1388 6 1 11 90

تکیه در زبان فارسی Stress in Persian 1 1 این تحقیق در چارچوب نظریۀ واج‌شناسی لایه‌ای (Autosegmental-metricall) به مطالعه تکیه در زبان فارسی می‌پردازد و می‌کوشد با تمایز میان دو مفهوم مجزای ذهنی و عینی از تکیه، جایگاه تکیه در کلمات زبان فارسی را مورد مطالعه قرار دهد. مفهوم ذهنی از تکیه اشاره به دانش زبانی اهل زبان از الگوی برجستگی واژه‌ها در ذهن گویشور زبان دارد که به آن تکیه واژگانی(stress) می‌گویند و مفهوم عینی از تکیه به الگوی برجستگی کلمه در گفتار اطلاق می‌شود که به آن تکیه زیروبمی(pitch accent) می‌گویند. تحقیق حاضر با استناد به اطّلاعات موجود در واژگان ذهنی(mental lexicon) گویشور فارسی نشان می‌دهد (بر خلاف برخی تحقیقات پیشین) که انواع واژه‌های فارسی در ذهن اهل زبان دارای الگوی تکیه واحدی است. میان تکیه واژگانی و تکیه زیروبمی رابطه قابل‌پیش‌بینی و معناداری وجود دارد و از این رابطه علاوه‌بر مطالعات محض زبانی، در تولید خودکار آهنگ(intonation) و نوای گفتار(prosody) نیز می‌توان استفاده کرد. با توجّه به یافته‌های این تحقیق، مباحثی مانند الگوی تکیه در صیغه¬های مختلف فعل یا در صورت‌های گوناگون تصریفی اسم و یا بی‌تکیه بودن برخی از واحدهای واژگانی مانند حروف اضافه و غیره موضوعیت خود را از دست می‌دهند. در اینجا تکیه‌بر بودن و یا نبودن انواع تکواژهای اشتقاقی، تصریفی و واژه‌بست‌ها مورد بررسی قرار گرفته است که حضور آن ها در ساختمان کلمه، جایگاه تکیه کلمه را قابل‌پیش‌بینی می‌کند. 2 Abstract: This research has been carried out in the framework of Auto segmental-metrical (AM) phonology to study the stress in Persian. Two types of abstract and concrete prominences were distinguished in which the first one refers to the stress and the second one refers to the pitch accent. Stress is assumed to be a lexical property of the lexemes, but pitch accent is assumed to be an intonational element; therefore, contrary to stress, pitch accent in not fixed and predictable. Pitch accents could appear only on the lexically stressed syllables, if the context necessitates. Using the interface between phonology and morphology, it was concluded that all classes of lexemes are stressed on their final syllables in Persian; of course some grammatical morphemes are exceptions. Stress in inflected forms of words was formalized in which inflectional morphemes are stressed and receive the stress of the word, but clitics are unstressed and do not change the position of word stress if added to the stem. The results of this study could be used in linguistic studies and in different branches of Natural Language Processing (NLP) as well. 3 12 2009/09/22 1388/6/31 2018/02/19 1396/11/30 محرم اسلامی دانشگاه صنعتی شریف m_eslami@sharif.ir stress lexical stress pitch accent autosegmental-metrical phonology intonation. تکیه تکیه واژگانی تکیه زیروبمی واج‌شناسی لایه‌ای آهنگ Amini, Afsaneh. 1997. ‘On Stress in Persian’, Toronto Working Papers in Linguistics 16(1),1–20.##Bolinger, Dwight. 1958. A theory of pitch accent in English. Word 14: 109-49. ##Booij, Geert. 2005. The Grammar of word. OXFORD UNIVERCITY PRESS.##Chodzko, Alexander. 1852. Grammaire persane ou principes de l’iranien moderne. Paris, Maisonneuve and Cie.##Crystal, David. 1969. Prosodic systems and intonation in English, Cambridge University Press. ##Ferguson, Charles A. 1957. Word stress in Persian. Language, 33: 123-135. Fox, Anthony. 1996. Generative phonology. ##Hayati, A. Majid. 1997. A contrastive analysis of English and Persian stress. ##PSiCL, 32: 51-56. ##Kahnemuyipour, Arsalan. 2003. Syntactic Categories and Persian Stress. In Natural Language & Linguistic Theory, 21: 333-379.##Katamba, Francis. 1993. Morphology, Macmillan Press LTD.##Ladd, D. Robert 1996. Intonational phonology. Cambridge University Press.##Mahootian, Shahrzad. 1997. Persian, Routledge, London.##Martinet, A. 1964. Elements of general linguistics, University of Chicago Press. ##Phillott, Douglas Graven. 1919. Higher Persian grammar. Calcutta: The University Press.##Pierrehumbert, Janet. 1980. The phonology and phonetics of English intonation. PhD thesis, MIT.##Samareh, Yadollah. 1977. A course in colloquial Persian. Tehran, Tehran University Press. ##Towhidi, J. 1974. Studies in phonetics and phonology of Modern Persian, Humburg: Helmut Buske Verlag. ##Windfuhr, L. Gernot. 1979. Persian Grammar: History and State of its study, The Hague: Mouton.##Yarmohammadi, L. 1964. A contrastive study of modern English and modern Persian. PhD thesis, Indiana University.##Amini, Afsaneh. 1997. ‘On Stress in Persian’, Toronto Working Papers in Linguistics 16(1),1–20.##Bolinger, Dwight. 1958. A theory of pitch accent in English. Word 14: 109-49. ##Booij, Geert. 2005. The Grammar of word. OXFORD UNIVERCITY PRESS.##Chodzko, Alexander. 1852. Grammaire persane ou principes de l’iranien moderne. Paris, Maisonneuve and Cie.##Crystal, David. 1969. Prosodic systems and intonation in English, Cambridge University Press. ##Ferguson, Charles A. 1957. Word stress in Persian. Language, 33: 123-135. Fox, Anthony. 1996. Generative phonology. ##Hayati, A. Majid. 1997. A contrastive analysis of English and Persian stress. ##PSiCL, 32: 51-56. ##Kahnemuyipour, Arsalan. 2003. Syntactic Categories and Persian Stress. In Natural Language & Linguistic Theory, 21: 333-379.##Katamba, Francis. 1993. Morphology, Macmillan Press LTD.##Ladd, D. Robert 1996. Intonational phonology. Cambridge University Press.##Mahootian, Shahrzad. 1997. Persian, Routledge, London.##Martinet, A. 1964. Elements of general linguistics, University of Chicago Press. ##Phillott, Douglas Graven. 1919. Higher Persian grammar. Calcutta: The University Press.##Pierrehumbert, Janet. 1980. The phonology and phonetics of English intonation. PhD thesis, MIT.##Samareh, Yadollah. 1977. A course in colloquial Persian. Tehran, Tehran University Press. ##Towhidi, J. 1974. Studies in phonetics and phonology of Modern Persian, Humburg: Helmut Buske Verlag. ##Windfuhr, L. Gernot. 1979. Persian Grammar: History and State of its study, The Hague: Mouton.##Yarmohammadi, L. 1964. A contrastive study of modern English and modern Persian. PhD thesis, Indiana University.## ##

برچسب‌زنی نقش معنایی جملات فارسی با رویکرد یادگیری مبتنی بر حافظه Semantic Role Labeling of Persian Sentences with Memory-Based Learning Approach 1 1 استخراج نقش های معنایی یکی از گام های اصلی در بازنمایی معنی متن است. نقش های معنایی، ارتباط معنایی بین فعل و آرگومان های آن در جمله را مشخص می‌کنند. در این مقاله یک سیستم برچسب‌زنی خودکار نقش معنایی برای متون فارسی با رویکرد یادگیری ماشین ارائه شده است. مجموعه داده¬های مورد نیاز سیستم بخشی از پیکرۀ متنی زبان فارسی است که توسط پژوهشکدۀ پردازش هوشمند علائم تهیّه و برچسب‌گذاری شده است. سیستم پیشنهادی از دو مرحلۀ تشکیل شده؛ در مرحلۀ اوّل با تجزیۀ نحوی جمله، حد و مرز سازه و همچنین نوع گروه نحوی این اجزا در جمله مشخص می‌شود. این اطّلاعات به عنوان ورودی در مرحلۀ دوم مورد استفاده قرار می‌گیرد. مرحلۀ دوم سیستم مربوط به تخصیص نقش های معنایی مناسب به سازه‌های مشخص شده در مرحلۀ قبل می‌باشد. برای این منظور از ویژگی های نحوی و ساختاری هر سازه، بهره گرفته می شود. نتایج به دست آمده نشان‌دهندۀ 81.6% F1= برای زیر سیستم تجزیۀ نحوی، و 87.4% F1= برای زیرسیستم برچسب‌زنی معنایی درحالتی که ورودی های سیستم به¬صورت دستی تصحیح شده باشند. همچنین کارآیی کل سیستم 73.8%F1= را برای سیستم کامل برچسب‌زنی معنایی، یعنی تجزیۀ نحوی و تخصیص نقش نشان می‌دهد. نتایج به دست آمده حاکی از آن است که می‌توان از یک پیکرۀ آموزشی کوچک 1300 کلمه¬ای نتایج قابل قبولی به¬دست آورد. 2 Abstract Extracting semantic roles is one of the major steps in representing text meaning. It refers to finding the semantic relations between a predicate and syntactic constituents in a sentence. In this paper we present a semantic role labeling system for Persian, using memory-based learning model and standard features. Our proposed system implements a two-phase architecture to first identify the arguments by a shallow syntactic parser or chunker, and then to label them with appropriate semantic role, with respect to the predicate of the sentence. We show that good semantic parsing results, can be achieved with a small 1300-sentence training set. In order to extract features, we developed a shallow syntactic parser which divides the sentence into segments with certain syntactic units. The input data for both systems is drawn from RCISP corpus which is hand-labeled with required syntactic and semantic information. The results show an F-score of 81.6% on argument boundary detection task and an F-score of 87.4% on semantic role labeling task using Gold-standard parses. an overall system performance shows an F-score of 73.8% on complete semantic role labeling system i.e. boundary plus classification. 13 22 2009/09/222009/09/22 1388/6/31 2018/02/192018/02/19 1396/11/30 سعید راحتی قوچانی دانشگاه ازاد اسلامی مشهد rahati@mshdiau.ac.ir آزاده کامل قالی باف دانشگاه ازاد اسلامی مشهد azadeh_kamel@hotmail.com اعضم استاجی داشنگاه فردوسی مشهد estaji@um.ac.ir Semantic Role Labeling Shallow Semantic Parsing Shallow Syntactic Parsing Memory- Based Learning. پردازش زبان طبیعی برچسب‌زنی معنایی تجزیۀ سطحی معنایی تجزیۀ سطحی نحوی یادگیری مبتنی بر حافظه. [1] Marquez Lluís, Carreras Xavier, Litkowski Kenneth, Stevenson Suzanne, "Semantic Role Labeling: An Introduction to the Special Issue" Association For Computational Linguistic 2008.##[2] Gerwert Stevens , "Automatic semantic role labeling in a Dutch corpus" , master thesis, Universiteit Utrecht, Faculty of arts , September 2006## [3] Sun Honglin, Jurafsky Daniel. "Shallow Semantic Parsing of Chinese" . In Proceedings of NAACL 2004, Boston, USA##[4] Gilda Daniel, Jurafsky Daniel, "Automatic Labeling Of Semantic Role", Association of computer linguistic, 28(3). pp.245–288. 2002## [5] Pradhan Sameer, Jurafsky Daniel, “Support Vector Learning for Semantic Argument Classification", Springer Science, 2005 ##[6] Lim Joon-Ho, Hwang Young-sook, Park So-young, and Rim Hae-chang. "Semantic role labeling using maximum entropy model", In Proceedings of CoNLL-2004. 2004##[7] http://framenet.icsi.berkeley.edu/##[8] http://verbs.colorado.edu/~mpalmer/projects/ ace/ PBguidelines.pdf##[9] Morante Roser, Busser Bertjan, "Role Labelling for Catalan and Spanish using TiMBL", Proceedings of the 4th International Workshop on Semantic Evaluations (SemEval-2007), pages 183–186.##[10] Hammerton James , M. Osborne, S. Armstrong, W. Daelemans. 2002. "Introduction to Special Issue on Machine Learning Approaches to Shallow Parsing", Journal of Machine Learning Research , 551-558.## [11] Sadr-Mousavi Maryam, Shamsfard Mehrnoush, "Thematic Role Extraction Using Shallow Parsing", International journal of computational Intelligence Volume 4 , 2007##[12] Dowty David, "Thematic Proto-roles and Argument Selection", Language 67, pp.547–619,1991.## [13] Levin Beth, "English Verb Classes and Alternations", the University of Chicago Press, Chicago and London, 1993## [14] Fillmore Charles, "The case for case". Academic Press, New York, 1997##[15] http://www.rcisp.com##[16] Daelemans Walter, "TiMBL: Tilburg Memory-Based Learner", Tilburg University and CNTS Research Group, University of Antwerp 2006## [17] Ratnaparkhi Adwait, "A linear observed time statistical parser based on maximum entropy models", InEMNLP-97, The Second Conference on Empirical Methods in Natural Language Processing, 1997.##[18] ILK: Induction of Linguistic Knowledge, http://ilk.uvt.nl/## [1] Marquez Lluís, Carreras Xavier, Litkowski Kenneth, Stevenson Suzanne, "Semantic Role Labeling: An Introduction to the Special Issue" Association For Computational Linguistic 2008.##[2] Gerwert Stevens , "Automatic semantic role labeling in a Dutch corpus" , master thesis, Universiteit Utrecht, Faculty of arts , September 2006## [3] Sun Honglin, Jurafsky Daniel. "Shallow Semantic Parsing of Chinese" . In Proceedings of NAACL 2004, Boston, USA##[4] Gilda Daniel, Jurafsky Daniel, "Automatic Labeling Of Semantic Role", Association of computer linguistic, 28(3). pp.245–288. 2002## [5] Pradhan Sameer, Jurafsky Daniel, “Support Vector Learning for Semantic Argument Classification", Springer Science, 2005 ##[6] Lim Joon-Ho, Hwang Young-sook, Park So-young, and Rim Hae-chang. "Semantic role labeling using maximum entropy model", In Proceedings of CoNLL-2004. 2004##[7] http://framenet.icsi.berkeley.edu/##[8] http://verbs.colorado.edu/~mpalmer/projects/ ace/ PBguidelines.pdf##[9] Morante Roser, Busser Bertjan, "Role Labelling for Catalan and Spanish using TiMBL", Proceedings of the 4th International Workshop on Semantic Evaluations (SemEval-2007), pages 183–186.##[10] Hammerton James , M. Osborne, S. Armstrong, W. Daelemans. 2002. "Introduction to Special Issue on Machine Learning Approaches to Shallow Parsing", Journal of Machine Learning Research , 551-558.## [11] Sadr-Mousavi Maryam, Shamsfard Mehrnoush, "Thematic Role Extraction Using Shallow Parsing", International journal of computational Intelligence Volume 4 , 2007##[12] Dowty David, "Thematic Proto-roles and Argument Selection", Language 67, pp.547–619,1991.## [13] Levin Beth, "English Verb Classes and Alternations", the University of Chicago Press, Chicago and London, 1993## [14] Fillmore Charles, "The case for case". Academic Press, New York, 1997##[15] http://www.rcisp.com##[16] Daelemans Walter, "TiMBL: Tilburg Memory-Based Learner", Tilburg University and CNTS Research Group, University of Antwerp 2006## [17] Ratnaparkhi Adwait, "A linear observed time statistical parser based on maximum entropy models", InEMNLP-97, The Second Conference on Empirical Methods in Natural Language Processing, 1997.##[18] ILK: Induction of Linguistic Knowledge, http://ilk.uvt.nl/## ##

استفاده از زمان پاسخ، مؤلفّۀ شناختی P300 و تلفیق دو مد به منظور تشخیص Using Reaction Time, P300 and Multimodal Information to Assess "Guilty Knowledge" 1 1 روش های موجود تشخیص دروغ که بر اساس پلی گرافی کلاسیک عمل می کنند، سعی می کنند با استفاده از مشخصّات چندین سیگنال فیزیولوژیک، به تفکیک فرد راستگو یا دروغ گو بپردازند. رویکرد دیگری که در کنار روش کلاسیک مطرح گردیده است، استفاده از مؤلفۀ شناختی P300 سیگنال های مغزی برای کشف دانش فرد خطاکار است؛ در ادامۀ توسعۀ این روش ها، موضوعی که در این تحقیق به آن پرداخته شده است، بحث ارزیابی تشخیص دانش فرد خطاکار از تحلیل زمان پاسخ فرد و تلفیق تحلیل زمان پاسخ و مؤلفّۀ شناختی P300 مغز است. به همین منظور چندین روش قبلی، تحلیل مغزی و تحلیل زمان پاسخ پیاده سازی و توسعه داده شد و ترکیب حالات مختلفی از روش ها مورد بررسی قرار گرفت. نتیجۀ روش تحلیل زمان پاسخ توسعه یافته در این تحقیق، به صحّت 81% و سطح زیر منحنی 0.85 رسیده است که با بهترین نتیجۀ تحلیل مغزی در کارهای قبل (استفاده از طبقه بندی کننده با ویژگی های مبتنی بر تبدیل موجک که صحّت 80% و سطح زیر منحنی 0.86 داشت به طورکامل قابل مقایسه است. از بین حالات مختلف تلفیق روش های تحلیل مغزی و زمان پاسخ، بهترین نتیجه، مربوط به روش تحلیل زمان پاسخ بوت استرپ شده و تشخیصP300 به روش اختلاف دامنه بوت استرپ شده بود. این تلفیق صحّت تفکیک بین افراد خطاکار و بی گناه را تا 88% بهبود داد که این بهبود با استفاده از آزمون مک نمار در مقایسه با نتیجۀ روش اختلاف دامنۀ بوت استرپ شده به¬عنوان بهترین نتیجۀ تحقیقات قبل به طور کامل معنی دار (0.01 ) بود. 2 Abstract: Current lie detection methods, based on the polygraph technique, rely upon the measurement of several physiological characteristics to discriminate whether a truth or a lie is expressed. P300-based GKT (guilty knowledge test) has been suggested as an alternative approach for conventional polygraph technique. The purpose of this study is to evaluate RT (response time) analysis and combination of RT and ERP to identify participants possessing specific guilty knowledge. For the analysis, several previous methods were implemented and results of RT analysis and fusion ERP and RT analysis were compared which other. The accuracy of RT analysis (bootstrapped analysis of reaction time method) is 81% and AUC (area under curve) of correct detection in guilty and innocent subjects is 0.85 which are comparable to 80% accuracy of ERP analysis (Wavelet classifier method) and AUC=0.86 in previous study. Between the many fusion methods, fusion of BART and BAD method has the better accuracy and best AUC, this is superior result compared to results of previous methods from McNemar’s test point of view. These results show that brain response and behavioral response have complement information. The Fusion of BART and BAD method is combination of brain and behavioral response, therefore this proposed as best approach for Assess "Guilty Knowledge". 23 32 2009/09/222009/09/222009/09/22 1388/6/31 2018/02/192018/02/192018/02/19 1396/11/30 امین محمدیان پژوهشگاه توسعه فناوری های پیشرفته خواجه نصیرالدین طوسی a.mohammadian@aut.ac.ir وحید ابوطالبی دانشگاه یزد abootalebi@yazduni.ac.ir محمدحسن مرادی mhmoradi@aut.ac.ir محمد علی خلیل زاده makhalilzadeh@mshdiau.ac.ir Reaction Time Guilty Knowledge Test Event Related Potential Multimodal Analysis. آزمون دانش فرد خطاکار پتانسیل برانگیختۀ بینایی تحلیل چند مد [1]- Rosenfeld, J.P., Shue E. and Singer, E, 2007. Single versus multiple probe blocks of P300-based concealed information tests for self-referring versus incidentally obtained information. Biological Psychology 74, 396-404.##[2]- Ganis, G., Kosslyn, S.M., Stose, S., Thompson, W.L., Yurgelun-Todd, D.A., 2003. Neural correlates of different types of deception: an fMRI investigation. Cerebral Cortex 13, 830–836.##[3]- Kozel, F.A., Padgett, T.M., George, M.S., 2004a. A replication study of the neural correlates of deception. Behavioral Neuroscience 118, 852–856.##[4]- Kozel, F.A., Revell, L.J., Lorberbaum, J.P., Shastri, A., Elhai, J.D., Horner, M.D., Smith, A., Nahas, Z., Bohning, D.E., George, M.S., 2004b. A pilot study of functional magnetic resonance imaging brain correlates of deception in healthy young men. The Journal of Neuropsychiatry and Clinical Neurosciences 16, 295–305.##[5]- Langleben, D.D., Loughead, J.W., Bilker, W.B., Ruparel, K., Childress, A.R., Busch, S.I., Gur, R.C., 2005. Telling truth from lie in individual subjects with fast event-related fMRI. Human Brain Mapping 26, 262–272.##[6]- Lee, T.M.C., Liu, H.L., Tan, L.H., Chan, C.C.H., Mahankali, S., Feng, C.M., Hou, J., Fox, P.T., Gao, J.H., 2002. Lie detection by functional magnetic resonance imaging. Human Brain Mapping 15 (3), 157–164.##[7]- National Research Council, 2002. The Polygraph and Lie Detection. National Academies Press, Washington, D.C.##[8]- Nunez, J.M., Casey, B.J., Egner, T., Hare, T., Hirsch, J., 2005. Intentional false responding shares neural substrates with response conflict and cognitive control. Neuroimage 25, 267–277.##[9]- Phan, K.L., Magalhaes, A., Ziemlewicz, T.J., Fitzgerald, D.A., Green, C., Smith, W., 2005. Neural correlates of telling lies: a functional magnetic resonance imaging study at 4 Tesla. Academic Radiology 12, 164–172.##[10]- Farwell, L.A., Donchin, E., 1991. The truth will out: interrogative polygraphy (lie detection) with event-related potentials. Psychophysiology 28, 531–547.##[11]- Rosenfeld, J.P., 2002. Event-related potentials in the detection of deception, malingering, and false memories. In: Kleiner, M. (Ed.), Handbook of Polygraph Testing. Academic Press, N.Y., pp. 265–286.##[12]- Gronau, N., Shakhar, G. B. and Cohen, A, 2005. Behavioral and physiological measures in the detection of concealed information, Journal of Applied Psychology 90(1), 147-158.##[13]- Verschuere, B., Crombez, G., Koster, E. H. W., 2005, Behavioral responding to concealed information: examining the role of relevance orienting. Psychologica Belgica, 45, 207-216. ##[14]- Verschuere, B., Crombez, G., Koster, E. H. W., & Declercq, A. 2004. Autonomic and behavioral responding to concealed information: Differentiating orienting and defensive responses. Psychophysiology, 41, 261-266.##[15]- Seymour T. L., Colleen M., Seifert M. G., Shafto A. and Mosmann. L, 2000. Using Response Time Measures to Assess "Guilty Knowledge. Journal of Applied Psychology 85 (1), 30-37.##[16]- Rosenfeld, J.P., Soskins, M., Bosh, G., Ryan, A., 2004. Simple effective countermeasures to P300-based tests of detection of concealed information. Psychophysiology 41 (2), 205-219.##[17]- Meijer E.H., Smulders F.T.Y., Merckelbach H.L.G.J. 2008 Combining P300 and SCR in the detection of concealed information, Symposium / International Journal of Psychophysiology 69, 139–205.##[18]- Abootalebi, V., Moradi, M. H., Khalilzadeh, M. A. 2006. A comparison of methods for ERP assessment in a P300-based GKT. International Journal of Psychophysiology 62, 309-320.##[19]- Abootalebi, V. 2006. Analysis of Cognitive Components of Brain Potentials and it's Application in Lie Detection. PhD Thesis in biomedical.engineering, Amirkabir University of Technology. ##[20]- Wei, L., Yang, Y R., Nishikawa R. M. and Jiang, Y, 2005. A Study on Several Machine-Learning Methods for Classification of Malignant and Benign Clustered Micro calcifications, IEEE Transactions On Medical Imaging 24 (3), 371-380.##[21]- Sykacek, P., Roberts, S., Stokes, M., Curran, E., Gibbs, M. and Pickup L, 2003. Probabilistic methods in BCI research. IEEE Transactions On Neural Systems And Rehabilitation Engineering 11 (2). 192-195.##[22]- Seymour T. L., Kerlin J. R. 2007 Successful detection of verbal and visual concealed knowledge using an RT-based paradigm Applied Cognitive Psychology, ی(4), 475 – 490.##[23]- Mohammadian. A., Abootalebi. V., Moradi. M. H., Khalilzadeh. M. A. Multimodal Detection of Deception Using fusion of Reaction Time and P300 component, Cairo International Biomedical Engineering Conference 2008.## ####[1]- Rosenfeld, J.P., Shue E. and Singer, E, 2007. Single versus multiple probe blocks of P300-based concealed information tests for self-referring versus incidentally obtained information. Biological Psychology 74, 396-404.##[2]- Ganis, G., Kosslyn, S.M., Stose, S., Thompson, W.L., Yurgelun-Todd, D.A., 2003. Neural correlates of different types of deception: an fMRI investigation. Cerebral Cortex 13, 830–836.##[3]- Kozel, F.A., Padgett, T.M., George, M.S., 2004a. A replication study of the neural correlates of deception. Behavioral Neuroscience 118, 852–856.##[4]- Kozel, F.A., Revell, L.J., Lorberbaum, J.P., Shastri, A., Elhai, J.D., Horner, M.D., Smith, A., Nahas, Z., Bohning, D.E., George, M.S., 2004b. A pilot study of functional magnetic resonance imaging brain correlates of deception in healthy young men. The Journal of Neuropsychiatry and Clinical Neurosciences 16, 295–305.##[5]- Langleben, D.D., Loughead, J.W., Bilker, W.B., Ruparel, K., Childress, A.R., Busch, S.I., Gur, R.C., 2005. Telling truth from lie in individual subjects with fast event-related fMRI. Human Brain Mapping 26, 262–272.##[6]- Lee, T.M.C., Liu, H.L., Tan, L.H., Chan, C.C.H., Mahankali, S., Feng, C.M., Hou, J., Fox, P.T., Gao, J.H., 2002. Lie detection by functional magnetic resonance imaging. Human Brain Mapping 15 (3), 157–164.##[7]- National Research Council, 2002. The Polygraph and Lie Detection. National Academies Press, Washington, D.C.##[8]- Nunez, J.M., Casey, B.J., Egner, T., Hare, T., Hirsch, J., 2005. Intentional false responding shares neural substrates with response conflict and cognitive control. Neuroimage 25, 267–277.##[9]- Phan, K.L., Magalhaes, A., Ziemlewicz, T.J., Fitzgerald, D.A., Green, C., Smith, W., 2005. Neural correlates of telling lies: a functional magnetic resonance imaging study at 4 Tesla. Academic Radiology 12, 164–172.##[10]- Farwell, L.A., Donchin, E., 1991. The truth will out: interrogative polygraphy (lie detection) with event-related potentials. Psychophysiology 28, 531–547.##[11]- Rosenfeld, J.P., 2002. Event-related potentials in the detection of deception, malingering, and false memories. In: Kleiner, M. (Ed.), Handbook of Polygraph Testing. Academic Press, N.Y., pp. 265–286.##[12]- Gronau, N., Shakhar, G. B. and Cohen, A, 2005. Behavioral and physiological measures in the detection of concealed information, Journal of Applied Psychology 90(1), 147-158.##[13]- Verschuere, B., Crombez, G., Koster, E. H. W., 2005, Behavioral responding to concealed information: examining the role of relevance orienting. Psychologica Belgica, 45, 207-216. ##[14]- Verschuere, B., Crombez, G., Koster, E. H. W., & Declercq, A. 2004. Autonomic and behavioral responding to concealed information: Differentiating orienting and defensive responses. Psychophysiology, 41, 261-266.##[15]- Seymour T. L., Colleen M., Seifert M. G., Shafto A. and Mosmann. L, 2000. Using Response Time Measures to Assess "Guilty Knowledge. Journal of Applied Psychology 85 (1), 30-37.##[16]- Rosenfeld, J.P., Soskins, M., Bosh, G., Ryan, A., 2004. Simple effective countermeasures to P300-based tests of detection of concealed information. Psychophysiology 41 (2), 205-219.##[17]- Meijer E.H., Smulders F.T.Y., Merckelbach H.L.G.J. 2008 Combining P300 and SCR in the detection of concealed information, Symposium / International Journal of Psychophysiology 69, 139–205.##[18]- Abootalebi, V., Moradi, M. H., Khalilzadeh, M. A. 2006. A comparison of methods for ERP assessment in a P300-based GKT. International Journal of Psychophysiology 62, 309-320.##[19]- Abootalebi, V. 2006. Analysis of Cognitive Components of Brain Potentials and it's Application in Lie Detection. PhD Thesis in biomedical.engineering, Amirkabir University of Technology. ##[20]- Wei, L., Yang, Y R., Nishikawa R. M. and Jiang, Y, 2005. A Study on Several Machine-Learning Methods for Classification of Malignant and Benign Clustered Micro calcifications, IEEE Transactions On Medical Imaging 24 (3), 371-380.##[21]- Sykacek, P., Roberts, S., Stokes, M., Curran, E., Gibbs, M. and Pickup L, 2003. Probabilistic methods in BCI research. IEEE Transactions On Neural Systems And Rehabilitation Engineering 11 (2). 192-195.##[22]- Seymour T. L., Kerlin J. R. 2007 Successful detection of verbal and visual concealed knowledge using an RT-based paradigm Applied Cognitive Psychology, ی(4), 475 – 490.##[23]- Mohammadian. A., Abootalebi. V., Moradi. M. H., Khalilzadeh. M. A. Multimodal Detection of Deception Using fusion of Reaction Time and P300 component, Cairo International Biomedical Engineering Conference 2008.## ## ##

طبقه بندی احساس افراد با استفاده از سیگنال های مغزی و محیطی Emotion Classification Using Brain and Peripheral Signals 1 1 تحقیقات نشان می دهد که احساس، یک فرآیند ذهنی و متوجه مغز انسان می باشد و روی فرآیند های مهمّی چون حافظه، تمرکز، تفکّر و تصمیم گیری اثر دارد. به همین، دلیل مطاله مکانیزم و عملکرد آن مورد توجّه محققان علوم شناختی قرار گرفته است. مطالعه‌ احساس از طریق پردازش سیگنال های بیولوژیکی، علاوه بر کاربردهای کلینیکی که در زمینه تشخیص و درمان به موقع ناهنجاری های روانی می تواند داشته باشد، در علوم مبتنی بر تعاملات انسان و رایانه نیز نقش مهمی بازی می کند و باعث پیشرفت های زیادی در این زمینه می گردد. هدف اصلی در این تحقیق، طبقه بندی احساس افراد با استفاده از سیگنال های مغزی و محیطی است. دادگان مورد استفاده، از مجموعه دادگان eNTERFACE است که در سال 2006 جمع آوری شده، سه حالت احساسی برانگیختگی مثبت، برانگیختگی منفی و حالت آرام یا استراحت را مورد مطالعه قرار داده است. سیگنال مغزی به¬صورت همزمان با چهار سیگنال محیطی: تنفس، میزان هدایت پوست، فشار خون و دما از پنج نفر ثبت شده است. ویژگی های مرتبط با حالات مختلف احساسی از سیگنال ها استخراج شده، که در مورد سیگنال های محیطی ویژگی های حوزه زمان و حوزه فرکانس مورد نظر می باشد و در مورد سیگنال مغزی، علاوه بر ویژگی های حوزه زمان و فرکانس، ویژگی های غیرخطی بعد همبستگی، نمای لیاپانوف و بعد فرکتال نیز استفاده شده است و در مورد سیگنال های مغزی از روش Synchronization Likelihood به منظور انتخاب الکترود استفاده شده است. ساختارهای چهارطبقه بندی کننده KNN,QDA,LDA,SVM مورد استفاده قرار گرفته است و نتایج سیگنال‌های مغزی و محیطی به صورت جداگانه و نیز در ترکیب با یکدیگر مقایسه شده اند. بیشترین میزان صحت،63.3% در طبقه بندی سیگنال های مغزی ، 61.67% در طبقه بندی سیگنال های محیطی و 61.67% در طبقه بندی ترکیب سیگنال های مغزی و محیطی، به دست آمده است. نتایج نشان می دهد که استفاده از سیگنال مغزی نسبت به سیگنال محیطی و نیز ترکیب مغزی و محیطی در ایجاد تمایز بین حالات مختلف احساسی مورد مطالعه، موفق تر است؛ ولی نتایج به دست آمده از ترکیب سیگنال مغزی و محیطی، نتایج مقاوم تری نسبت به تغییر افراد و تغییر روش ها محسوب می شود. 2 Abstract Emotions play a powerful and significant role in human beings everyday life. They motivate us, impact our beliefs and decision making and would affect some cognitive processes like creativity, attention, and memory. Nowadays the use of emotion in computers is an increasingly in vogue field. In many ways emotions are one of the last and least explored frontiers of intuitive human-computer interactions. This can perhaps be explained by the fact that computers are traditionally viewed as logical and rational tools which is incompatible with the often irrational and seeming illogical nature of emotions. It is apparent that we as humans, in spite of having extremely good abilities at felling and expressing emotions, still cannot agree on how they should best be defined. until now, there are a bunch of good reasons which supports that emotion is a fitting topic for Human-Computer Interaction research. Human beings who are emotional creatures should theoretically be able to interact more effectively with computers which can account for these emotions. So Emotions assessed would make some improvement in HCI. The goal of our research is to perform a multimodal fusion between EEG’s and peripheral physiological signals for emotion detection. The input signals were electroencephalogram, galvanic skin resistance, blood pressure and respiration, which can reflect the influence of emotion on the central nervous system and autonomic nervous system respectively. The acquisition protocol is based on a subset of pictures which correspond to three specific areas of valance-arousal emotional space(positively excited, negatively excited, and calm). The features extracted from input signals, and to improve the results of brain signals, nonlinear features as correlation dimension, largest lyapunov exponent and fractal dimension is used. The performance of four classifiers: LDA, QDA, KNN, SVM has been evaluated on different feature sets: peripheral signals, EEG’s, and both. Synchronization likelihood is used as a channel selection algorithm and the performance of two feature selection algorithms; Genetic Algorithm and Mutual information is evaluated. The best result of accuracy in EEG signals is 63.3% with QDA as classifier, the best result of peripheral signals is 61.67% and the best of both is 63.3% with QDA. In comparison among the results of different feature sets, EEG signals seem to perform better than other physiological signals, and the results presented showed that EEG’s can be used to assess emotional states of a user. Also, fusion provides more robust results since some participants had better scores with peripheral signals than with EEG’s and vice-versa. 33 52 2009/09/222009/09/222009/09/222009/09/22 1388/6/31 2018/02/192018/02/192018/02/192018/02/19 1396/11/30 زهرا خلیلی khalili.bme@hmail.com محمدحسن مرادی mhmoradi@aut.ac.ir Emotion EEG peripheral signals feature extraction classification channel selection nonlinear features. سیستم های بازشناخت احساس سیگنال مغزی سیگنال های محیطی استخراج ویژگی طبقه بندی [1]. A. Sebe, I. Cohan, T. Gevers and T.S. Huang, “Multimodal Approaches for Emotion Recognition: A Survey”, International Imaging VI. Proceedings of the SPIE, Vol. 5670, pp. 56-67, 2004.##[2]. D. O. Bos. ‘‘EEG-based Emotion Recognition the influence of visual and auditory stimuli’’, Nederland, pp. 11-16, 2006. ##[3]. J. Gratch, S. Marsella, “A Domain-independent Framework for Modeling Emotion”, Journal of Cognitive Systems Research, Vol. 5, Issue 4, pp. 269-306, 2004.##[4]. M. Grimm and K. Kroschel, “Rule-based emotion classification using acoustic feature”, in PROC.Int.Conf. on Telemedicine and Multimedia Communication, 2005.## ##[5]. A. Savran, K. Ciftci, G. Chanel, J. Cruz Mota, L. Hong Viet, B. Sankur, L. Akarun, A. Caplier, M. Rombaut” Emotion Detection in the Loop from Brain Signals and Facial Images”, eNTERFACE’06, July 17th – August 11th, Dubrovnik, Croatia. 2006.##[6]. E T. Rolls,”The Brain and Emotion”, Oxford University Press, 1998. ##[7]. J. M. Jenkins, K. Oatley, and N. L. Stein,” Human Emotions: A Reader”, Blackwell Publishers, Malden, MA, 1998.## ##[8]. C. Darwin, “The Expression of the Emotions in Man and Animals”, John Murray, London, 2nd edition, 1890.##[9]. G. Chanel, J. Kronegg, D. Grandjean, T. Pun, ‘‘Emotion assessment: Arousal evaluation using EEG's and peripheral physiological signals’’, Proc. Int. Workshop Multimedia Content Representation, Classification and Security (MRCS), Sept. 11- 13, 2006, Istanbul, Turkey, B. Gunsel, A. K. Jain, A. M. Tekalp,B. Sankur, Eds., Lecture Notes in Computer Science, Vol. 4105,Springer, 530-537.## ##[10]. J. Kim, “Emotion Recognition from Physiological Measurement (Biosignal)” Workshop Santorini, HUMAINE WP4/SG3.##[11]. M. Murugappan, M. Rizon, R. Nagarajan, S. Yacoob, M. Karthigayan and M. Sugisaka Feature Extraction Methods for Human Emotion Recognition using EEG - A Study. Malaysia-Japan International Symposium on Advanced Technology, 2007, accepted.##[12] www.nyas.org##[13]. www.thebrain.mcgill.ca ##[14].www.pga.com/improve/features/mentalgame/improve_heartmath062904.cfm.##[15]. E. Douglas-Cowie,”HUMAINE”, IST FP6 Contract no.507422, 2004.##[16]. K. H. Kim, S.W. Bang, S.R.Kim, “Emotion recognition system using short-term monitoring of physiological signals “ , Medical & Biological Engineering & Computing , vol 42. pp. 419-427, 2004.##[17]. J. Healey, R. picard, ” Digital processing of affective signals”, IEEE, 1998.##[18]. A. Haag, S. Goronzy, P. Schaich, and J. Williams, "Emotion Recognition Using Bio-Sensors: First Step Toward an Automatic System," Affective Dialog Systems: Tutorial And Research Workshop, Kloster Irsee, Germany, June 14-16, 2004.##[19]. J. Wangner, J. kim, E. Andre,” From physiological signals to emotions: implementing and comparing selected methods for feature extraction and classification”, HUMAINE FP6-2005.##[20]. R. Horlings, D. Datcu, and L J M. Rothkrantz, “Emotion Recognition using Brain Activity”, Proceedings on Int Conference on Computer Systems and Technologies, pp. II-1-1 – II-1-5, 2008.## ##[21]. K. Takahashi, A. Tsukaguchi ,“Remarks on Emotion Recognition from Multi-Modal Bio-Potential Signals”, IEEE Transactions on Industrial Technology, Vol 3, pp. 1654-1659, 2003.## ##[22]. T. Iizuka, M. Nakawa, “Emotion Analysis with Fractal-Dimension of EEG Signals”, IEIC Technical Report,Vol 102 (534), pp. 13-18, 2005.##[23]. H. Oya, H. Kawasaki, A. Mathhew, Howard III. and R. Adolphs, “Electrophysiological Responses in the Human Amygdala Discriminate Emotion Categories of Complex Visual Stimul”. The Journal of Neuroscience, Vol 22(21), pp. 9502-9512, 2002.##[24]. N. A. Jones, T. Field, N. A. M. Fox, Davalos and Gomez C. “EEG during Different Emotions in 10-monthold infants of Depressed Mothers”, Journal of Reproductive and Infant Psychology, Vol 19, pp. 296- 312, 2001.##[25]. Y. P. Lin, C. H. Wang, T. L. Wu, S. K. Jeng, and J. H. Chen, “Multilayer Perceptron for EEG Signal Classification during Listening to Emotional Music”, Proceedings of TENCON 2007, pp. 1-3, 2007.## [26]. O. Danny, “EEG-based Emotion Recognition – The Influence of Visual and Auditory Stimuli”, Technical Report, pp. 1-16, B, 2008.##[27]. K. Takahashi. “ Remarks on Emotion Recognition from Bio-Potential Signals ”, IEEE Transactions on Autonomous Robots and Agents, pp. 186-191, 2004.## ##[28]. G. Chanel, K.Ansari-Asl, T.Pun,” Valence-arousal evaluation using physiological signals in an emotion recall paradigm”, IEEE trans, 1-4244-0991, pp. 2662-2666.##[29] . P. Ekman, “Emotion in the Human Face”, Cambridge University Press, New York, NY, 2nd edition, 1982.##[30] www.enterface.net ##[31]. R. L. Mandryk, M. S. Atkins, “A Fuzzy physiological Approach for Continuously Modeling Emotion During Interaction with Play Technologies”, International Journal of Human-Computer Studi es, Volume 65, Issue 4.## [32] ## ر. سپهر، "تشخیص بیماری آپنه با استفاده از سیگنال قلبی"، پایان‌نامه کارشناسی ارشد، زمستان 1386. ##[33]. G. Chanel, C. Rebetez, M. Bétrancourt, T. Pun, “Boredom, engagement and anxiety as indicators for Adaptation to difficulty in games”, Proceedings of the 12th international conference on Entertainment media, Tampere, Finland, Games track, pp. 13-17, 2008. ##[34]. K. Nazarpour, S. Sanei, L. Shoker, and J. A. Chambers, “Parallel space-time-frequency decomposition of EEG signals for brain computer interfacing,” in Proceedings of the 14th European Signal Processing Conference (EUSIPCO ’06), Florence, Italy, September 2006.##[35]. http://www.pqsystems.com/eline/2001/02/b.htm.##[36]. http://www.itl.nist.gov/div898/handbook.htm.##[37]. L. I. Aftanas, N. V. Reva, A.A. Varlamov, S.V. Pavlov, and V.P. Makhnev, “Analysis of Evoked EEG Synchronization and Desynchronization in Conditions of Emotional Activation in Humans: Temporal and Topographic” ”, Neuroscience and Bahavioral physiology, Vol. 34. No. 8, 2004.##.##[38]. L. I. Aftanas, N. V. Lotova, V. I. Koshkarov, V. P. Maknev, Y. N. Mordvinstev, S. A. Popov, “Non-linear dynamic complexity of the human EEG during evoked emotions”, International Journal of Psychophysiology, pp. 63-76, 1998. ##[39]. L. I. Aftanas, N. V. Lotova, V. I. Koshkarov, V. P. Maknev, Y. N. Mordvinstev, S. A. Popov, “Non-linear analysis of emotion EEG: calculation of Kolmogorov entropy and the principal Lyapunov exponent” Neuroscience Letters pp. 13-16, 1997. ##[40]. “Nonlinear Biomedical Signal Processing”, Metin Akay, New York, IEEE, Press Marketing, 2001.##[41]. M. Banbrook, S. McLaughlin, I. Mann, “Speech Characterization and Synthesis by Nonlinear Methods”, IEEE Transaction on Speech and Audio Processing, Vol.7, No.1, Januray 1999.##[42]. M. Hagmuller, G. Kubin, “Poincare Section for Pitch Mark Determination”.##[43]. A. C. Lindgren, M. T. Johnson, R. J. Povinelli, “Speech Recognition Using Reconstructed Phase Space Features”, ICASSP, IEEE, 2003.##[44]. M. T. Rosenstein, J. J.Collins, C. J. De Luca, “Reconstruction Expansion as a Geometry-based Framework for Choosing Proper Delay Times”, Boston university, November 1993.##[45]. I. Tokuda, “Surrogate Analysis for Detecting Nonlinear Dynamics in Normal Vowels”, Acoustical Society of America, December 2001.##[46]. R. Carvajal, N. Wessel, M. Vallverdu, P. Caminal, A. Voss, “Correlation Dimension Analysis of Heart Rate Variability in Patients With Dialated Cardiomyopathy”, Computer Methods and Programs in Biomedicine, 2005.##[47]. “Estimation and Prediction for Nonlinear Time Serie”, S. Borovkova, Chapter 2, 2001.##[48]. “Biomedical Signal Processing and Signal Modelling”, E.N. Bruce, Wiley Series in Telecommunication and Signal Processing, 2001. ##[49]. Y-C Lai, I. Osorio, M. Ann, F. Harrison, M. G. Frei, “Correlation-dimension and Autocorrelation Fluctuations in Epileptic Seizure Dynamics”, The American Physical Society, Vol. 65, 2002.##[50]. J. B.Alonso, F. Diaz-de-Maria, C. M. Travieso, M. A. Ferrer, “Using Nonlinear Features for Voice Disorder Detection”.##[51]. I. Kokkinos, P. Maragos, “Nonlinear Speech Analysis Using Models for Chaotic Systems”, IEEE Transaction on Speech and Audio Processing, Vol.13, No.6, November 2005.##[52]. W. Kinsner, “Characterizing Chaos Through Lyapunov Metrices”, IEEE Transaction on Systems, Man and Cybernetics, Vol.36, No.2, March 2006.##[53]. U. Parlitz, “Nonlinear Time Series Analysis”, Proceedings of the NDES’95, Ireland, July 1995.##[54]. R. Esteller, G. Vachtsevanos, J. Echauz, B. Litt, “A Comparison of Waveform Fractal Dimension Algorithms”, IEEE Transactions on Circuits and Systems, 2000.##[55]. F. Martinez, A. Guillamond, J.J. Martinez, “Vowel and Consonant Characterization Using Fractal Dimension in Natural Speech”, Spain.##[56]. R. Esteller, G. Vachtsevanos, J. Echauz, T.Henry, P.Pennell, C.Epstein, R.Bakay, C.Bowen, B.Litt, “Fractal Dimension Characterizes Seizure Onset in Epileptic Patients”.##[57]. A. Webb, "Statistical pattern recognition". Newyork, 1999.##[58]. E. Fix and J. L. Hodges, “Discriminatory Analysis. Nonparametric Discrimination: Consistency Properties,” Technical Report 4, Project Number 21-49-004, USAF School of Aviation Medicine, Randolph Field, TX, 1951.##[59]. E. Fix and J. L. Hodges, “Discriminatory analysis: nonparametric discrimination: small sample performance,” Technical Report No. 11. Project No. 21-49-004, USAF School of Aviation Medicine, Randolph Field, Texas, 1952.##[60]. E. J.R. Justino, F. Bortolozzi, R. Sabourin, “A Comparison of SVM and HMM Classifiers in the off-line Signature Verification”, Pattern Recognition Letters, 2004.##[61]. Y-D. Cai, X-J Liu, X-b Xu, G-P Zhou, “Support Vector Machines for Predicting Protein Structural Class”, BMC Bioinformatics, 2001.##[62]. C. J.C.Burges, “A Tutorial on Support Vector Machines for Pattern Recognition”, Data Mining and Knowledge Discovery, 1998.##[63]. J. Yao, S. Zhao, L. Fan, “An Enhanced Support Vector Machine Model for Instrusion Detection”, Canada.##[64]. K. Ansari-Asl, G. Chanel, and T. Pun, “A Channel Selection Method For EEG Classification In Emotion Assessment Based On Synchronization Likelihood”, EUSIPCO, Poznan 2007. pp 1241-1245.##[65]. D. Fran¸ cois, V. Wertz , M. Verleysen , “The permutation test for feature selection by mutual information”, ESANN'2006 proceedings - European Symposium on Artificial Neural Networks Bruges (Belgium), 26-28 April 2006, d-side publi., ISBN 2-930307-06-4.##[1]. A. Sebe, I. Cohan, T. Gevers and T.S. Huang, “Multimodal Approaches for Emotion Recognition: A Survey”, International Imaging VI. Proceedings of the SPIE, Vol. 5670, pp. 56-67, 2004.##[2]. D. O. Bos. ‘‘EEG-based Emotion Recognition the influence of visual and auditory stimuli’’, Nederland, pp. 11-16, 2006. ##[3]. J. Gratch, S. Marsella, “A Domain-independent Framework for Modeling Emotion”, Journal of Cognitive Systems Research, Vol. 5, Issue 4, pp. 269-306, 2004.##[4]. M. Grimm and K. Kroschel, “Rule-based emotion classification using acoustic feature”, in PROC.Int.Conf. on Telemedicine and Multimedia Communication, 2005.## ##[5]. A. Savran, K. Ciftci, G. Chanel, J. Cruz Mota, L. Hong Viet, B. Sankur, L. Akarun, A. Caplier, M. Rombaut” Emotion Detection in the Loop from Brain Signals and Facial Images”, eNTERFACE’06, July 17th – August 11th, Dubrovnik, Croatia. 2006.##[6]. E T. Rolls,”The Brain and Emotion”, Oxford University Press, 1998. ##[7]. J. M. Jenkins, K. Oatley, and N. L. Stein,” Human Emotions: A Reader”, Blackwell Publishers, Malden, MA, 1998.## ##[8]. C. Darwin, “The Expression of the Emotions in Man and Animals”, John Murray, London, 2nd edition, 1890.##[9]. G. Chanel, J. Kronegg, D. Grandjean, T. Pun, ‘‘Emotion assessment: Arousal evaluation using EEG's and peripheral physiological signals’’, Proc. Int. Workshop Multimedia Content Representation, Classification and Security (MRCS), Sept. 11- 13, 2006, Istanbul, Turkey, B. Gunsel, A. K. Jain, A. M. Tekalp,B. Sankur, Eds., Lecture Notes in Computer Science, Vol. 4105,Springer, 530-537.## ##[10]. J. Kim, “Emotion Recognition from Physiological Measurement (Biosignal)” Workshop Santorini, HUMAINE WP4/SG3.##[11]. M. Murugappan, M. Rizon, R. Nagarajan, S. Yacoob, M. Karthigayan and M. Sugisaka Feature Extraction Methods for Human Emotion Recognition using EEG - A Study. Malaysia-Japan International Symposium on Advanced Technology, 2007, accepted.##[12] www.nyas.org##[13]. www.thebrain.mcgill.ca ##[14].www.pga.com/improve/features/mentalgame/improve_heartmath062904.cfm.##[15]. E. Douglas-Cowie,”HUMAINE”, IST FP6 Contract no.507422, 2004.##[16]. K. H. Kim, S.W. Bang, S.R.Kim, “Emotion recognition system using short-term monitoring of physiological signals “ , Medical & Biological Engineering & Computing , vol 42. pp. 419-427, 2004.##[17]. J. Healey, R. picard, ” Digital processing of affective signals”, IEEE, 1998.##[18]. A. Haag, S. Goronzy, P. Schaich, and J. Williams, "Emotion Recognition Using Bio-Sensors: First Step Toward an Automatic System," Affective Dialog Systems: Tutorial And Research Workshop, Kloster Irsee, Germany, June 14-16, 2004.##[19]. J. Wangner, J. kim, E. Andre,” From physiological signals to emotions: implementing and comparing selected methods for feature extraction and classification”, HUMAINE FP6-2005.##[20]. R. Horlings, D. Datcu, and L J M. Rothkrantz, “Emotion Recognition using Brain Activity”, Proceedings on Int Conference on Computer Systems and Technologies, pp. II-1-1 – II-1-5, 2008.## ##[21]. K. Takahashi, A. Tsukaguchi ,“Remarks on Emotion Recognition from Multi-Modal Bio-Potential Signals”, IEEE Transactions on Industrial Technology, Vol 3, pp. 1654-1659, 2003.## ##[22]. T. Iizuka, M. Nakawa, “Emotion Analysis with Fractal-Dimension of EEG Signals”, IEIC Technical Report,Vol 102 (534), pp. 13-18, 2005.##[23]. H. Oya, H. Kawasaki, A. Mathhew, Howard III. and R. Adolphs, “Electrophysiological Responses in the Human Amygdala Discriminate Emotion Categories of Complex Visual Stimul”. The Journal of Neuroscience, Vol 22(21), pp. 9502-9512, 2002.##[24]. N. A. Jones, T. Field, N. A. M. Fox, Davalos and Gomez C. “EEG during Different Emotions in 10-monthold infants of Depressed Mothers”, Journal of Reproductive and Infant Psychology, Vol 19, pp. 296- 312, 2001.##[25]. Y. P. Lin, C. H. Wang, T. L. Wu, S. K. Jeng, and J. H. Chen, “Multilayer Perceptron for EEG Signal Classification during Listening to Emotional Music”, Proceedings of TENCON 2007, pp. 1-3, 2007.## [26]. O. Danny, “EEG-based Emotion Recognition – The Influence of Visual and Auditory Stimuli”, Technical Report, pp. 1-16, B, 2008.##[27]. K. Takahashi. “ Remarks on Emotion Recognition from Bio-Potential Signals ”, IEEE Transactions on Autonomous Robots and Agents, pp. 186-191, 2004.## ##[28]. G. Chanel, K.Ansari-Asl, T.Pun,” Valence-arousal evaluation using physiological signals in an emotion recall paradigm”, IEEE trans, 1-4244-0991, pp. 2662-2666.##[29] . P. Ekman, “Emotion in the Human Face”, Cambridge University Press, New York, NY, 2nd edition, 1982.##[30] www.enterface.net ##[31]. R. L. Mandryk, M. S. Atkins, “A Fuzzy physiological Approach for Continuously Modeling Emotion During Interaction with Play Technologies”, International Journal of Human-Computer Studi es, Volume 65, Issue 4.## [32] ## ر. سپهر، "تشخیص بیماری آپنه با استفاده از سیگنال قلبی"، پایان‌نامه کارشناسی ارشد، زمستان 1386. ##[33]. G. Chanel, C. Rebetez, M. Bétrancourt, T. Pun, “Boredom, engagement and anxiety as indicators for Adaptation to difficulty in games”, Proceedings of the 12th international conference on Entertainment media, Tampere, Finland, Games track, pp. 13-17, 2008. ##[34]. K. Nazarpour, S. Sanei, L. Shoker, and J. A. Chambers, “Parallel space-time-frequency decomposition of EEG signals for brain computer interfacing,” in Proceedings of the 14th European Signal Processing Conference (EUSIPCO ’06), Florence, Italy, September 2006.##[35]. http://www.pqsystems.com/eline/2001/02/b.htm.##[36]. http://www.itl.nist.gov/div898/handbook.htm.##[37]. L. I. Aftanas, N. V. Reva, A.A. Varlamov, S.V. Pavlov, and V.P. Makhnev, “Analysis of Evoked EEG Synchronization and Desynchronization in Conditions of Emotional Activation in Humans: Temporal and Topographic” ”, Neuroscience and Bahavioral physiology, Vol. 34. No. 8, 2004.##.##[38]. L. I. Aftanas, N. V. Lotova, V. I. Koshkarov, V. P. Maknev, Y. N. Mordvinstev, S. A. Popov, “Non-linear dynamic complexity of the human EEG during evoked emotions”, International Journal of Psychophysiology, pp. 63-76, 1998. ##[39]. L. I. Aftanas, N. V. Lotova, V. I. Koshkarov, V. P. Maknev, Y. N. Mordvinstev, S. A. Popov, “Non-linear analysis of emotion EEG: calculation of Kolmogorov entropy and the principal Lyapunov exponent” Neuroscience Letters pp. 13-16, 1997. ##[40]. “Nonlinear Biomedical Signal Processing”, Metin Akay, New York, IEEE, Press Marketing, 2001.##[41]. M. Banbrook, S. McLaughlin, I. Mann, “Speech Characterization and Synthesis by Nonlinear Methods”, IEEE Transaction on Speech and Audio Processing, Vol.7, No.1, Januray 1999.##[42]. M. Hagmuller, G. Kubin, “Poincare Section for Pitch Mark Determination”.##[43]. A. C. Lindgren, M. T. Johnson, R. J. Povinelli, “Speech Recognition Using Reconstructed Phase Space Features”, ICASSP, IEEE, 2003.##[44]. M. T. Rosenstein, J. J.Collins, C. J. De Luca, “Reconstruction Expansion as a Geometry-based Framework for Choosing Proper Delay Times”, Boston university, November 1993.##[45]. I. Tokuda, “Surrogate Analysis for Detecting Nonlinear Dynamics in Normal Vowels”, Acoustical Society of America, December 2001.##[46]. R. Carvajal, N. Wessel, M. Vallverdu, P. Caminal, A. Voss, “Correlation Dimension Analysis of Heart Rate Variability in Patients With Dialated Cardiomyopathy”, Computer Methods and Programs in Biomedicine, 2005.##[47]. “Estimation and Prediction for Nonlinear Time Serie”, S. Borovkova, Chapter 2, 2001.##[48]. “Biomedical Signal Processing and Signal Modelling”, E.N. Bruce, Wiley Series in Telecommunication and Signal Processing, 2001. ##[49]. Y-C Lai, I. Osorio, M. Ann, F. Harrison, M. G. Frei, “Correlation-dimension and Autocorrelation Fluctuations in Epileptic Seizure Dynamics”, The American Physical Society, Vol. 65, 2002.##[50]. J. B.Alonso, F. Diaz-de-Maria, C. M. Travieso, M. A. Ferrer, “Using Nonlinear Features for Voice Disorder Detection”.##[51]. I. Kokkinos, P. Maragos, “Nonlinear Speech Analysis Using Models for Chaotic Systems”, IEEE Transaction on Speech and Audio Processing, Vol.13, No.6, November 2005.##[52]. W. Kinsner, “Characterizing Chaos Through Lyapunov Metrices”, IEEE Transaction on Systems, Man and Cybernetics, Vol.36, No.2, March 2006.##[53]. U. Parlitz, “Nonlinear Time Series Analysis”, Proceedings of the NDES’95, Ireland, July 1995.##[54]. R. Esteller, G. Vachtsevanos, J. Echauz, B. Litt, “A Comparison of Waveform Fractal Dimension Algorithms”, IEEE Transactions on Circuits and Systems, 2000.##[55]. F. Martinez, A. Guillamond, J.J. Martinez, “Vowel and Consonant Characterization Using Fractal Dimension in Natural Speech”, Spain.##[56]. R. Esteller, G. Vachtsevanos, J. Echauz, T.Henry, P.Pennell, C.Epstein, R.Bakay, C.Bowen, B.Litt, “Fractal Dimension Characterizes Seizure Onset in Epileptic Patients”.##[57]. A. Webb, "Statistical pattern recognition". Newyork, 1999.##[58]. E. Fix and J. L. Hodges, “Discriminatory Analysis. Nonparametric Discrimination: Consistency Properties,” Technical Report 4, Project Number 21-49-004, USAF School of Aviation Medicine, Randolph Field, TX, 1951.##[59]. E. Fix and J. L. Hodges, “Discriminatory analysis: nonparametric discrimination: small sample performance,” Technical Report No. 11. Project No. 21-49-004, USAF School of Aviation Medicine, Randolph Field, Texas, 1952.##[60]. E. J.R. Justino, F. Bortolozzi, R. Sabourin, “A Comparison of SVM and HMM Classifiers in the off-line Signature Verification”, Pattern Recognition Letters, 2004.##[61]. Y-D. Cai, X-J Liu, X-b Xu, G-P Zhou, “Support Vector Machines for Predicting Protein Structural Class”, BMC Bioinformatics, 2001.##[62]. C. J.C.Burges, “A Tutorial on Support Vector Machines for Pattern Recognition”, Data Mining and Knowledge Discovery, 1998.##[63]. J. Yao, S. Zhao, L. Fan, “An Enhanced Support Vector Machine Model for Instrusion Detection”, Canada.##[64]. K. Ansari-Asl, G. Chanel, and T. Pun, “A Channel Selection Method For EEG Classification In Emotion Assessment Based On Synchronization Likelihood”, EUSIPCO, Poznan 2007. pp 1241-1245.##[65]. D. Fran¸ cois, V. Wertz , M. Verleysen , “The permutation test for feature selection by mutual information”, ESANN'2006 proceedings - European Symposium on Artificial Neural Networks Bruges (Belgium), 26-28 April 2006, d-side publi., ISBN 2-930307-06-4.## ##

نهان‌کاوی در تصاویر JPEG بر مبنای دسته‌بندی ویژگی‌های آماری و تصمیم‌گیری دو مرحله‌ای JPEG Image Steganalysis Based on Classification of Statistical Features and Two Stage Decision Making 1 1 در این مقاله روش جامعی برای نهان‌¬کاوی در تصاویر JPEGG معرّفی می‌شود. در این روش پس از بررسی دقیق اثر فرآیندهای پنهان‌نگاری گوناگون بر مشخصّات آماری تصویر، ویژگی‌های بهینه‌ای از تصویر استخراج می‌شود که توانایی بالایی در ایجاد تمایز بین دو گروه تصاویر طبیعی و پنهان‌نگار دارند. علاوه بر استخراج ویژگی‌های بهینه، در یک تصمیم‌گیری سلسله مراتبی دقّت تشخیص به شکل قابل توجهی افزایش یافته است. در این مقاله نشان می‌دهیم که آمارگان مرتبه اوّل ضرایب DCT (مانند هیستوگرام) بیشتر در حمله به روش‌های پنهان‌نگاری جای-گذاری در LSB (مانند JSTEG، OUTGUESS، JPHide&Seek و StegHide) موفق‌تر از آمارگان مرتبه دوم (مانند انواع همبستگی‌ها) عمل می‌کنند. همچنین مشخصات آماری مرتبه دوم در تشخیص سایر روش‌های پنهان‌نگاری در حوزه ضرایب DCT (بالاخص روش‌های تطبیق LSB، روش MB1، SSIS و روش مبتنی بر کوانتیزیشن) عملکرد بهتری از مشخصّات آماری مرتبه اوّل دارند. علاوه بر آن، روش نهان‌ کاوی معرفی شده با نگاه جامع به انواع روش‌های پنهان‌نگاری موجود، مشخّص می‌کند که نقاط ضعف هر یک در مقابل حملات آماری گوناگون چیست و چگونه می‌توان به روش‌های جاسازی امن‌تر دست پیدا کرد. نتایج تجربی نشان می‌دهد که دقّت این روش در مقایسه با روش‌های رقیب، بهتر بوده و در عین حال از جامعیت و تعمیم‌پذیری بالاتری برخوردار است. آزمایش ها روی مجموعه دوهزارتایی از تصاویر JPEG با ضرایب کیفیت متنوع انجام شده و روش معرفی شده، قادر بوده است که شش روش پنهان‌نگاری معمول (JSteg، OutGuess، F5، MB1، Sequential LSB matching و Random LSB Matching) را با دقّت بیش از 80% در نرخ های جاسازی بیش از 20% تشخیص دهد. طبقه‌بندی‌کننده‌های مورد استفاده برای طبقه‌بندی از نوع SVM هستند. 2 Abstract In this paper, we propose a comprehensive steganalysis scheme for JPEG images. In this method, the optimized features which can interpret high distinction between cover and stego images are extracted from images. These features have been selected after a careful study on modifications caused by different steganography algorithms on statistical characteristics of images. Furthermore, using a hierarchical decision making, we have considerably improved the detection accuracy. It has been shown that the first-order statistics of DCT coefficients (e.g. histogram) are often more successful than second-order statistics (e.g. different types of correlations) in detection of LSB flipping methods such as JSteg, OutGuess, JPHide&Seek and StegHide. On the other hand, the second order statistical characteristics have better performance in some other steganography methods (especially for LSB Matching, MB1, SSIS and PQ). The proposed Method reveals the weakness of the different steganography algorithms by thorough view on them. The results of our experiments indicate that the accuracy of proposed approach is better than some other state of the art steganalysis methods in the term of detection accuracy. Besides, it is more generalized and comprehensive. A database including 2000 JPEG images with different quality factors has been used for these experiments. The new scheme can detect six common steganography methods: JSteg, OutGuess, F5, MB1, Sequential and Random LSB Matching, with accuracies higher than 80% for the payload of more than 20%. We have used SVM for our classification scheme. 53 70 2009/09/222009/09/222009/09/222009/09/222009/09/22 1388/6/31 2018/02/192018/02/192018/02/192018/02/192018/02/19 1396/11/30 مریم بیگ زاده پژوهشگاه توسعه فناوری های پیشرفته خواجه نصیرالدین طوسی mbeigzadeh@aut.ac.ir محمد رضایی پژوهشگاه توسعه فناوری های پیشرفته خواجه نصیرالدین طوسی reaei.image@yahoo.com فاطمه السادات جمالی دینان پژوهشگاه توسعه فناوری های پیشرفته خواجه نصیرالدین طوسی jamalidinan@jmail.com Blind JPEG Steganalysis data hiding attack LSB flipping LSB matching feature categorization نهان‌کاوی تصاویر JPEG حمله به پنهان‌نگاری جای گذاری در LSB تطبیق LSB. دسته‌بندی ویژگی‌ها. [1] J. Fridrich, "Feature-Based Steganalysis for JPEG Images and its Implications for Future Design of Steganographic Schemes", Information Hiding, 6th International Workshop, LNCS 3200, PP 67-81, 2004.##[2] D. Fu, Y. Q. Shi, D. Zou, G. Xuan, “JPEG Steganalysis Using Empirical Transition Matrix in Block DCT Domain”, Workshop on Multimedia Signal Processing, Victoria, BC, Canada, 2006.##[3] T. Pevny, J. Fridrich, "Determining the stego algorithm for JPEG images", IEEE Proc.-Inf. Secur., vol. 153, No. 3, September 2006.##[4] T. Holotyak, J. Fridrich, S. Voloshynovskiy, "Blind Statistical Steganalysis of Additive Steganography Using Wavelet Higher Order Statistics", Proc. 9th IFIP TC-6 TC-11 Conference on Communications and Multimedia Security, Salzburg, Austria, September 19–21, 2005.##[5] F. Huang, B. Li, J. Huang, "Universal JPEG Steganalysis Based on Microscopic and Macroscopic Calibration", Proc. ICIP, PP. 2068-2071, IEEE 2008.##[6] T. Pevny, J. Fridrich, "Multi-class Blind Steganalysis for JPEG Images", Proc. SPIE Electronic Imaging, Photonics West, January 2006.##[7] T. Pevny, J. Fridrich, "Towards Multi-class Blind Steganalyzer for JPEG Images", Proc. International Workshop on Digital Watermarking, vol. 3710 of Lecture Notes in Computer Science, Siena, Italy, Springer-Verlag, Berlin, September 15–17, 2005. ##[8] T. Pevny, J. Fridrich, "Multi-Class Detector of Current Steganographic Methods for JPEG Format",, Department of Electrical and Computer Engineering, Binghamton, 2008.##[9] T. Pevny, J. Fridrich, "Merging Markov and DCT Features for Multi-Class JPEG Steganalysis", In E.J. Delp and P.W. Wong, editors, Proc. SPIE, Electronic Imaging, Security, Steganography, and Watermarking of Multimedia Contents IX, vol. 6505, PP. 03–04 January 2007.##[10] J. Fridrich, M. Goljan, R. Du, "Steganalysis Based on JPEG Compatibility", Proc. Special Digital Watermarking Data Hiding, pp. 275-280, 2001: http://www.ssie.binghamton.edu/fridrich.##[11] X. Y. Luo, D. S. Wang, P. Wang, F. L. Liu, “A review on blind detection for image steganography”, Signal Processing, doi:10.1016/j.sigpro.2008.03.016, (www.elsevier.com/locate/sigpro), 2008. ##[12] S. Lyu, H. Farid, "Detecting Hidden Messages Using Higher-Order Statistics and Support Vector Machines" Proc. 5th International Workshop on Information Hiding, 2002.##[13] S. H. ZHAN, H. B. ZHANG, "BLIND STEGANALYSIS USING WAVELET STATISTICS AND ANOVA", Proc. 6th International Conference on Machine Learning and Cybernetics, Hong Kong, 19-22 August 2007.##[14] G. Xuan, Y. Q. Shi, J. F. Gao, D. Zou, Ch. Yang, Zh. Zhang, P. Chai, C. Chen, W. Chen, “Steganalysis Based on Multiple Features Formed by Statistical Moments of Wavelet Characteristic Functions”, Springer-Verlag Berlin Heidelberg, LNCS 3727, PP. 262 – 277, 2005.##[15] C. Chen, Y. Q. Shi, W. Chen, G. Xuan, “STATISTICAL MOMENTS BASED UNIVERSAL STEGANALYSIS USING JPEG 2-D ARRAY AND 2-D CHARACTERISTIC FUNCTION”, Proc. IEEE International Conference on Image Processing (ICIP), Atlanta, GA, USA, October 2006.##[16] Y. Q. Shi, G. Xuan, Ch. Yang, J. Gao, Zh. Zhang, P. Chai, "Effective Steganalysis Based on Statistical Moments of Wavelet Characteristic Function", Proc. International Conference on Information Technology: Coding and Computing, (ITCC’05) IEEE, 2005.##[17] H. Sajedi, M. Jamzad, "A Steganalysis Method Based on Contourlet Transform Coefficients", Proc. International Conference on Intelligent Information Hiding and Multimedia Signal Processing, , PP. 245-248, 2008.##[18] X. Chen, Y. Wang, T. Tan, L. Guo, "Blind Image Steganalysis Based on Statistical Analysis of Empirical Matrix", Proc. 18th International Conference on Pattern Recognition (ICPR), 2006.##[19] Y. Q. Shi, C. Chen, W. Chen, "A Markov Process Based Approach to Effective Attacking JPEG Steganography", Information Hiding, 8th international Workshop, 2006.##[20] J. Fridrich, M. Goljan, D. Hogea, "Steganalysis of JPEG Images: Breaking the F5 algorithm", Fifth International Workshop on Information Hiding, (Noordwijkerhout, Netherlands), Springer Verlag, PP. 310-32, 2005.##[21] B. Li, F. Huang, J. Huang, "STEGANALYSIS OF LSB GREEDY EMBEDDING ALGORITHM FOR JPEG IMAGES USING COEFFICIENT SYMMETRY", IEEE, Proc. ICIP 2007.##[22] X. Yu, N. Babaguchi, "Breaking the YASS Algorithm via Pixel and DCT Coefficients Analysis", Japan Graduate School of Engineering, Osaka University, IEEE, 2008.##[23] D. Zou, Y. Q. Shi, W. Su, G. Xuan, “Steganalysis Based on Markov Model of Thresholded Prediction-Error Image”, Proc. IEEE International Conference on Multimedia and Expo (ICME), Toronto, ON, Canada, 2006.##[24] A. Westfeld, A. Pfitzmann, "Attacks on Steganographic Systems, Breaking the Steganographic Utilities EzStego, JSteg, Steganos, and S-Tools—and Some Lessons Learned", Proc. Information Hiding—3rd Int’l Workshop, Springer Verlag, PP. 61–76, 1999.##[25] N. Provos, "Defending Against Statistical Analysis", Center for Information Technology Integration, University of Michigan, 1999.##[26] J. Fridrich, J. Kodovský, and T. Pevný. "Statistically undetectable JPEG steganography: Dead ends, challenges, and opportunities". In ACM Multimedia & Security Workshop, pages 3–14, September 20–21 2007.##[27] D.C. Wu and W.H. Tsai, “A steganographic method for images by pixel-value differencing”, Pattern Recognition Letters, 2003.##[28] Ker, A. D.: Resampling and the Detection of LSB Matching in Colour Bitmaps. In: Delp, E. J., Wong, P. W. (eds.): Security, Steganography and Watermarking of Multimedia Contents VII, Proc. of SPIE, San Jose, CA (2005) 1–15.##[29] Rainer B¨ohme, "Assessment of Steganalytic Methods Using Multiple Regression Models", Technische Universit¨at Dresden, Institute for System Architecture, Germany, 2005.##[30] L. M. Marvel, Jr. C. G. Boncelet, C. T. Retter, "Spread spectrum image steganography", IEEE Trans. on Image Processing, Vol. 8(8), PP. 1075-1083, 1999.##[31] K. Sullivan, U. Madhow, Sh. Chandrasekaran, B.S. Manjunath, "Steganalysis of Spread Spectrum Data Hiding Exploiting Cover Memory", in Proc. IST/SPIE 17th Annu. Symp. Electronic Imaging Science Technology, San Jose, CA, pp. 38–46, Jan. 2005.##[32] J. J. Harmsen, “STEGANALYSIS OF ADDITIVE NOISE MODELABLE INFORMATION HIDING”, MASTER OF SCIENCE Thesis, Rensselaer Polytechnic Institute Troy, New York, April 2003.##[33] V. Sabeti, Sh. Samavi, M. Mahdavi, Sh. Shirani, "Steganalysis of Embedding in Difference of Image Pixel Pairs by Neural Network", The ISC (ISeCure) International Journal of Information Security, vol. 1, No. 1, PP. 17 - 26, January 2009.##[34] A. Ker, “Steganalysis of LSB matching in grayscale images,” IEEE Signal Process. Lett., vol. 12, No. 6, PP. 441–444, June 2005##[35] X. Mankun, L. Tianyun, P. Xijian, "Steganalysis Of LSB Matching Based On Wavelet Denoising Estimation in Grayscale Image", Proc. 2nd International Conference on Future Generation Communication and Networking, IEEE, 2008.##[36] J. Zhang, I. J. Cox, G. Do¨err, "Steganalysis for LSB Matching in Images with High-frequency Noise", Proc. MMSP,PP. 385-388, IEEE, 2007.##[37] M. Abolghasemi, H. Aghainia, K. Faez, M. A. Mehrabi, "LSB Data Hiding Detection Based on Gray Level Co-Occurrence Matrix (GLCM)", Proc. International Symposium on Telecommunications, PP. 656-659 , IEEE, 2008##[1] J. Fridrich, "Feature-Based Steganalysis for JPEG Images and its Implications for Future Design of Steganographic Schemes", Information Hiding, 6th International Workshop, LNCS 3200, PP 67-81, 2004.##[2] D. Fu, Y. Q. Shi, D. Zou, G. Xuan, “JPEG Steganalysis Using Empirical Transition Matrix in Block DCT Domain”, Workshop on Multimedia Signal Processing, Victoria, BC, Canada, 2006.##[3] T. Pevny, J. Fridrich, "Determining the stego algorithm for JPEG images", IEEE Proc.-Inf. Secur., vol. 153, No. 3, September 2006.##[4] T. Holotyak, J. Fridrich, S. Voloshynovskiy, "Blind Statistical Steganalysis of Additive Steganography Using Wavelet Higher Order Statistics", Proc. 9th IFIP TC-6 TC-11 Conference on Communications and Multimedia Security, Salzburg, Austria, September 19–21, 2005.##[5] F. Huang, B. Li, J. Huang, "Universal JPEG Steganalysis Based on Microscopic and Macroscopic Calibration", Proc. ICIP, PP. 2068-2071, IEEE 2008.##[6] T. Pevny, J. Fridrich, "Multi-class Blind Steganalysis for JPEG Images", Proc. SPIE Electronic Imaging, Photonics West, January 2006.##[7] T. Pevny, J. Fridrich, "Towards Multi-class Blind Steganalyzer for JPEG Images", Proc. International Workshop on Digital Watermarking, vol. 3710 of Lecture Notes in Computer Science, Siena, Italy, Springer-Verlag, Berlin, September 15–17, 2005. ##[8] T. Pevny, J. Fridrich, "Multi-Class Detector of Current Steganographic Methods for JPEG Format",, Department of Electrical and Computer Engineering, Binghamton, 2008.##[9] T. Pevny, J. Fridrich, "Merging Markov and DCT Features for Multi-Class JPEG Steganalysis", In E.J. Delp and P.W. Wong, editors, Proc. SPIE, Electronic Imaging, Security, Steganography, and Watermarking of Multimedia Contents IX, vol. 6505, PP. 03–04 January 2007.##[10] J. Fridrich, M. Goljan, R. Du, "Steganalysis Based on JPEG Compatibility", Proc. Special Digital Watermarking Data Hiding, pp. 275-280, 2001: http://www.ssie.binghamton.edu/fridrich.##[11] X. Y. Luo, D. S. Wang, P. Wang, F. L. Liu, “A review on blind detection for image steganography”, Signal Processing, doi:10.1016/j.sigpro.2008.03.016, (www.elsevier.com/locate/sigpro), 2008. ##[12] S. Lyu, H. Farid, "Detecting Hidden Messages Using Higher-Order Statistics and Support Vector Machines" Proc. 5th International Workshop on Information Hiding, 2002.##[13] S. H. ZHAN, H. B. ZHANG, "BLIND STEGANALYSIS USING WAVELET STATISTICS AND ANOVA", Proc. 6th International Conference on Machine Learning and Cybernetics, Hong Kong, 19-22 August 2007.##[14] G. Xuan, Y. Q. Shi, J. F. Gao, D. Zou, Ch. Yang, Zh. Zhang, P. Chai, C. Chen, W. Chen, “Steganalysis Based on Multiple Features Formed by Statistical Moments of Wavelet Characteristic Functions”, Springer-Verlag Berlin Heidelberg, LNCS 3727, PP. 262 – 277, 2005.##[15] C. Chen, Y. Q. Shi, W. Chen, G. Xuan, “STATISTICAL MOMENTS BASED UNIVERSAL STEGANALYSIS USING JPEG 2-D ARRAY AND 2-D CHARACTERISTIC FUNCTION”, Proc. IEEE International Conference on Image Processing (ICIP), Atlanta, GA, USA, October 2006.##[16] Y. Q. Shi, G. Xuan, Ch. Yang, J. Gao, Zh. Zhang, P. Chai, "Effective Steganalysis Based on Statistical Moments of Wavelet Characteristic Function", Proc. International Conference on Information Technology: Coding and Computing, (ITCC’05) IEEE, 2005.##[17] H. Sajedi, M. Jamzad, "A Steganalysis Method Based on Contourlet Transform Coefficients", Proc. International Conference on Intelligent Information Hiding and Multimedia Signal Processing, , PP. 245-248, 2008.##[18] X. Chen, Y. Wang, T. Tan, L. Guo, "Blind Image Steganalysis Based on Statistical Analysis of Empirical Matrix", Proc. 18th International Conference on Pattern Recognition (ICPR), 2006.##[19] Y. Q. Shi, C. Chen, W. Chen, "A Markov Process Based Approach to Effective Attacking JPEG Steganography", Information Hiding, 8th international Workshop, 2006.##[20] J. Fridrich, M. Goljan, D. Hogea, "Steganalysis of JPEG Images: Breaking the F5 algorithm", Fifth International Workshop on Information Hiding, (Noordwijkerhout, Netherlands), Springer Verlag, PP. 310-32, 2005.##[21] B. Li, F. Huang, J. Huang, "STEGANALYSIS OF LSB GREEDY EMBEDDING ALGORITHM FOR JPEG IMAGES USING COEFFICIENT SYMMETRY", IEEE, Proc. ICIP 2007.##[22] X. Yu, N. Babaguchi, "Breaking the YASS Algorithm via Pixel and DCT Coefficients Analysis", Japan Graduate School of Engineering, Osaka University, IEEE, 2008.##[23] D. Zou, Y. Q. Shi, W. Su, G. Xuan, “Steganalysis Based on Markov Model of Thresholded Prediction-Error Image”, Proc. IEEE International Conference on Multimedia and Expo (ICME), Toronto, ON, Canada, 2006.##[24] A. Westfeld, A. Pfitzmann, "Attacks on Steganographic Systems, Breaking the Steganographic Utilities EzStego, JSteg, Steganos, and S-Tools—and Some Lessons Learned", Proc. Information Hiding—3rd Int’l Workshop, Springer Verlag, PP. 61–76, 1999.##[25] N. Provos, "Defending Against Statistical Analysis", Center for Information Technology Integration, University of Michigan, 1999.##[26] J. Fridrich, J. Kodovský, and T. Pevný. "Statistically undetectable JPEG steganography: Dead ends, challenges, and opportunities". In ACM Multimedia & Security Workshop, pages 3–14, September 20–21 2007.##[27] D.C. Wu and W.H. Tsai, “A steganographic method for images by pixel-value differencing”, Pattern Recognition Letters, 2003.##[28] Ker, A. D.: Resampling and the Detection of LSB Matching in Colour Bitmaps. In: Delp, E. J., Wong, P. W. (eds.): Security, Steganography and Watermarking of Multimedia Contents VII, Proc. of SPIE, San Jose, CA (2005) 1–15.##[29] Rainer B¨ohme, "Assessment of Steganalytic Methods Using Multiple Regression Models", Technische Universit¨at Dresden, Institute for System Architecture, Germany, 2005.##[30] L. M. Marvel, Jr. C. G. Boncelet, C. T. Retter, "Spread spectrum image steganography", IEEE Trans. on Image Processing, Vol. 8(8), PP. 1075-1083, 1999.##[31] K. Sullivan, U. Madhow, Sh. Chandrasekaran, B.S. Manjunath, "Steganalysis of Spread Spectrum Data Hiding Exploiting Cover Memory", in Proc. IST/SPIE 17th Annu. Symp. Electronic Imaging Science Technology, San Jose, CA, pp. 38–46, Jan. 2005.##[32] J. J. Harmsen, “STEGANALYSIS OF ADDITIVE NOISE MODELABLE INFORMATION HIDING”, MASTER OF SCIENCE Thesis, Rensselaer Polytechnic Institute Troy, New York, April 2003.##[33] V. Sabeti, Sh. Samavi, M. Mahdavi, Sh. Shirani, "Steganalysis of Embedding in Difference of Image Pixel Pairs by Neural Network", The ISC (ISeCure) International Journal of Information Security, vol. 1, No. 1, PP. 17 - 26, January 2009.##[34] A. Ker, “Steganalysis of LSB matching in grayscale images,” IEEE Signal Process. Lett., vol. 12, No. 6, PP. 441–444, June 2005##[35] X. Mankun, L. Tianyun, P. Xijian, "Steganalysis Of LSB Matching Based On Wavelet Denoising Estimation in Grayscale Image", Proc. 2nd International Conference on Future Generation Communication and Networking, IEEE, 2008.##[36] J. Zhang, I. J. Cox, G. Do¨err, "Steganalysis for LSB Matching in Images with High-frequency Noise", Proc. MMSP,PP. 385-388, IEEE, 2007.##[37] M. Abolghasemi, H. Aghainia, K. Faez, M. A. Mehrabi, "LSB Data Hiding Detection Based on Gray Level Co-Occurrence Matrix (GLCM)", Proc. International Symposium on Telecommunications, PP. 656-659 , IEEE, 2008 ##

تشخیص و بررسی کاهش دامنۀ P300 در پتانسیل‌های وابسته به رویداد شنوایی تک‌ثبت با استفاده از الگوریتم ژنتیک و طبقه بندی‌کنندۀ شبکۀ عصبی Single Trial P300 Recognition in Auditory Event Related Potential Using Genetic Algorithm and Neural Network Classifier 1 1 P3000 را برجسته‌ترین مؤلّفۀ در بین مؤلّفه‌های شناختی مختلف موجود در سیگنال الکتریکی مغز می‌دانند. طبق تحقیقات انجام شده، هنگامی که مغز در حین پردازش یک سری از تحریکات معمول، به یک تحریک جدید (تحریک غیرمعمول) برمی‌‌خورد، در سیگنال مغزی ثبت‌‌شده، یک موج P300 ظاهر می‌‌شود که با تشخیص این مؤلّفه می‌توان تحریکات جدید را از تحریکات معمول جداسازی کرد. دامنۀ مؤلّفۀ P300 در هنگام اعمال تحریکات صوتی، پس از گذشت مدّت زمانی از شروع آزمایش کاهش می‌یابد؛ به نحوی که در تشخیص دامنۀ این مؤلّفه با مشکل روبرو می‌شویم. در این تحقیق با استفاده از پنج تحریک صوتی، به بررسی کاهش دامنۀ این مؤلّفه و علل آن در سه بلوک ثبت مجزّا و همچنین تشخیص این مؤلّفۀ شناختی، به وسیلۀ شبکۀ عصبی و الگوریتم ژنتیک پرداخته‌ایم. در نهایت با استفاده از ده ویژگی بهینه، به عنوان ورودی طبقه بندی کنندۀ شبکۀ عصبی در کانال Pz با صحّت 47/61% در دادگان آموزش و 60% در دادگان آزمون در بلوک اوّل، تک‌ثبت‌های حاوی موج P300 از تک‌ثبت‌های فاقد این موج جداسازی شده‌اند. 2 Abstract P300 is known as the most prominent component between cognitive components in electrical brain activity. According to done research, when brain encounters an inconsistent stimulation during processing a series of usual stimulation, a P300 component appears in recorded brain signal which could distinguishes from usual ones. Amplitude of P300 decreases after a short during act of auditory simulation; so that we face difficulty in recognition of component features. In the research we considered reduction of the amplitude of P300 with five auditory stimulations and its reasons in three separate record blocks as well as recognition of the component with Neural Network and Genetic Algorithm. Finally single-trial recordings containing P300 component from single-trial recordings without P300 component have been discriminated by six optimum features as Neural Network classifier input in Pz channel with accuracy of 80.55% in learning data and 50% in test data in the first block. 71 78 2009/09/222009/09/222009/09/222009/09/222009/09/222009/09/22 1388/6/31 2018/02/192018/02/192018/02/192018/02/192018/02/192018/02/19 1396/11/30 مهدی عبدالصالحی makhalilzadeh@mshdiau.ac.ir محمدعلی خلیل زاده makhalilzadeh@mshdiau.ac.ir محمودرضا آذرپژوه azarpazhooh@yahoo.com Electroencephalography (EEG) Event Related Potential (ERP) P300 Neural Network Genetic Algorithm الکترو انسفالوگرافی( EEG ) پتانسیل‌های وابسته به رویداد P300 شبکۀ عصبی الگوریتم ژنتیک عبدالصالحی، م؛ اکبرزاده توتونچی، م؛ تشخیص مؤلفه های شناختی در سیگنال مغزی با استفاده از ANFIS؛ یازدهمین کنفرانس بین المللی کامپیوتر تهران؛ 1384##[2] Niedermeyer, & et al "Electroencephalography: Basic Principles, Clinical Applications and Related Fields".5th ed. Philadelphia, PA: Lippincott Williams and Wilkins; 2005.##[3] N Jeremy Hill. & et al; "An Auditory Paradigm for Brain-Computer Interface"; Max Plank Institute for Biological Cybernetics; 2004##[4]ابوطالبی، و؛ مرادی ، م.ح؛ خلیل زاده، م.ع؛ تشخیص مؤلفه های شناختی در سیگنال های مغزی با استفاده از ضرایب ویولت؛فصلنامه مهندسی پزشکی زیستی؛ شماره اول،سال اول##[5] Odin van der Stelt & et al; "Application of Electroencephalography to the Study of Cognitive and Brain Functions in Schizophrenia"; Schizophrenia Bulletin vol. 33 no. 4 pp. 955–970, 2007## [6] Lindin M & et al; "Stimulus intensity effects on P300 amplitude across repetition of standard auditory Oddball task"; Biological Psychology; Vol. 69; PP 375-385; 2005##[7] Kalatzis, I;et al; Design and implementation of an SVM-based computer classification system for discriminating depressive patients from healthy controls using the P600 component of ERP signals, Computer Methods and Programs in Biomedicine, Vol.75, pp.11-22, 2004.##[8] Miller,M.T.,Jerebko, A.K., Malley, J.D. and Summers, R.M., "Feature Selection Algorithm", Proceedings of SPIE, Vol.5031, pp.102-110, 2003##[9] Lindin M,et al; "Changes in P300 amplitude during an active standard auditory oddball task"; Biological Psychology; pp. 153-167, 2004##عبدالصالحی، م؛ اکبرزاده توتونچی، م؛ تشخیص مؤلفه های شناختی در سیگنال مغزی با استفاده از ANFIS؛ یازدهمین کنفرانس بین المللی کامپیوتر تهران؛ 1384##[2] Niedermeyer, & et al "Electroencephalography: Basic Principles, Clinical Applications and Related Fields".5th ed. Philadelphia, PA: Lippincott Williams and Wilkins; 2005.##[3] N Jeremy Hill. & et al; "An Auditory Paradigm for Brain-Computer Interface"; Max Plank Institute for Biological Cybernetics; 2004##[4]ابوطالبی، و؛ مرادی ، م.ح؛ خلیل زاده، م.ع؛ تشخیص مؤلفه های شناختی در سیگنال های مغزی با استفاده از ضرایب ویولت؛فصلنامه مهندسی پزشکی زیستی؛ شماره اول،سال اول##[5] Odin van der Stelt & et al; "Application of Electroencephalography to the Study of Cognitive and Brain Functions in Schizophrenia"; Schizophrenia Bulletin vol. 33 no. 4 pp. 955–970, 2007## [6] Lindin M & et al; "Stimulus intensity effects on P300 amplitude across repetition of standard auditory Oddball task"; Biological Psychology; Vol. 69; PP 375-385; 2005##[7] Kalatzis, I;et al; Design and implementation of an SVM-based computer classification system for discriminating depressive patients from healthy controls using the P600 component of ERP signals, Computer Methods and Programs in Biomedicine, Vol.75, pp.11-22, 2004.##[8] Miller,M.T.,Jerebko, A.K., Malley, J.D. and Summers, R.M., "Feature Selection Algorithm", Proceedings of SPIE, Vol.5031, pp.102-110, 2003##[9] Lindin M,et al; "Changes in P300 amplitude during an active standard auditory oddball task"; Biological Psychology; pp. 153-167, 2004## ##

تشخیص عابر پیاده با استفاده از کلاس بندهای SVM و هیستوگرام در توالی تصاویر مادون قرمز Pedestrian Detection in Infrared Image Sequences Using SVM and Histogram Classifiers 1 1 در محیط‌هایی که نمی‌توان از چشم غیر مسلح و دوربین‌های معمولی برای تشخیص انسان از غیر انسان استفاده کرد ( مانند محیط‌های تاریک، مه و دود)، بهترین راه حل استفاده از تصاویر مادون قرمز است. این مقاله یک روش مقاوم برای تشخیص انسان در توالی تصاویر مادون قرمز ارایه می‌دهد. برای این منظور از ترکیب کلاس‌بند SVM و کلاس‌بند مبتنی بر هیستوگرام استفاده شده است؛ به این ترتیب که الگوهایی از تصویر که احتمال حضور انسان در آن‌ها موجود می‌‌باشد، پس از فرآیندپیش پردازش استخراج شده و به کلاس‌بندهای هیستوگرام و SVM داده می‌شوند. برای یادگیری و تست الگوریتم ارایه شده از پایگاه دادۀ گرمایی عابرپیادۀ OSU استفاده شده است. نتایج اجرای الگوریتم ارایه شده روی این پایگاه داده، کارآیی و دقّت آن را نشان می‌دهد. 2 Abstract In dark environments and foggy or smoky conditions where it is not possible to use eyesight and usual binoculars to detect human from other objects, the best solution is to use infrared images. This paper presents a robust method to recognize pedestrians in infrared image sequences. For this purpose, combination of SVM and histogram classifiers has been used. A pre-processing phase extracts image patterns similar to human patterns and delivers them to histogram and SVM classifiers. For training and testing phases of the presented algorithm thermal data base of OSU pedestrian video sequences has been utilized. Results of the algorithm present its good accuracy and performance. 79 90 2009/09/222009/09/222009/09/222009/09/222009/09/222009/09/222009/09/22 1388/6/31 2018/02/192018/02/192018/02/192018/02/192018/02/192018/02/192018/02/19 1396/11/30 محسن محسنی دانشگاه آزاد ملارد m@mohseni@comp.iust.ac.ir محسن سریانی دانشگاه علم و صنعت soryani@iust.ac.ir Pedestrian detection Infrared images Support Vector Machine Histogram classifie تشخیص عابر پیاده تصاویر مادون قرمز ماشین بردار پشتیبان هیستوگرام [1] http://nncf.unl.edu/eldercare/info/seniordriving/nightdrive.html. Technical Report 6, Nebraska Highway Safety Program and the Lincoln-Lancaster County Health Department, July 2001.##[2] M Bertozzi, A Broggi, MD Rose, A Lasagni, “Infrared Stereo Vision-based Pedestrian Detection”, Procs. IEEE Intelligent Vehicles Symposium, 2005.##[3] L. Zhao and C. Thorpe, “Stereo and neural network-based pedestrian detection,” IEEE Trans. on Intelligent Transportation Systems, vol. 1, no. 3, pp. 148–154, Sept. 2000.##[4] C. Mertz, S. McNeil, and C. Thorpe, “Side collision warning systems for transit buses,” in IEEE Intelligent Vehicle Symp., Oct. 2000.##[5] M. Bertozzi et al., “Pedestrian detection in infrared images,” in Proc. IEEE Intelligent Vehicles Symp., Columbus, OH, pp. 662–667, June 2003.##[6] A. Broggi et al., “Shape-based pedestrian detection,” in Proc. IEEE Intelligent Vehicles Symp., Dearbon, MI, pp. 215–220, 2000.##[7] Takayuki Tsuji, Hiroshi Hattori, Masahito Watanabe, and Nobuharu Nagaoka. "Development of night-vision system", IEEE Transactions on ITS, Vol. 3 No.3, pages 203-209, Sept. 2002.##[8] H. Elzein et al., “A motion and shape-based pedestrian detection algorithm,” in Proc. IEEE Intelligent Vehicles Symp., Columbus, OH, pp. 500–504, June 2003.##[9] م. محسنی، م. سریانی. تشخیص عابر پیاده در توالی تصاویر مادون قرمز با استفاده از SVM . کنفرانس ماشین بینایی و پردازش تصویر ایران، 1387.##[10] A. Mohan and T. Poggio, “Example-based object detection in images by components,” IEEE Trans.Pattern Anal.Machine Intell., vol. 23, pp. 349–361, Apr. 2001.##[11] H. Nanda and L. Davis, “Probabilistic template based pedestrian detection in infrared videos,” presented at the IEEE IntelligentVehicles Symp., Versailles, France, June 2002.##[11][12] B. E. Boser, I. M. Guyon and V. N.Vapnik, “A training algorithm for optimal margin classifiers”, Proceedings of the fifth annual workshop on Computational learning theory, 1992.##[12][13] J. Davis and V. Sharma, "Background-Subtraction using Contour-based Fusion of Thermal and Visible Imagery," Computer Vision and Image Understanding, Vol 106, No. 2-3, 2007, pp. 162-182.##[13][14] OSU Thermal Pedestrian Database, http://www.cse.ohio-state.edu/otcbvs-bench/##[14][15] Support Vector Machine toolbox for Matlab Version 2.51, Anton Schwaighofer. January 2002##[1] http://nncf.unl.edu/eldercare/info/seniordriving/nightdrive.html. Technical Report 6, Nebraska Highway Safety Program and the Lincoln-Lancaster County Health Department, July 2001.##[2] M Bertozzi, A Broggi, MD Rose, A Lasagni, “Infrared Stereo Vision-based Pedestrian Detection”, Procs. IEEE Intelligent Vehicles Symposium, 2005.##[3] L. Zhao and C. Thorpe, “Stereo and neural network-based pedestrian detection,” IEEE Trans. on Intelligent Transportation Systems, vol. 1, no. 3, pp. 148–154, Sept. 2000.##[4] C. Mertz, S. McNeil, and C. Thorpe, “Side collision warning systems for transit buses,” in IEEE Intelligent Vehicle Symp., Oct. 2000.##[5] M. Bertozzi et al., “Pedestrian detection in infrared images,” in Proc. IEEE Intelligent Vehicles Symp., Columbus, OH, pp. 662–667, June 2003.##[6] A. Broggi et al., “Shape-based pedestrian detection,” in Proc. IEEE Intelligent Vehicles Symp., Dearbon, MI, pp. 215–220, 2000.##[7] Takayuki Tsuji, Hiroshi Hattori, Masahito Watanabe, and Nobuharu Nagaoka. "Development of night-vision system", IEEE Transactions on ITS, Vol. 3 No.3, pages 203-209, Sept. 2002.##[8] H. Elzein et al., “A motion and shape-based pedestrian detection algorithm,” in Proc. IEEE Intelligent Vehicles Symp., Columbus, OH, pp. 500–504, June 2003.##[9] م. محسنی، م. سریانی. تشخیص عابر پیاده در توالی تصاویر مادون قرمز با استفاده از SVM . کنفرانس ماشین بینایی و پردازش تصویر ایران، 1387.##[10] A. Mohan and T. Poggio, “Example-based object detection in images by components,” IEEE Trans.Pattern Anal.Machine Intell., vol. 23, pp. 349–361, Apr. 2001.##[11] H. Nanda and L. Davis, “Probabilistic template based pedestrian detection in infrared videos,” presented at the IEEE IntelligentVehicles Symp., Versailles, France, June 2002.##[11][12] B. E. Boser, I. M. Guyon and V. N.Vapnik, “A training algorithm for optimal margin classifiers”, Proceedings of the fifth annual workshop on Computational learning theory, 1992.##[12][13] J. Davis and V. Sharma, "Background-Subtraction using Contour-based Fusion of Thermal and Visible Imagery," Computer Vision and Image Understanding, Vol 106, No. 2-3, 2007, pp. 162-182.##[13][14] OSU Thermal Pedestrian Database, http://www.cse.ohio-state.edu/otcbvs-bench/##[14][15] Support Vector Machine toolbox for Matlab Version 2.51, Anton Schwaighofer. January 2002## ##