature-based methods.  In global feature-based methods, the entire shape of the model is described, while in local methods, the geometric properties of the local area around a point are used to obtain the characteristic of the point. Unlike global methods, local methods do not entail any segmentation and they are more robust to clutter and occlusion. The local feature-based methods extract some geometric features from local surfaces around specific points named keypoints. The geometric features of a keypoint are encoded into a feature descriptor. How to describe the environment around a keypoint is the main challenge of these methods. The commonly used local feature-based methods often are sensitive to noise, varying mesh resolution, and rigid transformation. To overcome such disadvantages, in this paper, a new local feature descriptor based on the Mercator projection is proposed. The Mercator projection is one of the most popular 3D to 2D projections that can preserve true distance, direction, and relative longitude and latitude between any two points in point clouds. To evaluate, the proposed method has been compared with several state-of-the-art descriptor methods. The superiority of this method over other methods is shown by using the criteria of square Root Mean Square Error (RMSE), Recall versus 1-Precision Curve (RPC), and registration correction, rotation, and translation errors, and it is proved that this method has good descriptiveness power and it is robust to noise and varying mesh resolution. Introduction In this paper, we propose a new local descriptor to provide robust and precise geometric features. The geometric features are extracted using the Mercator projection of the neighborhood sphere. Our contributions are as follows: (1) The proposed descriptor directly learns from the point clouds (2) using the proposed method, there is only one representation for each point so the problem of multiple representations of a point is addressed. Also, the Mercator projection has many properties that make it appropriate for data representations in a point cloud. (3) It can accurately describe the geometric properties around a point. (3) The Mercator projection is a conformal projection so it preserves true distances, directions, and relative longitudes and latitudes. (4) It keeps small element geometry, which means Mercator projection preserves the shapes of small regions.  The proposed method Given a query point p, a sphere of radius r is centered at p for determining the neighbor points. Then Mercator projection is used for mapping the sphere into a plane with considering the Local reference frame (LRF) as previously suggested by Tombaret al. (2010b). The Mercator projection is a cylindrical projection that was proposed by G. Mercator in 1569. In this projection, the surface of a sphere is mapped into a plane. It preserves true distances, directions, and relative longitudes and latitudes. The Mercator projection for each point is identified using two following equations:  (2)  where λ is the  longitude and φ is the  latitude of a point  in the sphere, and (x,  y) represents corresponding point  in the Cartesian map. For extracting images as the input of the Siamese network, we need ranges for achieved x and  y. The variable x is in the interval [−π,  π] but range of y is different for the Mercator projection of each keypoint. As a result, the minimum and maximum of the variable y for all neighbor points are considered as the range of y, then a histogram 30 × 30 is measured. The Mercator projections of all neighbors are defined and the number of points  in each bin counted. Then we normalize the histogram by dividing each bin by the total number of neighbor points, it causes more robustness to noise and mesh resolution. Results and discussion The performance of the proposed method is evaluated on the Bologna (Tombari et al., 2010c) and John Burkardt in terms of RMSE, RPC and registration correction rate, rotation and translation errors. The proposed outperforms other methods in term of RPC also the results show that the method is robust to noise, rigid transformation and varying mesh resolution.},  
Keywords = {Point cloud, 3D object recognition, Local descriptor, Mercator projection},
volume = {19},
Number = {1}, 
pages = {111-124}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.1.111},
url = {http://jsdp.rcisp.ac.ir/article-1-1163-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1163-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Zabihzadeh, Davood and Zahedi, Saeed and Monsefi, Rez},  
title = {An Effective Approach for Robust Metric Learning in the Presence of Label Noise}, 
abstract ={Many algorithms in machine learning, pattern recognition, and data mining are based on a similarity/distance measure. For instance, the kNN classifier and clustering algorithms such as k-means require a similarity/distance function. Also, in Content-Based Information Retrieval (CBIR) systems, we need to rank the retrieved objects based on the similarity to the query. As generic measures like Euclidean and cosine similarity are not appropriate in many applications, metric learning algorithms have been developed with the aim of learning an optimal distance function from data. These methods often need training data in the form of pair or triplet sets. Nowadays, this training data is popularly obtained via crowdsourcing from the Internet.  Therefore, this information may be contaminated with label noise resulting in the poor performance of the learned metric. In some datasets, even it is possible that the learned metrics perform worse than the general ones such as Euclidean. To address this emerging challenge, we present a new robust metric learning algorithm that can identify outliers and label noise simultaneously from training side information. For this purpose, we model the probability distribution of label noise based on information in the training data. The proposed distribution function efficiently assigns the high probability to the data points contaminated with label noise. On the other hand, its value on the normal instances is near zero. Afterward, we weight the training instances according to these probabilities in our metric learning optimization problem. The proposed optimization problem can be solved using available SVM libraries such as LibSVM efficiently. Note that the proposed approach for identifying data with label noise is general and can easily be applied to any existing metric learning algorithms. After the metric learning phase, we utilized both the weights and the learned metric to enhance the accuracy of the metric-based classifier such as kNN. Several experiments are conducted on both real and synthetic datasets. The results confirm that the proposed algorithm enhances the performance of the learned metric in the presence of label noise and considerably outperforms state-of-the-art peer methods at different noise levels.},  
Keywords = {Robust Metric Learning, Label Noise, Outlier, Distance Measure},
volume = {19},
Number = {1}, 
pages = {125-136}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.1.125},
url = {http://jsdp.rcisp.ac.ir/article-1-1096-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1096-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Abedi, Zahra and Yazdian-Dehkordi, Mahdi},  
title = {Extending SAR Image Despckling methods for ViSAR Denoising}, 
abstract ={Synthetic Aperture Radar (SAR) is widely used in different weather conditions for various applications such as mapping, remote sensing, urban, civil, and military monitoring. Recently, a new radar sensor called Video SAR (ViSAR) has been developed to capture sequential frames from moving objects for environmental monitoring applications such as image or video segmentation, classification and change detection. Same as SAR images, the major problem of ViSAR is the presence of speckle noise. In this paper, the performance of several image-based denoising methods is studied for de-speckling of ViSAR frames through “Frame-by-Frame”, “Averaging” and “3D” schemes. In “Frame-by-Frame” scheme, each video frame is denoised independently of the other frames; whereas, in “Averaging” scheme, the denoised images are averaged along a time window. In “3D” scheme, denoising is performed on 3D blocks in space-time (x-y-t) domain. In addition to these schemes, a novel extension on SAR-BM3D method, called ViSAR Incremental BM3D (ViSAR-IBM3D) approach is proposed for video denoising. The SAR-BM3D method performs denoising in two steps. At the first step, it uses wavelet denoising to primitively denoise the original image; in the next step, this image in combination with the original image are used to estimate the final denoised image. The main challenge of SAR-BM3D method is high time complexity especially for video frames. Here, in ViSAR-IBM3D, we benefit from the correlation between the frames of video and utilize the denoised images in previous frame to de-speckle the current frame. The proposed method can remarkably reduce the time complexity and improve preserving the details and the contrast of the denoised frames. The experimental results evaluated on real-world ViSAR video as well as video with simulated noises show that the proposed 3D filtering scheme and the proposed ViSAR-IBM3D method achieve better denoising performance than the other ones.},  
Keywords = {SAR, ViSAR, Noise, Speckle, SAR-BM3D, ViSAR-IBM3D},
volume = {19},
Number = {1}, 
pages = {137-152}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.1.137},
url = {http://jsdp.rcisp.ac.ir/article-1-1044-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1044-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {partabian, jaafar and rafe, vahid and parvin, hamid and nejatian, samad and bagherifard, Karamollah},  
title = {Reachability checking in complex and concurrent software systems using intelligent search methods}, 
abstract ={The model checking technique is a formal and effective method for verifying software systems, which analyses it via generating and examining all possible states of a model of the software system. In safety-critical systems, one could not admit the risk of error even in the testing process, therefore it is necessary to carry out the verification process before implementation and at the model level. Using this technique to evaluate properties such as security entails all available states (all state space) being generated, then the state space of the system in question be carefully examined. The main challenge of the model checking technique in large and complex systems with wide or infinite state space is the problem of state space explosion (lack of memory in the generation of all possible states). Graph transformation systems are one of the most widely used formal modeling systems and a suitable solution for modeling and checking complex systems. In systems where security property verification is not possible, the security feature can be refuted by searching for an accessible mode in which a specific configuration (e.g. error or undesirable behavior) occurs. Recent studies advocate that partial and intelligent exploration of part of the state space could be a good solution to the problem of state space explosion. The goal of this study is to use the random forest algorithm in the model checking which can solve the problem of state space explosion by selecting a few promising paths. A path is hopeful whenever the probability of reaching an answer through this path is higher than other paths. In the proposed method, a small model of the system is first created using the official language of the Graph Description System (GTS). Afterwards, a training data set of paths to the goal is generated from the small model mode space. The generated training data set is then provided to the random forest algorithm to identify and discover the logical relationships within it. In the next stage, the acquired knowledge is used to intelligently explore the incomplete space of the large model state. The proposed approach is used in the verification of the reachability property and to refute the safety feature in large and complex systems where it is impossible to generate the entire system state space. In order to evaluate the proposed approach, it has been implemented in GROOVE which is an open source tool for designing and checking models in graph conversion systems. The results indicate that the proposed method performs better than the compared methods in terms of average running time and the length of the generated witness.},  
Keywords = {Software systems verification, Knowledge discovery, State space explosion, intelligent search},
volume = {19},
Number = {1}, 
pages = {153-166}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.1.153},
url = {http://jsdp.rcisp.ac.ir/article-1-1075-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1075-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Sheikhzade, Shokooh and Vahdat-Nejad, Hamed and Havangi, Ramaz},  
title = {Pothole Detection by Soft Computing}, 
abstract ={Potholes on roads are regarded as serious problems in the transportation domain, and ignoring them lead to an increase in accidents, traffic, vehicle fuel consumption, and waste of time and energy. As a result, pothole detection has attracted researchers’ attention, and different methods have been presented for it up to now. Data analysis methods such as machine learning and soft computing have been widely used for detection purposes. They rely on a dataset and propose a system that can detect a special event in similar datasets. Their effectiveness can be measured by evaluating their accuracy in detecting the event. Image processing involves a wide range of analytics that are used to extract specific information from images. The majority of image processing programs require massive computational power. The major part of previous research is based on image processing. They utilize dedicated cameras which are embedded in vehicles to take images and analyze them through massive image processing programs. This scheme requires dedicated hardware that is not typically available on vehicles. In this paper, a new scheme is proposed, which uses accelerometer and GPS sensors. These types of sensors are available in today’s smartphones as well as modern vehicles. The data generated by these sensors is processed via soft computing to increase the accuracy of pothole detection. The proposed algorithm uses a combination of a fuzzy system and evolutionary algorithms. Fuzzy systems have been widely used to model the real-world problems that are described by uncertainty and ambiguity. Evolutionary algorithms (e.g., genetic algorithms) try to imitate evolutionary science in solving hard problems. Genetic algorithm and harmony search are used to adjust membership functions of the proposed fuzzy system. For evaluation, a case study has been conducted with regard to detect potholes on Ghaffari Street in Birjand. To this end, a real dataset has been collected and used for implementing the proposed method. Experimental results show the high accuracy of the proposed algorithm in comparison to other solutions. They reveal that the accuracy of the proposed genetic fuzzy algorithm is 98 percent and for the proposed harmony fuzzy algorithm is 99 percent.},  
Keywords = {Soft computing, Pothole detection, Fuzzy system, Genetic algorithm, Harmony search.},
volume = {19},
Number = {2}, 
pages = {1-12}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.2.1},
url = {http://jsdp.rcisp.ac.ir/article-1-1101-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1101-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Sharifi, Abbas Ali and Emami, Hojjat},  
title = {Increasing the Performance of OFDM Systems by PAPR Reduction in PTS Technique using Election Optimization Algorithm}, 
abstract ={Orthogonal Frequency Division Multiplexing (OFDM) is a useful technology in wireless communications that provides high-rate data transmission in multipath fading channels. The advantages of OFDM systems are the high spectral efficiency and strong resistance to frequency selective fading. In OFDM systems, a large number of sub-carriers are used to modulate the symbols causing the time-domain OFDM signal to have a large dynamic range, or a high peak-to-average power ratio (PAPR). When the signals are applied to a nonlinear power amplifier, the OFDM systems’ performance is degraded by the high PAPR. In recent years, several works have been done to reduce the PAPR of OFDM systems. One of the most well-known methods is a partial transmit sequence (PTS). Regardless of the PTS advantages, it suffers from a high computational complexity. Because it requires an exhaustive search over all possible combinations of phase factors. The computational complexity of the PTS increases with increasing the number of phase factors and sub-blocks. There are several approaches to overcome the computation complexity issue of the PTS technique. The majority of these methods mainly employed swarm intelligence and evolutionary optimization algorithms to resolve the PTS shortcoming. These methods report encouraging results, however, their performance is far from the ideal state. This highlights that improving the performance of PTS is an open problem and there is room for more improvement. As an element of research, we propose an optimization approach based on the election algorithm (EA) to overcome the computational complexity of the PTS technique. To realize this goal, we improve the EA algorithm by introducing a new version of positive advertisements operator. The new operator efficiently improves the search capability of the EA through balancing between the exploration and exploitation power of the algorithm. The proposed EA based PTS (EA-PTS) approach, by searching the optimal phase factors, imposes less computational complexity on the system and reduces the PAPR to an acceptable level. The proposed method is compared with the optimal PTS (O-PTS), genetic algorithm-based PTS (GA-PTS) and imperialism competition algorithm based PTS (ICA-PTS) techniques. Simulation results show that the proposed EA-PTS has better performance in simultaneously reducing the PAPR and computational complexity.},  
Keywords = {OFDM, PAPR, Partial Transmit Sequence (PTS), Election Algorithm (EA), EA-PTS},
volume = {19},
Number = {2}, 
pages = {13-26}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.2.13},
url = {http://jsdp.rcisp.ac.ir/article-1-1087-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1087-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {YasrebiNaeini, Ehsan and hatami, mahl},  
title = {Improving Imbalanced Data Classification Accuracy by using Fuzzy Similarity Measure and Subtractive Clustering}, 
abstract ={One of the biggest challenges in this field is classification problems which refers to the number of different samples in each class. If a data set includes two classes, imbalance distribution occurs when one class has a large number of samples while the other is represented by a small number of samples. In general, the methods of solving these problems are divided into two categories: under-sampling and over-sampling. In this research, it is focused on under-sampling and the advantages of this method will be analyzed by considering the efficiency of classifying imbalanced data and it’s supposed to provide a method for sampling a majority data class by using subtractive clustering and fuzzy similarity measure. For this purpose, at first the subtractive clustering is conducted and the majority data class is clustered. Then, using fuzzy similarity measure, samples of each cluster will be ranked and appropriate samples are selected based on these rankings. The selected samples with the minority class create the final dataset. In this research, MATLAB software is used for implementation, the results are evaluated by using AUC criterion and analyzing the results has been performed by standard statistical tools. The experimental results show that the proposed method is superior to other methods of under-sampling.},  
Keywords = {Imbalanced data, Fuzzy similarity measure, Under-sampling, Subtractive clustering},
volume = {19},
Number = {2}, 
pages = {27-38}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.2.27},
url = {http://jsdp.rcisp.ac.ir/article-1-1010-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1010-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Daneshpour, Negin and mirabolghasemi, Seyedeh fatemeh},  
title = {Missing Data Imputation in Multivariate Time Series Data}, 
abstract ={Multivariate time series data are found in a variety of fields such as bioinformatics, biology, genetics, astronomy, geography and finance. Many time series datasets contain missing data. Multivariate time series missing data imputation is a challenging topic and needs to be carefully considered before learning or predicting time series. Frequent researches have been done on the use of different techniques for time series missing data imputation, which usually include simple analytic methods and modeling in specific applications or univariate time series. In this paper, a hybrid approach to obtain missing data is proposed. An improved version of inverse distance weighting (IDW) interpolation is used to missing data imputation. The IDW interpolation method has two major limitations: 1) finding closest points to missing data 2) Choosing the optimal effect power for missing data neighbors. Clustering has been used to remove the first constraint and find closest points to the missing data. With the help of clustering, the search radius and the number of input points that are supposed to be used in interpolation calculations are limited and controlled, and it is possible to determine which points are used to determine the value of a missing data.Therefore, most similar data to the missing data are found. In this paper, the k-maens clustering method is used to find similar data. This method has been more accurate than other clustering methods in multivariate time series. Evolutionary algorithms are used to find the optimal effect power of each data point to remove the second constraint. Considering that each sample within each cluster has a different effect on the estimation of missing data, cuckoo search is used to find the effect on missing data. The cuckoo search algorithm is applied to the data of each cluster, and each data sample that has more similarity with the missing data has more influence, and each data sample that has less similarity has less influence and has less influence in determining the amount of missing data. Among evolutionary algorithms, evolutionary cuckoo search algorithm is used due to high convergence speed, much less probability of being trapped in local optimal points, and ability to quickly solve high dimensional optimization problems in multivariate time series problems. To evaluate the performance of the proposed method, RMS, MAE, , MSE and MAPE criteria are used. Experimental results are investigated on four UCI datasets with different percentages of missingness and in general, the proposed algorithm performs better than the other three comparative methods with an average RMSE error of 0.05, MAE error of 0.04, MSE error of 0.003, and MAPE error of 5. The correlation between the actual data and the estimated value in the proposed method is about 99%.},  
Keywords = {Missing Data imputation, IDW Interpolation, Cuckoo Search Algorithm, k-means Clustering, Multivariate Time Series},
volume = {19},
Number = {2}, 
pages = {39-60}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.2.39},
url = {http://jsdp.rcisp.ac.ir/article-1-1104-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1104-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {saeedi, nayyerh and Babaie, Shahram},  
title = {A New Hybrid Routing Algorithm based on Genetic Algorithm and Simulated Annealing for Vehicular Ad hoc Networks}, 
abstract ={In recent years, Vehicular Ad-hoc Networks (VANET) as an emerging technology have tried to reduce road damage and car accidents through intelligent traffic controlling. In these networks, the rapid movement of vehicles, topology dynamics, and the limitations of network resources engender critical challenges in the routing process. Therefore, providing a stable and reliable routing algorithm is a necessary requirement to maintain the Quality of Service (QoS) parameters of VANETs. In this paper, a new routing algorithm based on the clustering technique is proposed, which is called GCAR. In the proposed algorithm, the appropriate cluster heads are selected based on the genetic algorithm then two vehicles are selected between the neighboring clusters as the gateways and a vehicle chain is formed by these vehicles. Moreover, a combination of genetic algorithm and simulated annealing is applied to identify the suitable clusters. The conducted simulations in MATLAB tool indicate that, respectively, path discovery ratio, the number of clusters, throughput, and packet delivery ratio of the proposed algorithm have been improved by 18.4%, 2.55%, 3.45%, and 14.18% in comparison to the PassCAR approach. Furthermore, evaluation of the convergence, standard deviation, and standard error of the proposed algorithm prove its high convergence speed and stability.},  
Keywords = {Vehicular Ad-hoc Networks (VANET), Routing, Clustering, Genetic Algorithm, Simulated annealing},
volume = {19},
Number = {2}, 
pages = {61-72}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.2.61},
url = {http://jsdp.rcisp.ac.ir/article-1-1133-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1133-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Mahmoudi-Nasr, Payam and Kimia, Hossei},  
title = {A Mutual Authentication Method for Internet of Things}, 
abstract ={Today, we are witnessing the expansion of various Internet of Things (IoT) applications and services such as monitoring and health. These services are delivered to users via smart devices anywhere and anytime. Forecasts show that the IoT, which is controlled online in the user environment, will reach 25 billion devices worldwide by 2020. Data security is one of the main concerns in the IoT. The IoT is supposed to deal with a population of about billions of objects, so the number of malicious attacks can be very high and alarming given the global connection (anyone access) and the wide availability (access to any place at any time). However, these accesses can make security and privacy critical. Reports show that 26% of IoT attacks in 2019 were related to non-authentication, which is why IoT authentication has become one of the most sensitive security concepts. IoT devices are usually left unattended and this makes it easy for an attacker to target such equipment. For example, security breaches and unwanted changes in patient's health parameters in smart health care systems can cause wrong treatments or even lead to his death. The fact that each device in the IoT knows who it is communicating with and at what level of access is one of the important aspects of security, especially in cases where various devices with different capabilities have to perform common tasks and cooperate with each other. IoT authentication is a trust model to protect control access and data when information travels between devices. So far, different methods have been proposed for authentication in the IoT network. These methods are usually based on the public key, private key, random key distribution, and hash function. A point that should be taken into account in IoT authentication is that IoT networks and devices have limited bandwidth, low memory, low processing power, and energy limitations. Therefore, the proposed method should pay special attention to such limitations. In addition, IoT authentication needs to ensure enhanced security features such as confidentiality, data integrity, reliability, maintainability, scalability, and privacy to their consumers. This paper proposes a two-way or mutual authentication protocol in which both devices authenticate each other without human intervention in a smart home network. The proposed protocol is based on asymmetric encryption for authentication of devices, which have a shared private session key, along with hashing operations in the network. Also, to ensure the security of communications at each session, each device has a one-time private session key. The session keys are changed regularly to ensure the security of sessions between devices. The proposed protocol is programmed by HLPSL and simulated and verified by the SPAN and AVISPA tools. The security analysis results show the proposed protocol is extremely practical, and secure against potential attacks.},  
Keywords = {Internet of Things, Authentication protocol, Cryptography, Security,AVISPA},
volume = {19},
Number = {2}, 
pages = {73-86}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.2.73},
url = {http://jsdp.rcisp.ac.ir/article-1-1134-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1134-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Omidvar, MohammadNabi and Nejatian, Samad and Parvin, Hamid and Bagherifard, Karamolla and Rezaie, Vahideh},  
title = {Providing an algorithm for solving general optimization problems based on Domino theory}, 
abstract ={Optimization is a very important process in engineering. Engineers can create better production only if they make use of optimization tools in reduction of its costs including consumption time. Many of the engineering real-word problems are of course non-solvable mathematically (by mathematical programming solvers). Therefore, meta-heuristic optimization algorithms are needed to solve these problems. Based on this assumption, many new meta-heuristic optimization algorithms have been proposed inspired by natural phenomena, such as IWO [58], BBO [59], WWO [61], and so on. Inspired by domino toppling theory, we proposed an optimization algorithm. Using domino pieces, we can create countless complex structures. To simulate the domino movement in the search space of a problem, we consider the particles in the search space as the domino pieces and, by creating an optimal path, we will try to direct the dominoes to the optimal path. The optimal paths will be updated in each iteration. After initializing the dominoes randomly at the beginning of each evaluation, the picking piece or the first moving piece will be identified and then the particles will be selected by the optimal path. Applying a motion equation to each domino will move the dominoes forward in that direction. At first, a predefined dominoes will be randomly distributed in the problem space. Choosing the optimal path will accelerate the convergence of the domino particles towards the target. After choosing the path in current iteration, we now have to do the domino movement. The particles will move to a new location by applying the new location equation. By applying this equation, each domino piece will sit on the track ahead of itself. The front piece will also move to a new location by applying an equation separate from the rest. After moving the dominoes to the new location, the worst iteration of the previous iteration will be removed from the problem space. In the new iteration, the optimal domino path, the new locations of domino pieces and the global optimum will be updated. At the end of the algorithm, the global optimum will be determined as the optimal solution. This method is implemented in a simulator environment. To evaluate the performance of the Domino Optimization algorithm, we use a complete benchmark including 30 objective functions called CEC 2014 [67] that are single-objective numerical functions. In all cases, we set the population size to 50, the dimension size to 30, and the number of fitness function evaluation to 150,000. We compare the proposed Domino Optimization algorithm (DO) with the algorithms LOA [57], ICS [62], NPSO [63], MOHS [64], BCSO [65] and FFFA [66]. The results obtained from the 3 unimodal functions show that the proposed method is able to achieve a better solution than any of the state of the art algorithms at the equal resources. Results in the multimodal functions show that the proposed method has the best performance in finding the optimal solution in all of the available 13 functions in this section. In all of 6 functions in the hybrid section, the quality of the proposed method is better than all of the state of the art algorithms at the equal resources. The standard deviation values ​​of the proposed method, which are often small numbers, indicate algorithm convergence around the optimal solution. Also among the available methods, two algorithms, named NPSO and LOA, have good results after the proposed method. In the convergence analysis of dominoes, the diversity of objective functions in 100 distinct iterations shows a big value at the beginning of the algorithm, and a low value at the end of the algorithm.},  
Keywords = {Algorithm, Optimization, Dominoes, Cost Function, Behavior},
volume = {19},
Number = {2}, 
pages = {87-106}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.2.87},
url = {http://jsdp.rcisp.ac.ir/article-1-1094-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1094-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Rajabi, Zeinab and valavi, Mohamadreza and Hourali, Maryam},  
title = {Sentiment analysis methods in Persian text: A survey}, 
abstract ={With the explosive growth of social media such as Twitter and Instagram, reviews on e-commerce websites, and comments on news websites, individuals and organizations are increasingly using analyzing opinions in these media for their decision-making and designing strategies. Sentiment analysis is one of the techniques used to analyze users' opinions in recent years. The Persian language has specific features and thereby requires unique methods and models to be adopted for sentiment analysis, which are different from those in English and other languages. This paper identifies the characteristics and limitations of the Persian language. Sentiment analysis in each language has specified prerequisites; hence, the direct use of methods, tools, and resources developed for the English language in Persian has its limitations. The present study aims to investigate and compare previous sentiment analysis studies on Persian texts and describe views presented in articles published in the last decade. First, the sentiment analysis levels, approaches, and tasks are described. Then, a detailed survey of the applied sentiment analysis methods used for Persian texts is presented, and previous works in this field are discussed. The advantages and disadvantages of each proposed method are demonstrated. Moreover, the publicly available sentiment analysis resources of Persian texts are studied, and the characteristics and differences of each are highlighted. As a result, according to the recent development of the sentiment analysis field, some issues and challenges not being addressed in Persian texts are listed, and some guidelines are provided for future research on Persian texts. Future requirements of Persian text for improving the sentiment analysis system are detailed.},  
Keywords = {Sentiment Analysis, Opinion Mining, Sentiment Classification, Sentiment Data Resource, Persian Language},
volume = {19},
Number = {2}, 
pages = {107-132}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.2.107},
url = {http://jsdp.rcisp.ac.ir/article-1-1099-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1099-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Emami, Hojjat},  
title = {Presenting a method for extracting structured domain-dependent information from Farsi Web pages}, 
abstract ={Extracting structured information about entities from web texts is an important task in web mining, natural language processing, and information extraction. Information extraction is useful in many applications including search engines, question-answering systems, recommender systems, machine translation, and etc. An information extraction system aims to identify the entities from the text and extract their related information to form a profile of the target entity. In recent years, several methods have been proposed for extracting structured information from web text. The majority of existing methods for extracting entity-centric information require a predefined ontology. The ontology includes the complete knowledge of the entities and their attributes. The main challenge of these methods is their inability to extract information about entities that are not already defined in the ontology. Besides, the existing methods have ignored semantic information extraction and have not linked the extracted information to the general ontology entries. This highlights that introducing new methods for semantic information extraction is an open problem and there is room for more efforts in this field. As an element of research, we proposed a new method for the automatic extraction of semantically structured information from Farsi web text. The proposed method does not require background knowledge about the entities and their properties. The proposed method consists of three main phases including pre-processing, semantic analysis and frame extraction. To fulfill these phases, we use a combination of language resources, text processing tools, and distant ontologies. The main focuses of the proposed method are to enrich the predicate-argument frames with the semantic information extracted from distant ontologies, extract the entity-related information from predicate-argument frames, and link the extracted information with their corresponding sense in DBPedia ontology. The issue facilitates the processing of Farsi texts by computers. To evaluate the proposed method, we created a small Farsi dataset containing 100 complete sentences. Then, the proposed method is compared with three information extraction methods on this dataset. The results of experiments show the superiority of the proposed method compared to counterpart methods in terms of precision and F1 measures.},  
Keywords = {Web mining, information extraction, natural language processing, ontology, structured-semantic information},
volume = {19},
Number = {2}, 
pages = {133-146}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.2.133},
url = {http://jsdp.rcisp.ac.ir/article-1-1102-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1102-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {javadzade, milad and Kahaei, Mohammad Hosein and BeheshtiShirazi, Aliasghar},  
title = {Fast Reconstruction of SAR Images with Phase Error Using Sparse Representation}, 
abstract ={In the past years, a number of algorithms have been introduced for synthesis aperture radar (SAR) imaging. However, they all suffer from the same problem: The data size to process is considerably large. In recent years, compressive sensing and sparse representation of the signal in SAR have gained a significant research interest. This method offers the advantage of reducing the sampling rate but also suffers from speed processing limitation and it needs a huge amount of memory to reconstruct the image. On the other hand, inaccuracy in SAR model induces phase error to the results and makes the reconstructed image blurry. Existing sparse methods in the presence of phase error, have high computational costs and need a lot of processing time. In addition, these methods take up considerable space in the memory for saving the measurement matrix. In this paper, a fast method is proposed to reduce the computational cost of image reconstruction, based on the signal sparsity in the presence of phase error. The proposed method consists of substituting accurate observations of sparsity methods with approximated observations of matched filter methods. In this method, the output of Range-Doppler matched filter is reconstructed with sparse representation, and error phase is estimated simultaneously. This method leads to a nonconvex optimization problem and to solve that, we use the majorization minimization method. The phase error and reconstructed image are estimated in an iterative procedure. The use of approximated observation, eliminates the need for carrying out big matrix multiplications, and Fast Fourier Transformation, as a low computational cost operation, can be employed instead. In addition to computation speed, this method does not need any memory space for saving measurement matrices. In our numerical simulations, we compared the speed of processing and the mean square error (MSE) of reconstructed images for the proposed method with the state-of-the-art sparse method for different sizes of image and under-sampling rates. It is shown in simulations that the reconstructed image from our method has a slightly lower quality and higher MSE, because of the sidelobes effect of the matched filter output. However, in certain conditions, the speed of the proposed method is more than a hundred times faster than the compared method. The achieved processing speed with no need for the memory to store the measurement matrix at the expense of slightly lower image quality would be acceptable for most applications.},  
Keywords = {Synthetic aperture radar, Compressed sensing, Sparsity, Range-Doppler algorithm},
volume = {19},
Number = {2}, 
pages = {147-160}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.2.147},
url = {http://jsdp.rcisp.ac.ir/article-1-1109-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1109-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Tohidi, Nasim and Hasheminejad, Seyed Mohammad Hossei},  
title = {Optimizing question answering systems by Accelerated Particle Swarm Optimization (APSO)}, 
abstract ={One of the most important research areas in natural language processing is Question Answering Systems (QASs). Existing search engines, with Google at the top, have many remarkable capabilities. However, there is a basic limitation; search engines do not have deduction capability which a QAS is expected to have. In this perspective, a search engine may be viewed as a semi-mechanized QAS. Upgrading a search engine such to a QAS is a task whose complexity is hard to exaggerate. To achieve success, new concepts and ideas are needed to address difficult problems which arise when knowledge has to be dealt with in an environment of imprecision, uncertainty and partial truth.  QASs are search engines that have the ability to provide a brief and accurate answer to each question in natural language for instance, the question that a search engine answers with a set of documents, a QAS answers with a paragraph, sentence or etc. In this paper, a solution is proposed to optimize the performance and speed of web-based QASs for answering English questions.  As evolutionary algorithms are suitable for issues with large search space, in this approach we have used an evolutionary algorithm to optimize QASs. In this regard, we have chosen APSO which is a simplified version of PSO. The proposed method consists of five main stages: question analysis, pre-process, retrieval, extraction and ranking. We have tried to provide a method that would be more accurate in choosing the most probable answer from the documents that have been retrieved by the standard search engine and at the same time, be faster than similar methods. In ranking process, various attributes can be extracted from the text that are used in APSO. For this purpose, in addition to selecting a sentence from the text and examining its attributes, different cut parts of the sentence are selected each time by changing the beginning and end points of the cut part. The attributes which have been used in this study are: 1. Number of unigrams similar to the question words, 2. Number of bigrams similar to the question words, 3. Number of unigrams similar to the question words in the cut part, 4. Number of bigrams similar to the question words in the cut part, 5. Number of synonyms with the question words and 6. Number of synonyms with the question words in the cut part. The fitness function is the weighted sum of these attributes. Top-1 accuracy and MRR are the most valid metrics for measuring the performance of QASs. The proposed method has achieved the accuracy (top-1 accuracy) of 0.527 with respect to the standard dataset and the MRR of it, is 0.711. Both of these results are improved compared to most similar systems. In addition, the time taken to answer the input question in the proposed method, has been significantly reduced compared to similar methods. In general, the accuracy and MRR in this paper have progressed and the system needs less time to find the answer, in comparison with existing QASs.},  
Keywords = {question answering system, natural language processing, accelerated particle swarm optimization (APSO)},
volume = {19},
Number = {2}, 
pages = {161-174}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.2.161},
url = {http://jsdp.rcisp.ac.ir/article-1-1098-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1098-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {ZareChahooki, Mohammad Ali and khalifehzadeh, zahr},  
title = {A General Investigation on the Combination of Local and Global Feature Selection Methods for Request Identification on Telegram}, 
abstract ={Nowadays, the use of various messaging services is expanding worldwide with the rapid development of Internet technologies. Telegram is a cloud-based open-source text messaging service. According to the US Securities and Exchange Commission and based on the statistics given for October 2019 to present, 300 million people worldwide used telegram per month. Telegram users are more concentrated in countries such as Iran, Venezuela, Nigeria, Kenya, Russia, and Ukraine. This messenger has become a popular and extensively used messenger because it supports various languages and provides diverse services such as creating groups and channels with a large number of users and members. There is a large amount of contextual data on telegram groups containing hidden knowledge; the extraction of this knowledge can be beneficial. The requests on telegram users' messages are examples of this sort of data with hidden knowledge. Hence, identifying requests can respond to users' needs and help them fulfill their desires immediately; this drives users' business development. The authors identified these requests in a telegram search engine named the Idekav system of Yazd University. Then, the authors created opportunities to earn money by sending these requests to the business owners who were able to respond to them. Given the high dimensions of feature space in contextual data, it is necessary to reduce attributes using feature selection.        In the present study, the appropriate features were selected for Persian text classification and request identification. Among the feature selection methods, two local and global filter-based methods were chosen. By general investigation and combining the most extensively used filter-based FS methods, an optimal subset of important features was obtained. This hybrid feature selection method resulted in increased request identification accuracy, improved Persian text classification efficiency, and reduced training time and computation by optimizing the feature reduction. Of course, it is noteworthy that the classification accuracy is reduced in some methods; however, this value is negligible compared to the feature reduction value. Incorporating the concept of opinion mining into the analysis of emotions and questions can be a method to identify positive or negative demand in social networks. Therefore, the requests in the Persian telegram messages can be identified using opinion mining researches. For experiments in the present article, a dataset called Persian is used, which is extracted from the Idekav system. The selection of suitable features to increase model accuracy in request identification is an important part of this research. The support vector machine was employed to calculate accuracy. Given the acceptable results of the SVM, its various kernels were also calculated. Micro-averaging and macro-averaging criteria were also used for evaluation. Model inputs include many optimal feature subsets. Furthermore, feature selection methods have been proposed to produce suitable features for each model for increasing the accuracy of the model. Afterward, among all the features investigated, appropriate features have been selected for each of the applied feature selection models. For a more precise explanation, the main innovations of the present study are as follows: Use of the most common filters based on local and global feature selection methods to find the optimal feature set. Use of hybrid methods to create suitable features for predictive models of accuracy in Persian text classification and their application in identifying requests in Persian messages on telegram. Selecting suitable features to increase accuracy and reduce computational time for each of the models under consideration. In this regard, in addition to picking an efficient algorithm, it is attempted to provide a method for making more appropriate choices. Evaluation and testing of the proposed models for a large set of Persian data and many different features.},  
Keywords = {Feature Selection, Text mining, Classification Accuracy, Machine Learning},
volume = {19},
Number = {2}, 
pages = {175-196}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.2.175},
url = {http://jsdp.rcisp.ac.ir/article-1-1110-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1110-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Ravaei, Bahman and Rahimizadeh, Keyv},  
title = {Design an Efficient Community-based Message Forwarding Method in Mobile Social Networks}, 
abstract ={Mobile social networks (MSNs) are a special type of Delay tolerant networks (DTNs) in which mobile devices communicate opportunistically to each other. One of the most challenging issues in Mobile Social Networks (MSNs) is to design an efficient message forwarding scheme that has a high performance in terms of delivery ratio, latency and communication cost. There are two different approaches for message forwarding: the single copy and the multi copy. In the single copy schemes, only one copy of a message exists in the network, which is carried by a custodian relay. On the other hand, in multi copy schemes more than one copy of the message exist. Although the multi copy schemes generally have superior performance in terms of delivery ratio and latency, they incur high congestion in the network, which consequently degrades the network performance and increases message forwarding cost. Therefore, we present a scheme for managing the number of replica and selecting appropriate relays in order to increase the performance and decrease the forwarding cost. In this paper, we present a novel message forwarding scheme, named Multi Copy Community Aware Forwarding (MCCAF), for managing the number of message replicas and selecting appropriate relays in order to increase the performance and decrease the forwarding cost. MCCAF only forwards one replica of message to each community that the destination node belongs to it. In order to find communities and nodes’ future communities, MCCAF exploits a hidden semi-Markov model (HSMM). In the proposed method, hidden states represent communities and environmental chronological information such as location, visited nodes and access points are modeled as observation in HSMM. To have a more precise community prediction, the semi-Markov model is extended to compute the likelihoods of a node being in a particular community after N transitions. After that, appropriate relays are selected to forward a message with taking into account the message expiration time, future communities of relays and the number of message replica. Evaluation results on real traces demonstrate that the MCCAF has superior performance over rival schemes in terms of delivery ratio, latency, and forwarding cost. Specifically, MCCAF yields on average about 8% better delivery ratio and about 23% less delivery delay than the nearest rival method.},  
Keywords = {Forwarding, routing, mobile social networking, multi copy, community, hidden semi-Markov model},
volume = {19},
Number = {3}, 
pages = {1-18}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.3.1},
url = {http://jsdp.rcisp.ac.ir/article-1-1150-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1150-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Shahrouz, Elahe and Tahmoresnezhad, Jafar},  
title = {Image alignment via kernelized feature learning}, 
abstract ={Machine learning is an application of artificial intelligence that is able to automatically learn and improve from experience without being explicitly programmed. The primary assumption for most of the machine learning algorithms is that the training set (source domain) and the test set (target domain) follow from the same probability distribution. However, in most of the real-world applications, this assumption is violated since the probability distribution of the source and target domains are different. This issue is known as domain shift. Therefore, transfer learning and domain adaptation generalize the model to face target data with different distribution. In this paper, we propose a domain adaptation method referred to as IMage Alignment via KErnelized feature learning (IMAKE) in order to preserve the general and geometric information of the source and target domains. IMAKE finds a common subspace across domains to reduce the distribution discrepancy between the source and the target domains. IMAKE adapts both the geometric and the general distributions, simultaneously. Moreover, IMAKE transfers the source and target domains into a shared low dimensional subspace in an unsupervised manner. Our proposed method minimizes the marginal and conditional probability distribution differences of the source and target data via maximum mean discrepancy and manifold alignment for geometrical distribution adaptation. IMAKE maps the input data into a common latent subspace via manifold alignment as a geometric matching method. Therefore, the samples with the same class labels are collected around their means, and samples with different class are separated, as well. Moreover, IMAKE maintains the source and target domain manifolds to preserve the original data position and domain structure. Also, the use of kernels and mapping data into Hilbert space provides more accurate separation between different classes and is suitable for data with complex and unbalanced structures. The proposed method has been evaluated using a variety of benchmark visual databases with 36 experiments. The results indicate the significant improvements of the proposed method performance against other machine learning and transfer learning approaches.},  
Keywords = {Image classification, Transfer learning, Visual domain adaptation, Manifold alignment, Distribution mismatch},
volume = {19},
Number = {3}, 
pages = {19-34}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.3.19},
url = {http://jsdp.rcisp.ac.ir/article-1-1076-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1076-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Keshvari, Ruhollah and Imani, Maryam and ParsaMoghaddam, Mohse},  
title = {Short Term Load Forecasting Using Empirical Mode Decomposition, Wavelet Transform and Support Vector Regression}, 
abstract ={The Short-term forecasting of electric load plays an important role in designing and operation of power systems. Due to the nature of the short-term electric load time series (nonlinear, non-constant, and non-seasonal), accurate prediction of the load is very challenging. In this article, a method for short-term daily and hourly load forecasting is proposed. In this method, in the first step, the intrinsic mode functions (IMFs) of the Electric load curve, which are a group of average and pseudo-periodic average signals, are extracted by using the empirical mode decomposition (EMD) method, which is a non-linear and non-constant time-frequency method. For this purpose, the maximum and minimum points of the signal are determined, and then, in one cycle, the difference between the average curve of the upper and lower envelope is calculated with it. This continues until the result falls below a threshold value, and then, the rest of the signal which contains noise is discarded to get a relatively clean signal. In the second step, we need to obtain the sub-sequences of each IMF. So, we use the wavelet transform. The wavelet transform is a kind of transform that is used to decompose a continuous signal into its frequency components, and the resolution of each component is equal to its scale. Each subsequence contains different information and details that can help the improvement of the prediction accuracy. In the third step, the obtained subsequences are aggregated and finally used for prediction by Support Vector Regression (SVR). Support vector regression is a type of supervised learning system that is used for both grouping and estimating the fitting function of data in regression problems so that the least error occurs in the grouping of data or in the fitting function. The purpose of the proposed method is to reduce the error for daily and hourly load prediction. In this method, two datasets of Poland and Canada have been experimented. With four criteria of mean square error (MSE), root mean square error (RMSE), average absolute percentage error (MAPE) and mean absolute error (MAE), the results are evaluated. The findings show that the load prediction error for the Polish data set are as follows: MSE equal to 0.0012, RMSE equal to 0.0342, MAPE equal to 2.9771, and MAE equal to 0.0044. For Canadian data set, the results are as follows: MSE equal to 5.0969e-07, RMSE equal to 7.1393e-04, MAPE criterion equal to 0.9571, and the MAE criterion equal to 2624e-04. Comparison of the proposed method with other competing methods show that better results are achieved by the proposed method in term of the error rate.},  
Keywords = {Short-term electrical load forecasting, Electricity demand, empirical mode decomposition, wavelet transform, support vector regression},
volume = {19},
Number = {3}, 
pages = {35-48}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.3.35},
url = {http://jsdp.rcisp.ac.ir/article-1-1138-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1138-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Tobeiha, Atefeh and Behzadfar, Neda and Yousefi-Najafabadi, Mohamadreza and Mahdavi-Nasab, Homayon and Shahgholian, Ghazanfar},  
title = {Choosing the Distinguishing Frequency Feature of People Addicted to Heroin from Healthy while Resting}, 
abstract ={Addiction is a biological, psychological, and social disease. Several factors are involved in etiology, substance abuse, and addiction which interact with each other and lead to the beginning of drug use and then addiction. Heroin is an addictive drug that, by acting on the central nervous system, reduces the density of neurons in the brain and interferes with decision making. This paper examines the effects of heroin on brain function by studying the relationship between spectral strength of electroencephalogram (EEG) signal and heroin abuse. For this purpose, the resting EEG signal and cognitive activity of 15 healthy individuals and 15 heroin addicts were recorded in 16 channels in one session. The frequency range of EEG signal sub-bands was calculated separately for each individual. Welch method has been used to extract the power of EEG signal frequency sub-bands. The extracted features were examined using Mann-Whitney test and Davies-Bouldin index. The results show that the heroin-dependent group has higher power in delta (in the frontal, central and temporal regions) and theta (in all canals) than in the control group. In the heroin-dependent group, the power of alpha decreased compared to the control group. High alpha sub-bands power in the frontal, temporal and central lobes compared to other frequency sub-bands, as well as in the central, parietal and temporal lobes, the power of the second low alpha sub-band in decreased addicts. According to Davies-Bouldin, the power of the second low alpha sub-band in the T6 channel has a better power to differentiate between healthy and heroin-dependent people.},  
Keywords = {Heroin addiction, EEG signal, frequency characteristics, power, Davis- Boldin index},
volume = {19},
Number = {3}, 
pages = {49-64}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.3.49},
url = {http://jsdp.rcisp.ac.ir/article-1-1149-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1149-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {AzimiFar, Maryam and Nejatian, Samad and Parvin, Hamid and BagheriFard, Karamollah and Rezaei, Vahideh},  
title = {Predicting cardiac arrhythmia on ECG signal using an ensemble of optimal multicore support vector machines}, 
abstract ={The use of artificial intelligence in the process of diagnosing heart disease has been considered by researchers for many years. In this paper, an efficient method for selecting appropriate features extracted from electrocardiogram (ECG) signals, based on a genetic algorithm for use in an ensemble multi-kernel support vector machine classifiers, each of which is based on an optimized genetic algorithm is proposed. It has already been shown that due to its features (feature space mapping and decision boundary maximization), support vector machine classification is one of the classification methods that are suitable for any type of environment. This paper uses a number of multi-kernel support vector machine classifiers as an ensemble classifier. ensemble diversity is created by teaching each multi-kernel support vector machine classifier on a subspace (ie, a subset of features). In this method, the majority vote method is used to combine the output of the categories. On the other hand, in the classification of ECG signals, signals are usually used as their characteristics; As a result, since the methods of classifying signals are faced with a large number of features, and not removing these features creates a problem of high dimensions and also increases the computational for the intended application, the step of selecting the feature is inevitable. The extracted features include temporal properties, AR, and wavelet coefficients, the number of which will be optimized using a genetic algorithm. The evaluation of this set of features selected by the genetic algorithm is examined by applying it to a multivariate SVM. A genetic algorithm is used to optimize the parameters of each of the SVMs. Indicates the desired method. With the help of computer simulation, the overall accuracy of the system for identifying 6 types of heart rhythms is 99.15%, which in comparison with the accuracy obtained with previous research, shows the optimal performance of the proposed method.},  
Keywords = {ElectroCardioGram Signals, Feature Selection, Multiple Support Vector Machine, Esemble classification, Genetic Algorithm},
volume = {19},
Number = {3}, 
pages = {65-86}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.3.65},
url = {http://jsdp.rcisp.ac.ir/article-1-1128-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1128-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {SeyedRezaie, Morteza and Kheradmandian, Ghorban and KazemitabarAmirkolaie, Jav},  
title = {Detecting Suspicious Card Transactions in unlabeled data of bank Using Outlier Detection Techniqes}, 
abstract ={With the advancement of technology, the use of ATM and credit cards are increased. Cyber fraud and theft are the kinds of threat which result in using these Technologies. It is therefore inevitable to use fraud detection algorithms to prevent fraudulent use of bank cards. Credit card fraud can be thought of as a form of identity theft that consists of an unauthorized access to another person's card information for the purpose of charging purchases to the account or removing funds from it. Credit card fraud schemes are divided into two categories: application fraud and account takeover. When a credit card account gets opened without someone’s permission is called application fraud. Account takeovers, on the other hand, is when an existing credit card account is hijacked, and the criminal obtains enough personal information to modify the account's information. The criminal then subsequently reports the card lost or stolen in order to obtain a new card and make unauthorized purchases with it. Data mining as a technique capable of identifying useful patterns among a great deal of data is an effective method in detecting fraud in this regard. The main purpose of this paper is to present a new method for detecting unattended outliers that require high accuracy and recall. The method presented in this study is based on a combination of NMF, hierarchical k-means, k-means and k-nearest neighbors’ techniques. To evaluate the proposed method of outlier detection, several experiments were performed using standard data, in terms of accuracy and recall with Isolation Forest, k-nearest neighbors, Median kNN, and Average kNN. The dataset used in this paper is one that was provided in a 2016 Kaggle competition and was provided by a European bank after anonymization. The results, corroborate that the proposed method has higher accuracy and recall than other algorithms.},  
Keywords = {Fraud detection, Data mining, Outlier detection, hierarchical k means, NMF},
volume = {19},
Number = {3}, 
pages = {87-104}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.3.87},
url = {http://jsdp.rcisp.ac.ir/article-1-1125-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1125-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Hamidzadeh, Javad and Moradi, Mo},  
title = {Improving Chernoff criterion for classification by using the filled function}, 
abstract ={Linear discriminant analysis is a well-known matrix-based dimensionality reduction method. It is a supervised feature extraction method used in two-class classification problems. However, it is incapable of dealing with data in which classes have unequal covariance matrices. Taking this issue, the Chernoff distance is an appropriate criterion to measure distances between distributions. In the proposed method, for data classification, LDA is used to extract most discriminative features but instead of its Fisher criterion, the Chernoff distance is employed to preserve the discriminatory information for the several classes with heteroscedastic data. However, the Chernoff distance cannot handle the situations where the component means of distributions are close and leads to the component distribution overlap and underperforming classification. To overcome this issue, the proposed method designs an instance selection method that provides the appropriate covariance matrices. Aiming to improve LDA-based feature selection, the proposed method includes two phases: (1) it removes non-border instances and keeps border ones by introducing a maximum margin sampling method. The basic idea of this phase is based on keeping the hyperplane that separates a two-class data and provides large margin separation. In this way, the most representative instances are selected. (2) It extracts features on selected instances by the proposed extension of LDA which generates a desirable scatter matrix to increase the efficiency of LDA. In the proposed method, the instance selection process is considered a constrained binary optimization problem with two contradicting objects, and the problem solutions are obtained by using a heuristic method named filled function. This optimization method does not easily get stuck in local minima; meanwhile, it is not affected by improper initial points. The performance of the proposed method on data collected from the UCI database is evaluated by 10-fold validation. The results of experiments are compared to several competing methods, which show the superiority of the proposed method in terms of classification accuracy percentage and computational time.},  
Keywords = {Chernoff criterion, Data classification, Instance selection, Filled function, Maximum margin},
volume = {19},
Number = {3}, 
pages = {105-118}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.3.105},
url = {http://jsdp.rcisp.ac.ir/article-1-1126-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1126-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Geravanchizadeh, Masoud and Mobasheri, Parisa and JamshidiAvanaki, Hadi},  
title = {Classification of Iranian Traditional Music Dastgahs Using Features Based on Pitch Frequency}, 
abstract ={The Iranian traditional music is composed of seven majors Dastgahs: Chahargah, Homayoun, Mahour, Segah, Shour, Nava, and Rast-Panjgah. In this paper, a new algorithm for the classification of the Iranian traditional music Dastgahs based on pitch frequency is proposed. In this algorithm, the features of Lagrange coefficients of pitch logarithm (LCPL), Fuzzy similarity sets type 2 (FSST2), and their combination are used as the representation of music signals which are fed into the multi-class support vector machine (MSVM) as the classifier. The features of LCPL and FSST2 are obtained by applying some modifications on the pitch frequency of the desired music. To compute LCPL, first, the values of pitch frequency are extracted by the PRAAT algorithm. Then, after the applying a logarithmic operation, the tracks of pitch frequency are partitioned into smaller segments. The method of feature extraction is based on detecting the trough or valley points of the pitch tracks. In the following, the coordinates of trough points (i.e., the index of pitch frequency and the logarithmic value of the frequency) are considered as each segment boundaries. In the next step, the track between the two boundaries of each segment is approximated by a 6th order Lagrange polynomial and the computed polynomial coefficients are considered as a 6-dimensional feature vector. The first step in extracting the FSST2 feature is to compute the pitch frequencies of the input signal by the PRAAT algorithm. The second step involves the classification of music notes. Then, the subtractive clustering method is used to eliminate the incorrectly estimated pitch frequencies of the previous step. Next, the process of folding notes (i.e., transferring the extracted pitch frequencies into the reference octave band of 220-440 Hz) is performed followed by translating the frequency points to the cents with respect to 220 Hz. After folding notes in one octave, the Mahalanobis distance is applied to recognize which point on the reference octave corresponds to each musical note. These same procedures are conducted for the information pattern (theoretical data) of each Dastgah. In the final step, the folded frequency points of the unknown input signal and the information pattern of all Dastgahs are transferred to the Fuzzy logicType-2 domain and compared to determine a similarity measure which is considered as the extracted feature. The dataset used in the proposed classification algorithm contains the excerpts from solo performances with Tar played by Alizadeh, the well-known Iranian music master. The performances of the baselines and proposed classification algorithms are evaluated by the measures of Accuracy, Recall, Precision, F-measure, and MCC. The results show that the proposed algorithm has a better performance as compared with the baseline methods in terms of different classification criteria.},  
Keywords = {Music Classification, Pitch Frequency, Fuzzy Logic Type 2, MSVM, Iranian Music Dastgahs},
volume = {19},
Number = {3}, 
pages = {119-134}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.3.119},
url = {http://jsdp.rcisp.ac.ir/article-1-1155-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1155-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Ashoori, Zahra and Azimpour, Jalil and Mazarei, Has},  
title = {Using a Fuzzy Rule-based Algorithm to Improve Routing in MPLS Networks}, 
abstract ={Today, the use of wireless and intelligent networks are widely used in many fields such as information technology and networking. There are several types of these networks that MPLS networks are one of these types. However, in MPLS networks there are issues and problems in the design and implementation discussion, for example security, throughput, losses, power consumption and so on. Basically, the performance parameters of MPLS networks are directly dependent on the type of routing performed between these networks. In this paper, a routing algorithm for energy-based routing in MPLS networks is presented which performs routing online with increasing number of requests. This algorithm guarantees bandwidth and end-to-end delay and its performance is based on the Minimum Delay and Maximum Flow (MDMF) algorithm. The purpose of this algorithm is to uniformly distribute the load across the network for all requests and to delay high-bandwidth requests and maximum end-to-end delay using a fuzzy law-based approach. In addition, the proposed algorithm optimizes the use of resources and increases the number of requests accepted. In the proposed routing algorithm, the weight of each link of the network graph is first calculated based on a multi-objective weighted sum maximization problem. The weight of links must be calculated in such a way as to determine the shortest path weighted by the sum of the minimum weights in the graph. Then, links which their residual bandwidth is less than the requested bandwidth are removed from the grid graph and in the residual subgraph, the shortest weighted path between the input-output nodes is calculated using Dijkstra algorithm and based on the weights of each link. Therefore, this algorithm only requires the remaining capacity information of the links, where assumed this information is always available. The proposed method is implemented in MATLAB software and the results show a decrease in energy consumption and improvement of network performance parameters compared to similar methods.},  
Keywords = {MPLS Networks, Energy-Based Routing, Rule-Based Fuzzy Algorithm, Bandwidth, End-to-End Delay},
volume = {19},
Number = {3}, 
pages = {135-146}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.3.135},
url = {http://jsdp.rcisp.ac.ir/article-1-1073-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1073-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Bahrani, Payam and MinaeiBidgoli, Behrouz and Parvin, Hamid and Mirzarezaee, Mitra and Keshavarz, Ahm},  
title = {Hybrid Recommender System Based on Variance Item Rating}, 
abstract ={K-nearest neighbors (KNN) based recommender systems (KRS) are among the most successful recent available recommender systems. These methods involve in predicting the rating of an item based on the mean of ratings given to similar items, with the similarity defined by considering the mean rating given to each item as its feature. This paper presents a KRS developed by combining the following approaches: (a) Using the mean and variance of item ratings as item features to find similar items in an item-wise KRS (IKRS); (b) Using the mean and variance of user ratings as user features to find similar users with a user-wise KRS (UKRS); (c) Using the weighted mean to integrate the ratings of neighboring users/items; (d) Using ensemble learning. Three proposed methods EVMBR, EWVMBR and EWVMBR-G are presented in this paper. All three methods are user-based, in which VM distance is used as a measure of the difference between users / items, to find neighboring users / items, and then the weighted average is weighted, respectively. Also, weights based on the Gaussian combined covariance model are used to predict unknown user ratings. Our empirical evaluations show that the proposed method EVMBR, EWVMBR and EWVMBR-G, which utilizes ensemble learning, are the most accurate among the methods evaluated. Depending on the dataset, the proposed method EWVMBR-G managed to achieve 20 to 30 percent lower mean absolute error than the original MBR. In terms of runtime, the proposed methods are comparable to the MBR and much faster than the slope-one method and the cosine- or Pearson-based KNN recommenders.},  
Keywords = {K-Nearest Neighbor, Rating, Variance, Recommender System},
volume = {19},
Number = {3}, 
pages = {147-162}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.3.147},
url = {http://jsdp.rcisp.ac.ir/article-1-1244-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1244-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Dorvashi, Maryam and Behzadfar, Neda and Shahgholian, Ghazanfar},  
title = {Detection of Fatigue from Electroencephalogram Signal During Neurofeedback Training}, 
abstract ={Timely diagnosis of fatigue helps to improve the quality and effectiveness of neurofeedback training. Neurofeed­back training (NFT) is a method that can change brain activity by altering brain signal fluctuations and teaches individuals to produce or reproduce their brain activity patterns in order to improve performance. Neurofeedback training has been widely utilized over the recent years owing to its considerable effect on the cognitive processes. Fatigue during NFT is one of factors affecting the functioning and achievement of NFT which results in decreased learning ability. Timely diagnosis of fatigue during NFT preserves quality of NFT. Decreased learning ability reduces individuals' motivation for learning during NFT. In this paper, 12 participants` electroencephalogram signals were investigated to detect fatigue during NFT. Two training protocols named protocol 1 and 2 have been designed to improve working memory. Each protocol includes 6 participants and 10 training sessions that each session takes three 10-minute training intervals. Training features in protocol 1 are increased in power of lower2 alpha frequency band in OZ channel and permutation entropy reduction in FZ channel, while protocol 2`s training feature is increased in power of lower2 alpha frequency band in OZ channel. Occurrence of fatigue during NFT changes trend of training features. Changing of training features slope will decrease or become opposite to the goal of NFT. Therefore, examining trend of training features slope is a novel approach in detection of fatigue during NFT. During the occurrence of fatigue, in protocol 1, trend of power of lower2 alpha frequency band`s slope in the OZ channel is decreasing and the trend of entropy` s slope in the FZ channel is increasing. Consequently, the trend of score`s slope is also decreasing. Also in the protocol 2, the trend of power of lower 2 alpha frequency band`s slope in the OZ channel and score is decreasing. This shows that training features do not change in line with the neurofeedback`s goal. Fatigue was detected for 3 subjects in the protocol 1 and 1 subject in the protocol 2. Occurrence of fatigue was less in protocol 1 compared with protocol 2 since Protocol 1 `s training features are combination of frequency and non-frequency features, while the Protocol 2 `s training feature is only frequency feature. Detection of fatigue during NFT is an essential issue which contributes to increase in the effect of training and participants` performance.},  
Keywords = {neurofeedback training, training feature, electroencephalogram signal, fatigue},
volume = {19},
Number = {3}, 
pages = {163-174}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.3.163},
url = {http://jsdp.rcisp.ac.ir/article-1-1140-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1140-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Farhoodi, Mojgan and Mahmoudi, Maryam and Davoudi, Mo},  
title = {Producing a Persian Text Tokenizer Corpus Focusing on Its Computational Linguistics Considerations}, 
abstract ={The main task of the tokenization is to divide the sentences of the text into its constituent units and remove punctuation marks (dots, commas, etc.). Each unit is a continuous lexical or grammatical writing chain that is an independent semantic unit. Tokenization occurs at the word level and the extracted units can be used as input to other components such as stemmer. The requirement to create this tool is to identify and recognize the units that are known as independent semantic units in Persian language. This tool detects word boundaries in texts and converts the text into a sequence of words. In the English language, many activities have been done in the field of text tokenization and many tools have been development; such as: Stanford, Ragel, ANTLR, JFLex, JLex, Flex and Quex. In recent decades, valuable researches have also been conducted in the field of tokenization in Persian language that all of them have worked on the lexical and syntactic layer. In the current research, we tried to focus on the semantic layer in addition to those two layers. Persian texts usually have two simple but important problems. The first problem is multi-word tokens that result from connecting one word to the next. Another problem is polysyllabic units, which result from the separation of words that together form a lexical unit.  Tokenizer is one of the language preprocessing tools that is widely used in text analysis. This component recognizes the center of words in texts and turns it into a sequence of words for later analysis. Variety in Persian script and non-observance of the rules of separation and spelling of words on the one hand and the lexical complexities of Persian language on the other hand, different language processing such as tokenization face many challenges. Therefore, in order to obtain the optimal performance of this tool, it is necessary to first specify the computational linguistics considerations of tokenization in Persian and then, based on these considerations, provide a data set for training and testing. In this article, while explaining the mentioned considerations, we tried to prepare a data set in this regard. The prepared data set contains 21.183 tokens and the average length of sentences is 40.28.},  
Keywords = {Persian text tokenization corpus, Natural Language Processing (NLP), cyber linguistic},
volume = {19},
Number = {3}, 
pages = {175-188}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.52547/jsdp.19.3.175},
url = {http://jsdp.rcisp.ac.ir/article-1-1169-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1169-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2022}  
}

@article{ 
author = {Nourollahi, Hamid and Hosseini, S. Abolfazl and Shahzadi, Ali and ShaghaghiKandovan, Rami},  
title = {Signal detection  Using Rational Function Curve Fitting}, 
abstract ={In this manuscript, we proposed a new scheme in communication signal detection which is respect to the curve shape of received signal and based on the extraction of curve fitting (CF) features. This feature extraction technique is proposed for signal data classification in receiver. The proposed scheme is based on curve fitting and approximation of rational fraction coefficients. For each symbol of received signal, a specific rational function approximation is developed to fit with received signal curve and the coefficients of the numerator and denominator polynomials of this function are considered as new extracted features. Then  it will be shown that the coefficients of this polynomials have the potential for using as new features in a statistical classifier and have better performance in competition with other solutions such as linear and even nonlinear feature extraction methods in  classification. The criteria used in performance evaluation are  probability of error and signal to noise ratio in FSK and ASK modulations. For each symbol of received signal, a specific rational function approximation is developed to fit with received signal curve and the coefficients of the numerator and denominator polynomials of this function are considered as new extracted features. In the proposed method, there are two phases train and test, which are described in the following two steps. First, in the train phase, the algorithm starts by using binary FSK and ASK modulations, so first, a system generate a number of random symbols then signal is modulated by binary ASK and FSK. The Modulated FSK and ASK signals are corrupted in the channel with noise. The noise-corrupted signal enters the receiver at the corresponding transmitted interval. Then, the samples are extracted from the modulated signals based on predetermined sample rates. Then, we fit a rational fraction curve with degrees of L and M to each set of N samples. Afterward, we apply all the numerator (L+1) and denominator (M) coefficients to 0 and 1 classes  in the binary FSK and ASK modulations. We store all the specific coefficients of the deterministic symbols at different M and L values to create the corresponding histogram in each class. In each histogram (i.e., the coefficients of a class), we extract and store specific coefficients that completely discriminate between the two classes. Therefore, we determine all the histograms where there is a good approximation of discrimination and create the related table. Note that the data used in histograms are the training data. Then, in order to analyze and evaluate the performance of the proposed curve fitting method, we send the testing data through the channel corresponding to the related modulator. The results of the proposed classification method show that it provides smaller error rate regarding to the theoretical error rate probability in AWGN channel.  },  
Keywords = {detection, feature extraction, curve fitting, classification},
volume = {19},
Number = {4}, 
pages = {3-18}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.61186/jsdp.19.4.3},
url = {http://jsdp.rcisp.ac.ir/article-1-1182-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1182-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2023}  
}

@article{ 
author = {Sharifnezhad, Mona and Rahmani, Mohsen and Ghafarian, Hosei},  
title = {A New Framework for Distributed Multivariate Feature Selection}, 
abstract ={Feature selection is considered as an important issue in classification domain. Selecting a good feature through maximum relevance criterion to class label and minimum redundancy among features affect improving the classification accuracy. However, most current feature selection algorithms just work with the centralized methods. In this paper, we suggest a distributed version of the mRMR feature selection approach. In mRMR, feature selection is performed based on maximum relevance to class and minimum redundancy among the features. The suggested method include six stages: in the first stage, after determining training and test data, training data are distributed horizontally. All subsets have same number of features. In the second stage, each subset of features is scored using mRMR feature selection. Features with higher ranks are selected and others are eliminated. In the fourth stage, features which were omitted are voted. In the fifth stage, the selected features are merged to determine the final set. In the final stage, classification accuracy is evaluated using final training data and test data. Our method quality has been evaluated by six datasets. The results prove that the suggested method can improve classification accuracy compared to methods just based on maximum relevance to class label in addition to runtime reduction.},  
Keywords = {Multivariate filter feature selection, Embedded feature selection, Classification, Distribution},
volume = {19},
Number = {4}, 
pages = {19-32}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.61186/jsdp.19.4.19},
url = {http://jsdp.rcisp.ac.ir/article-1-1156-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1156-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2023}  
}

@article{ 
author = {Pejhan, Elham and Ghasemzadeh, Mohamm},  
title = {Improvement of generative adversarial networks for automatic text-to-image generation}, 
abstract ={This research is related to the use of deep learning tools and image processing technology in the automatic generation of images from text. Previous researches have used one sentence to produce images. In this research, a memory-based hierarchical model is presented that uses three different descriptions that are presented in the form of sentences to produce and improve the image. The proposed scheme focuses on using more information to produce high-resolution images, using competitive productive networks. Implementing programs related to this field require massive processing resources. Therefore, the proposed method was implemented and tested on a cluster with 25 GPUs using the hardware platform of the University of Copenhagen. The experiments were performed on CUB-200 and ids-ade datasets. The experimental results show that the proposed model can produce higher quality images than the two basic models StackGAN and AttGAN.},  
Keywords = {Generative Adversarial Network, Deep Learning, Hierarchical Model, Natural Language Processing},
volume = {19},
Number = {4}, 
pages = {33-44}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.61186/jsdp.19.4.33},
url = {http://jsdp.rcisp.ac.ir/article-1-1170-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1170-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2023}  
}

@article{ 
author = {Dehklharghani, Rahim and Emami, Hojat},  
title = {Verification of unemployment benefits’ claims using Classifier Combination method}, 
abstract ={Unemployment insurance is one of the most popular insurance types in the modern world. The Social Security Organization is responsible for checking the unemployment benefits of individuals supported by unemployment insurance. Hand-crafted evaluation of unemployment claims requires a big deal of time and money. Data mining and machine learning as two efficient tools for data analysis can assist Social Security Organization in automating this process. In this research work, a hybrid supervised learning method is proposed to verify the eligibility of applicants for unemployment. The proposed method takes as input the information of insured individuals, and assigns a numeric score to each applicant through analyzing the input data. Then, claimants are classified into two groups according to those scores: "Qualified” and "Unqualified". The proposed method includes two hybrid strategies: BSA-SVM and combination of confidence values. In BSA-SVM method, backtracking search algorithm (BSA) is used to estimate the prameters of support vector machines (SVM) and improves the classification performance. In the second approach, confidence values extracted from individual classofiers are combined to better classify the input data. Empirical evaluation shows an accuracy of 87% for BSA-SVM and 86% for the second approach.},  
Keywords = {Unemployment benefits, data mining, machine learning, supervised learning, BSA-SVM, classifier combination.},
volume = {19},
Number = {4}, 
pages = {45-60}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.61186/jsdp.19.4.45},
url = {http://jsdp.rcisp.ac.ir/article-1-1011-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1011-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2023}  
}

@article{ 
author = {Mahmoudi-Nasr, Payam},  
title = {An Authorization Framework for Database Systems}, 
abstract ={Today, data plays an essential role in all levels of human life, from personal cell phones to medical, educational, military and government agencies. In such circumstances, the rate of cyber-attacks is also increasing. According to official reports, data breaches exposed 4.1 billion records in the first half of 2019. An information system consists of several components, which one of the most important them is the database. A database in addition to being a repository of data, acts as a common information bus between system components. For this reason, any attack on the database may disrupt the operation of other components of the system. In fact, database security is shared throughout the whole information system. The attack may carried out in various ways, such as data theft, damaging data, and privacy breach. According to the sensitivity of the stored data, database attack could lead to significant human and financial losses even at the national level. Among the different types of threats, since legitimate operator plays a key role in an information system, his/her threat is one of the most dangerous threats to the security and integrity of a database system. This type of cyber-attack occurs when an insider operator abuses his/her legal permissions in order to access unauthorized data. In this paper, a new performance-based authorization framework has been presented which is able to reduce the potential of insider threat in the database system. The proposed method insure that only authenticated operator performs authorized activities on the database objects. In the proposed framework, the access permission of the operator to a database table is determined using his/her performance and the level of sensitivity of the table. The value of the operator performance is updated periodically or when an abuse is detected, in order to protect access to the contents of a database as well as preserve the consistency, integrity, and overall quality of the data. Simulation results, using real dataset from a hospital information system, indicate that the proposed framework has effective performance for mitigating insider threats.},  
Keywords = {Access control, Authorization, cyber security, database, insider threat},
volume = {19},
Number = {4}, 
pages = {61-70}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.61186/jsdp.19.4.61},
url = {http://jsdp.rcisp.ac.ir/article-1-1167-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1167-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2023}  
}

@article{ 
author = {NorouzzadehGilmolk, Ali Mohammad and Aref, Mohammad Reza and RamazaniKhorshidoust, Rez},  
title = {Design of cybernetic metamodel of cryptographic algorithms and ranking of its supporting components using ELECTRE III method}, 
abstract ={Nowadays, achieving desirable and stable security in networks with national and organizational scope and even in sensitive information systems, should be based on a systematic and comprehensive method and should be done step by step. Cryptography is the most important mechanism for securing information. a cryptographic system consists of three main components: cryptographic algorithms, cryptographic keys, and security protocols, which are mainly based on cryptographic algorithms. In designing a cryptographic algorithm, all the necessary components of information security must be considered in a model of excellence in technical, organizational, procedural and human aspects. To meet these needs, we must first extract the effective components in the design and implementation of cryptographic algorithms based on a model and then determine the impact of the components. In this paper, we use cybernetic methodology to prepare a   metamodel.   The cryptographic cybernetics metamodel has four components: " strategy / policy ", "main process", "support process" and "control process". The "main process" has four stages and also, the "suport process" includes 13 components of hardware and software. The interactions of these two processes shape its structure, leading to a complex graph. To prioritize suport components for resource allocation and cryptography strategy, it is necessary to rank these components in the designed metamodel. To overcome this complexity in order to rank the support components, we use the ELECTRE III method, which is a multi-criteria decision-making method. The results show that the components with high priority for the development of the cryptographic system are: Research and Development, Human Resources, Management, Organizational, Information and Communication Technology, Rrules and Regulations and standards. These results are consistent with reports published by the ITU in 2015, 2017 and 2018.},  
Keywords = {Cryptographic algorithms, Metamodel, Cybernetics, MCDM, ELECTRE III.},
volume = {19},
Number = {4}, 
pages = {71-84}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.61186/jsdp.19.4.71},
url = {http://jsdp.rcisp.ac.ir/article-1-1171-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1171-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2023}  
}

@article{ 
author = {Alizadeh, Javad and Bagheri, Nasour},  
title = {Some observations on a lightweight authentication scheme with capabilities of anonymity and trust in Internet of Things (IoT)}, 
abstract ={Over the last years‎, ‎the concept of Internet of Things (IoT) leads to a revolution in the communications of humans and things. ‎Security and efficiency could be the main challenges of that communication‎‎. ‎‎On the other hand, ‎ authenticity and confidentiality are two important goals to provide desired security in an information system‎, including IoT-based applications. An Authentication and Key Agreement (AKA) protocol is a tool to ‎achieve authenticity and agree on a secret key to reach confidentiality. Therefor using a secure AKA protocol, one can establish the mentioned security. ‎In the last years‎, ‎several articles have discussed AKA protocols in the WSN‎. ‎For example‎, ‎in 2014‎, ‎Turkanovic et al‎. proposed a new AKA scheme for the heterogeneous ad-hoc WSN. ‎In 2016‎, ‎Sabzinejad et al‎. presented an improved one. ‎In 2017‎, ‎Jiang et al‎. introduced a secure AKA protocol‎. ‎Some other AKA protocols have presented in the last three years. ‎All the mentioned protocols are lightweight ones and need minimum resources and try to decrease the computation and communication costs in the WSN context‎. ‎In 2019‎, ‎Janababaei et al. proposed an AKA scheme in the WSN for the IoT applications, in the journal of Signal and Data Processing (JSDP)‎. ‎In the context of efficiency‎, ‎the protocol only uses a hash function‎, ‎bitwise XOR‎, ‎and concatenation operation‎. ‎Hence‎, ‎it can be  considered as a lightweight protocol‎. ‎The authors also discussed the security of their scheme and claimed that the proposed protocol has the capability  to offer anonymity and trust and is secure against traceability‎, ‎impersonation‎, ‎reply and man in the middle attacks‎. ‎However, despite their claims‎, ‎this research highlights some vulnerabilities in that protocol, for the first time to the best of our knowledge‎. More precisely, we showe that a malicious sensor node can find the secret parameters of another sensor node when it establishes a session with the victimized sensor. Besides, an adversary can determine any session key of two sensor nodes, given only a known session key of them. We also show that the protocol could not satisfy the anonymity of the sensor nodes. Other attacks which influence the Janababaei et al.’s scheme, are impersonation attack on the sensor nodes and cluster heads and also the man in the middle attack. In this paper we find that the main weaknesses of the Janababaei et al.’s protocol are related to computation of the session key, . We also propose a simple remedy to enhance the security of the Janababaei et al.’s protocol. ‎An initial attempt to improve the protocol is using a hash function on the calculated key, . This suggestion is presented to enhance the security of the protocol against the observed weaknesses in this paper; but it does not mean that there are no other security issues in the protocol. Therefore, modification and improvement of the Janababaei et al.’s protocol such that it provides other security features can be considered in the future research of this paper. Besides, since in this paper we focus on the security of the protocol, then the efficiency of it was not discussed. Therefore one can consider the modification of the message structure of the protocol to reduce the computational and telecommunication costs of it as another future work in the context of this paper.},  
Keywords = {Internet of Things, Wireless Sensor Network, Authentication and Key Agreement, Anonymity},
volume = {19},
Number = {4}, 
pages = {85-94}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.61186/jsdp.19.4.85},
url = {http://jsdp.rcisp.ac.ir/article-1-1175-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1175-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2023}  
}

@article{ 
author = {Abbasi, sadrollah and Nejatian, Samad and Parvin, Hamid and Rezaei, Vahideh and BagheriFard, Karamollah},  
title = {The ensemble clustering with maximize diversity using evolutionary optimization algorithms}, 
abstract ={Data clustering is one of the main steps in data mining, which is responsible for exploring hidden patterns in non-tagged data. Due to the complexity of the problem and the weakness of the basic clustering methods, most studies today are guided by clustering ensemble methods. Diversity in primary results is one of the most important factors that can affect the quality of the final results. Also, the quality of the initial results is another factor that affects the quality of the results of the ensemble. Both factors have been considered in recent research on ensemble clustering. Here, a new framework for improving the efficiency of clustering has been proposed, which is based on the use of a subset of primary clusters, and the proposed method answers the above questions and ambiguities. The selection of this subset plays a vital role in the efficiency of the assembly. Since evolutionary intelligent algorithms have been able to solve the majority of complex engineering problems, this paper also uses these intelligent methods to select subsets of primary clusters. This selection is done using three intelligent methods (genetic algorithm, simulation annealing and particle swarm optimization). In this paper a clustering ensemble method is proposed which is based on a subset of primary clusters. The main idea behind this method is using more stable clusters in the ensemble. The stability is applied as a goodness measure of the clusters. The clusters which satisfy a threshold of this measure are selected to participate in the ensemble. For combining the chosen clusters, a co-association based consensus function is applied. A new EAC based method which is called Extended Evidence Accumulation Clustering, EEAC, is proposed for constructing the Co-association Matrix from the subset of clusters. Experimental results on several standard datasets with normalized mutual information evaluation, Fisher and accuracy criteria compared to Alizadeh, Azimi, Berikov, CLWGC, RCESCC, KME, CFSFDP, DBSCAB, NSC and Chen methods show the significant improvement of the proposed method in comparison with other ones.  Keywords: Clustering Ensemble, local optimization, evolutionary algorithm, correlation matrix, diversity.},  
Keywords = {Clustering Ensemble, local optimization, evolutionary algorithm, correlation matrix, diversity.},
volume = {19},
Number = {4}, 
pages = {95-120}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.61186/jsdp.19.4.95},
url = {http://jsdp.rcisp.ac.ir/article-1-1144-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1144-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2023}  
}

@article{ 
author = {Bakhtiari, Saeid and Nasiri, Zahra and Hejazi, Seyed Mohammad Sadegh},  
title = {Combination of Ensemble Data Mining Methods for Detecting Credit Card Fraud Transactions}, 
abstract ={As we know, credit cards speed up and make life easier for all citizens and bank customers. They can use it anytime and anyplace according to their personal needs, instantly and quickly and without hassle, without worrying about carrying a lot of cash and more security than having liquidity. Together, these factors make credit cards one of the most popular forms of online banking. This has led to widespread and increasing use for easy payment for purchases made through mobile phones, the Internet, ATMs, and so on. Despite the popularity and ease of payment with credit cards, there are various security problems, increasing day by day. One of the most important and constant challenges in this field is credit card fraud all around the world. Due to the increasing security issues in credit cards, fraudsters are also updating themselves. In general, as a field grows in popularity, more fraudsters are attracted to it, and this is where credit card security comes into play. So naturally, this worries banks and their customers around the world. Meanwhile, financial information acts as the main factor in market financial transactions. For this reason, many researchers have tried to prioritize various solutions for detecting, predicting, and preventing credit card fraud in their research work and provide essential suggestions that have been associated with significant success. One of the practical and successful methods is data mining and machine learning. In these methods, one of the most critical parameters in fraud prediction and detection is the accuracy of fraud transaction detection. This research intends to examine the Gradient Boosting methods, which are a subset of Ensemble Learning and machine learning methods. By combining these methods, we can identify credit card fraud, reduce error rates, and improve the detection process, which in turn increases efficiency and accuracy. This study compared the two algorithms LightGBM and XGBoost, merged them using simple and weighted averaging techniques, and then evaluate the models using AUC, Recall, F1-score, Precision, and Accuracy. The proposed model provided 95.08, 90.57, 89.35, 88.28, and 99.27, respectively, after applying feature engineering and using the weighted average approach for the mentioned validation parameters. As a result, function engineering and weighted averaging significantly improved prediction and detection accuracy.},  
Keywords = {Fraud Detection, Credit Card, Ensemble Learning, Data Mining},
volume = {19},
Number = {4}, 
pages = {121-136}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.61186/jsdp.19.4.121},
url = {http://jsdp.rcisp.ac.ir/article-1-1235-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1235-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2023}  
}

@article{ 
author = {Rahimi, Zahra and Homayounpour, Mohammad Mehdi},  
title = {A New Document Embedding Method for News Classification}, 
abstract ={Abstract- Text classification is one of the main tasks of natural language processing (NLP). In this task, documents are classified into pre-defined categories. There is lots of news spreading on the web. A text classifier can categorize news automatically and this facilitates and accelerates access to the news. The first step in text classification is to represent documents in a suitable way that can be distinguishable by a classifier. There is an abundance of methods in the literature for document representation which can be divided into a bag of words model, graph-based methods, word embedding pooling, neural network-based, and topic modeling based methods. Most of these methods only use local word co-occurrences to generate document embeddings. Local word co-occurrences miss the overall view of a document and topical information which can be very useful for classifying news articles.  In this paper, we propose a method that utilizes term-document and document-topic matrix to generate richer representations for documents.  Term-document matrix represents a document in a specific way where each word plays a role in representing a document. The generalization power of this type of representation for text classification and information retrieval is not very well. This matrix is created based on global co-occurrences (in document-level). These types of co-occurrences are more suitable for text classification than local co-occurrences. Document-topic matrix represents a document in an abstract way and the higher level co-occurrences are used to generate this matrix. So this type of representation has a good generalization power for text classification but it is so high-level and misses the rare words as features which can be very useful for text classification. The proposed approach is an unsupervised document-embedding model that utilizes the benefit of both document-topic and term-document matrices to generate a richer representation for documents. This method constructs a tensor with the help of these two matrices and applied tensor factorization to reveal the hidden aspects of data. The proposed method is evaluated on the task of text classification on 20-Newsgroups and R8 datasets which are benchmark datasets in the news classification area. The results show the superiority of the proposed model with respect to baseline methods. The accuracy of text classification is improved by 3%.},  
Keywords = {Text classification, Document representation, Document Embedding, Topic modeling, word co-occurrences},
volume = {19},
Number = {4}, 
pages = {137-148}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.61186/jsdp.19.4.137},
url = {http://jsdp.rcisp.ac.ir/article-1-1159-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1159-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2023}  
}

@article{ 
author = {Tajadini, Bahar and Seydnejad, SaeidReza and Rezakhani, Soheil},  
title = {Prediction of Epileptic Seizures in Patients with Temporal Lobe Epilepsy (TLE) based on Cepstrum analysis and AR model of EEG signal}, 
abstract ={Epilepsy is a chronic disorder of brain function caused by abnormal and excessive electrical neurons discharge in the brain. Seizures cause disturbances in consciousness that occur without prior notice, so their prediction ability, based on EEG data, can reduce stress and improve quality of life. An epileptic patient EEG data consists of five parts: Ictal, Inter-Ictal, pre-Ictal, Post-Ictal, and IT (seconds before Ictal onset). The purpose of predicting an attack is to detect the period of pre-ictal or IT to create warnings for medical procedures that are actually determined hours or minutes before ictal and do not necessarily mean the exact time of ictal [4]. The aim of many studies has been to identify the pre-ictal period based on EEG data. However, the problem of reliable prediction of epileptic seizures remains largely unsolved [5].  EEG and IEEG data types are used in detection and predicting methods. Due to the fact that artifacts and noises have a greater effect on EEG than IEEG, if there is IEEG, it has been tried to use it [6, 7]. Seizure warning methods that have a clinical application are generally based on the use on EEG [8]. Numerous studies have been performed to detect and predict seizures. The methods of signal processing and feature extraction are same in detection and prediction, but the difference is that, in detection, ictal and inter-ictal periods are compared, while in prediction, pre-ictal or IT and inter-ictal periods are being compared. Some algorithms use data modeling to extract features. References [13, 14], the coefficients AR model for the EEG data is obtained with least squares estimator, then the model coefficients are classified by SVM binary classification. In the article [15] the non-Gaussian EEG is considered using the ARIMA model (Autoregressive integrated moving average). In references [16, 17], predictions are performed based on the dynamic model with hidden variable and the sparse LVAR model, respectively. Also other features such as Mean Phase Coherency [18-20], Lag Synchronization Index to compare phase Synchronization between irregular oscillations [8,21], eigenspectra of space-delay correlation and covariance matrices [22], Largest Lyapunov Exponent [23, 25], decorrelation time, Hjorth parameters such as mobility and complexity, power spectrum in frequency bands, spectral edge frequency, the four statistical moments: mean, variance, kurtosis, skewness and there are features based on entropy and probability [6, 26-29]. Empirical mode decomposition (EMD) and wavelet transform methods have also been used to extract the feature [2, 30, 31, 37]. In articles [32, 33], the Cepstrum method has been used on short time multi channels EEG and IEEG in different patient states. Cepstrum is used to extract slow and periodic changes in speech that can be used to detect the ictal period from the inter-ictal, and has also been used to linearize the EEG [34]. In the paper [33], Cepstrum coefficients of multi-channel EEG are calculated and the 9 first coefficients are considered, then calculates the velocity and acceleration of the desired coefficients and uses a neural network to detect an epileptic seizure. The method of this paper was improved in 2014. In this way, first the signal energy and coefficients of Cepstrum are calculated and then the same process is followed. The accuracy values ​​of velocity and acceleration coefficients in this study were 89.7% - 98.7% and 98.9% - 99.9%, respectively [32].  In this study, the period of IT was detected in patients with temporal lobe epilepsy (TLE), which is the most common type of epilepsy [38]. For this purpose, two long term EEG channels LTM (long term monitoring) with a sampling rate 256, which are facing each other have been used. First, the desired signal is considered by the moving window with a length if 5 seconds and 80% overlap. The desired signal is normalized and its linear trend is removed and band-pass filtered (220 order FIR filter, cutoff at 6-20 Hz). Then the filtered date will de decomposed using discrete wavelet transform with 6-levels and Daubechies4 mother wavelet. In this step we will have 12 outputs. Next, by windowing of 500 samples and 75% overlap, the AR model with 8 order is applied to outputs. Cepstrum method can be used to detect regular and periodic changes in the ictal period of the EEG signal. According to this feature, the Cepstrum coefficients of the data window are calculated and the first coefficient of each window is considered. By applying a median filter to the 12 outputs of the previous stage, the current period of the first channel is compared to the background period of the same channel and the second channel, and the same is done for the second channel. This method reduces artifact error and inter-attack discharges. Finally, the signal is averaged by the moving window and the positive envelope of the curve is calculated. Given that we will eventually have 12 outputs, 12 threshold values are obtained for a patient’s training data, then these values are checked on the test data.  The proposed method was reviewed on a proposed model of adult epilepsy as well as 10 patients with long-term EEG data without artifact removal. Accuracy and average prediction time were 92% and 18.5 seconds, respectively. The algorithm performed better than other methods. Another advantage of the algorithm is the ability to reduce artifacts, while many studies have used short-term data without artifacts. Artifacts are located at different frequencies, which frequency analysis is performed by wavelet transform. Because two channel artifacts are unequal at the same time and in the same channel at different times, the artifacts are reduced by comparing the channels to each other. Algorithm testing on more patients is recommended to confirm the performance of the algorithm clinically.    },  
Keywords = {Epileptic Seizure Prediction, Temporal Lobe Epilepsy, Wavelet Transform, AR Model, Cepstrum, Median Filter, Positive Envelope of the Curve, Adult Epileptic Model.},
volume = {19},
Number = {4}, 
pages = {149-172}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.61186/jsdp.19.4.149},
url = {http://jsdp.rcisp.ac.ir/article-1-1177-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1177-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2023}  
}

@article{ 
author = {Reza, Shaghayegh and Seyyedsalehi, Ali and Seyyedsalehi, Zohreh},  
title = {Persian Phone Recognition Using Acoustic Landmarks and Neural Network-based variability compensation methods}, 
abstract ={Speech recognition is a subfield of artificial intelligence that develops technologies to convert speech utterance into transcription. So far, various methods such as hidden Markov models and artificial neural networks have been used to develop speech recognition systems. In most of these systems, the speech signal frames are processed uniformly, while the information is not evenly distributed in all of them. Auditory experiments have also shown that the human brain pays more attention to information-rich areas. By focusing on these areas instead of uniform processing, the brain can more robustly recognize speech in intrinsic and environmental speech variations such as speaker and noise. In contrast, the performance of most speech recognition systems degrades dramatically in these conditions. Therefore, to boost speech recognition systems' robustness, some researchers have focused on developing speech recognition systems by modeling these informative parts of the speech signal named landmarks. Similarly, in this article, we implemented a landmark-based system to obtain a robust Persian speech recognition system inspired by human brain perception. We also conducted neural networks-based variation compensation methods to boost its performance. In this article, acoustic landmarks are classified into two categories of events and states with the following definitions. Events are defined as areas of the speech signal in which the spectral characteristics change drastically while their length does not change a lot. The transition areas between some adjacent pairs of phones (phones' borders) are primarily selected as events. States are also defined as areas of the speech signal that spectral characteristics do not change significantly. Here the nuclei of phones are considered as the states. Previous research, linguistic sources, and implementation results have been used to determine the Persian language's appropriate landmarks. Finally, a set of 313 landmarks was selected and used in our acoustic landmarks-based phone recognition system.  The neural network structure used to recognize acoustic landmarks is a feed-forward fully connected structure with ReLU function in its hidden layers and a linear function in its final layer. The number of layers and neurons of this structure has been determined experimentally. The best structure is composed of 5 fully connected layers with 1000 neurons per layer. In this study, instead of considering 313 neurons to express each of the 313 landmarks, a heuristic labeling method is used to reduce the number of output neurons and utilize the shared information between the landmarks. The landmark recognition model slides on the speech feature sequence in the test phase to produce the output landmark sequence. Finally, to convert the obtained landmark sequence to a phone sequence, three rule-based post-processing steps are performed.  Variabilities are among the essential quality degradation sources in speech recognition; therefore, we proposed two approaches to reduce them and boost phone recognition quality in our landmark-based system. To this aim, we have utilized the nonlinear filtering characteristic of neural networks by implementing four neural network schemes. In scheme 1, a feed-forward neural network is first trained to map training landmarks to their corresponding well-recognized samples. Then this structure can act as a nonlinear filter before the landmark recognition block. In scheme 2, a unified structure is simultaneously trained to learn landmark labels and the filtering part. In both of these schemes, we used a recursive loop to increase the chance of attractor manipulation in the structures. In scheme 3, a recursive loop is added to one hidden layer. This loop acts as an input variability simulator and forces the network to recognize the input data and its variations correctly. Finally, in scheme four, a deep attractor neural network-based structure is proposed to shape the structure’s hidden layer components so that it can compensate for variabilities. The experiments are implemented on a Persian database named Farsdat, and the results are reported using phone error rate (PER) criteria. From every 25-millisecond speech frame, an acoustic feature called LHCB is extracted and combined with delta and delta-delta features of that frame. Every frame's features are concatenated with fourteen adjacent frames and are finally fed to our neural network-based landmark extraction model. The best-trained model obtained the PER of 21.74% on test data. Using scheme one to four, we achieved an absolute PER decrease by 0.39, 0.58, 0.43 and 1.30 percent, respectively. Comparing our landmark-based system's performance with other Persian phone recognition systems shows that this method could perform efficiently as a Persian phone recognition system.  In our future works, we intend to compare our acoustic-based phone recognition system's performance with conventional methods such as CTC in noisy conditions. Besides, it seems that acoustic landmarks can be used to create an alignment of the input speech sequence and the output transcription. Therefore, we will present a combination of CTC-based methods and acoustic landmarks to utilize acoustic landmarks' complementary information. This information might boost the performance and speed of CTC-based speech recognition methods, particularly in low resource languages.},  
Keywords = {Phone Recognition, Acoustic Landmarks, Deep Learning, Robust Recognition, Nonlinear Filtering},
volume = {19},
Number = {4}, 
pages = {173-196}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.61186/jsdp.19.4.173},
url = {http://jsdp.rcisp.ac.ir/article-1-1172-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-1172-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2023}  
}