Volume 21, Issue 3 (12-2024)
JSDP 2024, 21(3): 85-96 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Ebrahimi A, Shamsi M, Mohajjel M. Improvement of missing vital signs data estimation algorithm in wireless body sensor networks based on deep neural networks. JSDP 2024; 21 (3) : 4
URL: http://jsdp.rcisp.ac.ir/article-1-1277-en.html
URL: http://jsdp.rcisp.ac.ir/article-1-1277-en.html
Associate professor of Qom university of technology, Qom, Iran
Abstract: (554 Views)
In a wireless sensor network (WSN), due to various factors such as limited power, sensor transferability, hardware failure and network problems such as packet collisions, unreliable connection and unexpected damage, the amount sensed to the header or base station is not arrives. Therefore, data loss is very common in wireless sensor networks. Loss of measured data greatly reduces WBAN accuracy. Because WBAN deals with the vital signs of the human body, network reliability is very important. To solve this problem, missing data must be estimated. Many methods are used to reconstruct lost sensor data based on temporal correlation, spatial correlation, interpolation method, or sparse theory. Due to the characteristics of vital signs data, they can be considered as a series of sequential information. So far, various methods have been developed to estimate missing data in time series data in different fields. These methods can be divided into two categories: statistical methods and machine learning-based methods. In order to predict missing values, a missing data estimation model based on LSTM recurrent neural network whose network weights are optimized by particle swarm algorithm (PSO) is presented in this paper. In this paper, we use the MIMIC-III Waveform database to test the algorithm and determine the algorithm parameters. However, due to the large volume of data and the difficulty of testing the algorithm on all data, we suffice to test 500 patients with this data, whose vital signs included heart rate, respiration, blood oxygen, and so on. After data preprocessing, network training, predicting lost values and calculating error values, it is observed that the proposed technique of sgdm-LSTM By combining the PSO algorithm is a suitable method for estimating lost values. In addition, experimental results show that the mean square root error of the estimated value is lower than other methods. This value is 1.5898 with the best LSTM network hyperparameters.
Article number: 4
Type of Study: Research |
Subject:
Paper
Received: 2021/10/18 | Accepted: 2024/12/4 | Published: 2025/01/17 | ePublished: 2025/01/17
Received: 2021/10/18 | Accepted: 2024/12/4 | Published: 2025/01/17 | ePublished: 2025/01/17
References
1. L. Pan و J. Li، "K-Nearest Neighbor Based Missing Data Estimation Algorithm،" pp. 115-122، 2010. [DOI:10.4236/wsn.2010.22016]
2. Z. Gao، W. Cheng، X. Qiu و L. Meng، "A Missing Sensor Data Estimation Algorithm Based on،" 2015. [DOI:10.1155/2015/435391]
3. R. Kumar، D. Chaurasia، N. Chuahan و N. Chand، "Predicting Missing Values in Wireless Sensor Network using Spatial-Temporal Correlation،" International Journal of Computer Networks and Wireless Communications (IJCNWC)، 2017.
4. J. Pagán، "Robust and Accurate Modeling Approaches for Migraine Per-Patient Prediction from Ambulatory Data،" 2015. [DOI:10.3390/s150715419] [PMID] []
5. J. Q. Lin، H. C. Wu و S. C. Chan، "A New Regularized Recursive Dynamic Factor Analysis with Variable Forgetting Factor for Wireless Sensor Networks with Missing Data،" 2017 IEEE International Symposium on Circuits and Systems (ISCAS)، 2017. [DOI:10.1109/ISCAS.2017.8050594]
6. Q. Zhen و T. Zhang، "A Missing Data Estimation Algorithm in Wireless Sensor Networks،" Boletín Técnico، 2017.
7. L. Zhao و F. Zheng، "Missing Data Reconstruction Using Adaptively Updated Dictionary in Wireless Sensor Networks،" تأليف Proceeding of science، 2017. [DOI:10.22323/1.299.0040]
8. M. S. Saha و D. D. K. Anvekar، "Mitigation of Single Point Failure and Successful Data Recovery in Wireless Body Area Network،" International Journal of Network Infrastructure Security، 2017.
9. D. Sakurai، A. Santana و Y. Kawamura، "Estimation of Missing Data of Showcase Using Artificial Neural Networks،" تأليف IEEE 10th International Workshop on Computational Intelligence and Applications، 2017. [DOI:10.1109/IWCIA.2017.8203554] []
10. B. Kim، B. Lee و J. Cho، "ASRQ: Automatic Segment Repeat reQuest for IEEE 802.15.4-based WBAN،" IEEE SENSORS JOURNAL، 2016. [DOI:10.1109/JSEN.2017.2676163]
11. Y. Kawamura، K. Murakami، A. Santana، T. Iizaka و T. Matsui، "Differential Evolutionary Particle Swarm Optimization based ANN Training for Estimation of Missing Data of Refrigerated Showcase،" 57th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE)، 2018(8).
12. Y. Tian، K. Zhang، J. Li، X. Lin و B. Yang، "LSTM-based Traffic Flow Prediction with Missing Data،" Neurocomputing، 2018. [DOI:10.1016/j.neucom.2018.08.067]
13. S. Ghazal، M. Sauthier، D. Brossier، W. Bouachir، P. Jouvet و R. Noumeir، "Using machine learning models to predict oxygen saturation following ventilator support adjustment in critically ill children: a single center pilot study،" PLoS ONE، 2019. [DOI:10.1101/334896]
14. H. Cheng، Z. Xie، L. Wu، Z. Yu و R. Li، "Data prediction model in wireless sensor networks based on bidirectional LSTM،" Wireless Communications and Networking، 2019. [DOI:10.1186/s13638-019-1511-4]
15. S. Mujeeb، N. Javaid، M. Ilahi، Z. Wadud، F. Ishmanov و M. K. Afzal، "Deep Long Short-Term Memory: A New Price and Load Forecasting Scheme for Big Data in Smart Cities،" sustainability، 2019. [DOI:10.3390/su11040987]
16. R. Zhang، Z. Chen، S. Chen، J. Zheng، O. Büyüköztürk و H. Sun، "Deep long short-term memory networks for nonlinear structural seismic response prediction،" Computers and Structures، 2019. [DOI:10.1016/j.compstruc.2019.05.006]
17. F. Rundo، "Deep LSTM with Reinforcement Learning Layer for Financial Trend Prediction in FX High Frequency Trading Systems،" Applied Sciences، 2019. [DOI:10.3390/app9204460]
18. K. Yan، X. Wang، Y. Du، N. Jin، H. Huang و H. Zhou، "Multi-Step Short-Term Power Consumption Forecasting with a Hybrid Deep Learning Strategy،" energies، 2018. [DOI:10.3390/en11113089]
19. Y. Li، H. Wu و H. Liu، "Multi-step wind speed forecasting using EWT decomposition, LSTM principal computing, RELM subordinate computing and IEWT reconstruction،" Energy Conversion and Management، 2018. [DOI:10.1016/j.enconman.2018.04.082]
20. X. Yang، S. Mao، H. Gao، Y. Duan و Q. Zou، "Novel Financial Capital Flow Forecast Framework Using Time Series Theory and Deep Learning: A Case Study Analysis of Yu'e Bao Transaction Data،" IEEE Access، 2019. [DOI:10.1109/ACCESS.2019.2919189]
21. S. Zhao، Y. Zhang، S. Wang، B. Zhou و C. Cheng، "A recurrent neural network approach for remaining useful life prediction utilizing a novel trend features construction method،" Measurement، 2019. [DOI:10.1016/j.measurement.2019.06.004]
22. T. Zhang، S. Song، S. Li، L. Ma، S. Pan و L. Han، "Research on Gas Concentration Prediction Models Based on LSTM Multidimensional Time Series،" Energies، 2019. [DOI:10.3390/en12010161]
23. F. Lia، G. Renb و J. Lee، "Multi-step wind speed prediction based on turbulence intensity and hybrid deep neural networks،" Energy Conversion and Management، 2019. [DOI:10.1016/j.enconman.2019.02.045]
24. K. W. Minmin Luo، "Heart rate prediction model based on neural network،" IOP Conference Series: Materials Science and Engineering، 2020
25. L. Zhou، C. Zhau، N. Liu، X. Yao، و Z. Cheng، "Improved LSTM-based deep learning model for COVID-19 prediction using optimized approach ،" Engineering Applications of Artificial Intelligence، 2023 [DOI:10.1016/j.engappai.2023.106157] [PMID] []
26. H. Farrell، T. Liang، S. Misra، "DEEP NEURAL NETWORKS FOR ESTIMATION AND INFERENCE ،" Econometrica ، 2021 [DOI:10.3982/ECTA16901]
27. Y. Pan، J. Mu، "Enhancing WBANs Network Performance Based on Deep Learning With Integrated Spatiotemporal Information" IEEE Wireless Communications ، 2024 [DOI:10.1109/MWC.003.2400006]
28. K. W. Minmin Luo، " A Short-term Time Series Predictive Algorithm Based on Rolling Prediction and PSO-SVR،" 2024 IEEE 2nd International Conference on Control, Electronics and Computer Technology، 2024
29. مشيري، مریم، قادري زفرهايي، مصطفی و قانع گل محمدي، فرزان، " مقايسه دقت الگوريتم هاي يادگيري ماشين در تخمين داده هاي گمشده حاصل از آزمايش هاي ريزآرايه DNA"، مجله پژوهش هاي سلولي و مولكولي (مجله زيست شناسي ايران)، جلد 28، 1394.
30. ابراهیمی، ابوالفضل، شمسی، محبوبه و محجل، مرتضی، "برآورد داده های از دست رفته ی علائم حیاتی در شبکه های حسگر بی سیم بدن"،ششمین کنفرانس ملی پژوهش های کاربردی در مهندسی برق، مکانیک و مکاترونیک،تهران، 1399.
31. ابراهیمی، ابوالفضل، شمسی، محبوبه و محجل، مرتضی، "تنظیم بهینه پارامترهای شبکه عصبی عمیق در برآورد داده های از دست رفته ی علائم حیاتی در شبکه های حسگر بی سیم بدن"، مجله مدیریت مهندسی و رایانش نرم، شماره 16، صفحات 162-188، 1402.
32. عمرانپور، حسام و آزادیان، فهیمه، "ارائه یک رویکرد فازی برای بهینهسازی پیشبینی سری زمانی با مرتبه بالا"، فصلنامه پردازش علائم و داده ها، جلد 15 شماره 2، صفحات 3-16، 1397.
33. دانشپور، نگین و میرابوالقاسمی، سیده فاطمه، "پرکردن دادههای گمشده در دادههای سری زمانی چندمتغیره"، فصلنامه پردازش علائم و داده ها، جلد 19 شماره 2، صفحات 39-60، 1401.
34. عمرانپور، حسام و پورعلی، حدیثه، "ارائه مدل یادگیر ترکیب کرنلها برای پیشبینی سریهای زمانی براساس رگرسیون بردار پشتیبان و جستجوی فراابتکاری"، فصلنامه پردازش علائم و داده ها، جلد 19 شماره 1، صفحات 39-42، 1401.
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
