انتخاب یک فضای ویژگی بهینه در تشخیص حملات صرعی بر پایه آنالیز کمی‌سازی بازگشتی و الگوریتم ژنتیک
محورهای موضوعی : پردازش سیگنالهای پزشکی
1 - دانشجوی دکترا - دانشکده مهندسی برق، واحد مشهد، دانشگاه آزاد اسلامی، مشهد، ایران
2 - استادیار - دانشکده مهندسی برق، واحد مشهد، دانشگاه آزاد اسلامی، مشهد، ایران
کلید واژه: الگوریتم ژنتیک, انتخاب ویژگی, الکتروانسفالوگرام, تشخیص حمله صرعی, آنالیز کمی‌سازی بازگشتی,
چکیده مقاله :
در طبقه‌بندی داده‌ها انتخاب فضای ویژگی متناسب با ماهیت پدیده و قدرت تفکیک بالا بسیار حائز اهمیت است. قابلیت نگاشت بازگشتی در تحلیل دادگان غیرایستا موجب می‌شود در تشخیص حملات صرعی نیز مورد توجه قرار گیرد. در این پژوهش به تشخیص حملات صرعی توسط آنالیز کمی‌سازی بازگشتی بر پایه ترکیب الگوریتم ژنتیک و طبقه‌بند بیزین پرداخته شده است. در ابتدا نگاشت بازگشتی سیگنال EEG دو گروه صرعی و نرمال هریک شامل 100 نمونه، بازای پنج نوع معیار فاصله (ماکزیمم فاصله، مینیمم فاصله، اقلیدوسی، ماهالانوبیس، منهتن) و 10 حد آستانه(ε) مختلف تشکیل و بهترین مجموعه ویژگی بازای 50 تکرار الگوریتم ژنتیک بر اساس نرخ طبقه‌بندی بیزین انتخاب گردید. نتایج، نشانگر کارایی بالای روش پیشنهادی بوده به گونه‌ای که با انتخاب معیار مینیمم فاصله و حدآستانه 1˂ε˂ 1/0 تفکیک 100 % است. همچنین روش نسبت به حد آستانه (ε) و معیار فاصله حساسیت پایینی دارد. ویژگی Trans با بیشترین مشارکت در انتخاب ویژگی و بالاترین صحت، به عنوان ویژگی بهینه معرفی می‌شود.
Selecting optimal features based on nature of the phenomenon and high discriminant ability is very important in the data classification problems. Since it doesn't require any assumption about stationary condition and size of the signal and the noise in Recurrent Quantification Analysis (RQA), it may be useful for epileptic seizure Detection. In this study, RQA was used to discriminate ictal EEG from the normal EEG where optimal features selected by combination of algorithm genetic and Bayesian Classifier. Recurrence plots of hundred samples in each two categories were obtained with five distance norms in this study: Euclidean, Maximum, Minimum, Normalized and Fixed Norm. In order to choose optimal threshold for each norm, ten threshold of ε was generated and then the best feature space was selected by genetic algorithm in combination with a bayesian classifier. The results shown that proposed method is capable of discriminating the ictal EEG from the normal EEG where for Minimum norm and 0.1˂ε˂1, accuracy was 100%. In addition, the sensitivity of proposed framework to the ε and the distance norm parameters was low. The optimal feature presented in this study is Trans which it was selected in most feature spaces with high accuracy.
[1] M. Azarnoosh, "Variability of non-linear dynamic parameters of EEG signal in attentive long-term activity", Ph.D. Thesis, Islamic Azad University, Science and Research Branch, Tehran, Iran, 2012.
[2] S. Lashkari, "Evaluation of EEG signals during Epileptic seizures based on nonlinear features", Msc. Thesis, Islamic Azad University, Mashhad Branch, Mashhad, Iran, 2013.
[3] D. Kalyanmoy, et al. "A fast and elitist multi objective genetic algorithm: NSGA-II", IEEE Trans. on Evolutionary Computation, Vol. 6, No. 2, pp. 182-197, 2002.
[4] N. Faghih, A. Honarvar. " Genetic algorithms in planning preventive inspections", 2005.
[5] O. Gaoxiang. L. Xiaoli, D. Chuangyin, "Using recurrence plot for determinism analysis of EEG recordings in genetic absence epilepsy rats", Clinical neurophysiology, Vol. 119, pp. 1747–1755, 2008.
[6] U. Rajendra, et al, "Application of recurrence quantification analysis for the automated identification of epileptic EEG signals", International Journal of Neural Systems, Vol. 21, pp. 199-211, 2011.
[7] M. Niknazar, et al, "A new framework based on recurrence quantification analysis for epileptic seizure detection", IEEE Journal of Biomedical and Health Informatics, Vol. 17, pp. 572-578, 2013.
[8] N. Marwan, M.C. Romano, M. Thiel, "Recurrence plots for the analysis of complex systems", Physics Reports, Vol. 438, pp. 237–329, 2007.
[9] H. Rashidy, K. Faez, M. Hosseinzadeh, "Face recognition system using ant colony optimization-based selected features", Proceeding of the IEEE/CISDA, pp. 57-62, Honolulu, HI, April 2007.
[10] W. Siedlecki, J. Sklansky, "A note on genetic algorithms for large-scale feature selection", Pattern Recognition Letters, Vol. 10, pp. 335-347, 1989.
[11] A. Bon, et al, "Feature selection in beltline moulding process using genetic algorithm", Journal of Applied Sciences Research, Vol. 4, pp. 783-792, 2008.
[12] R. Jensen, "Combining rough and fuzzy sets for feature selection", Ph.D. Thesis, School of Informatics, University, Edinburgh, 2005.
[13] B. Liu, B. McKay, "Classification rule discovery with ant colony optimization", Proceeding of the IEEE/WIC/ACM, pp. 83-88, Oct. 2003.
[14] Y. Meng, "A swarm intelligence based algorithm for proteomic pattern detection of ovarian cancer", Proceeding of the IEEE/CIBCB, pp. 1-7, Toronto, Ont., Sep. 2006.
[15] R.G. Andrzejak, et al, "Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: Dependence on recording region and brain state", Physical Review, pp. 64, 2001.
[16] K. Ansari-Asl, et al. "Comparison of two estimators of time-frequency interdependencies between nonstationary signals: application to epileptic EEG", Proceeding of the IEEE/IEMBS, Vol. 1, pp. 263-266, San Francisco, CA, Sep. 2004.
[17] M.P. Tarvainen, et al., "Estimation of nonstationary EEG with Kalman smoother approach: an application to event-related synchronization (ERS)", IEEE Trans. on Biomedical Engineering, Vol. 51, No. 3, pp. 516-524, March 2004.
[18] Kaplan, Y. Alexander, et al., "Nonstationary nature of the brain activity as revealed by EEG/MEG: Methodological, practical and conceptual challenges", Signal Processing, Vol. 85, No. 11, pp. 2190-2212, 2005.
[19] T. Dikanev, et al. "EEG nonstationarity during intracranially recorded seizures: statistical and dynamical analysis." Clinical Neurophysiology, Vol. 116, No. 8, pp. 1796-1807, 2005.
[20] K.B. Korb, E. Ann, Nicholson. "Bayesian artificial intelligence". CRC press, 2010.
[21] C.R. Twardy, et al., "Epidemiological data mining of cardiovascular Bayesian networks", Electronic Journal of Health Informatics. 2006.
[22] V.P Nigam, G. Daniel, "A neural-network-based detection of epilepsy", Neurological Research, Vol. 26, pp. 55-60, 2004.
[23] N. Kannathal, et al, "Entropies for detection of epilepsy in EEG", Computer Methods and Programs in Biomedicine, Vol. 80, pp. 187-194, 2005.
[24] V. Srinivasan, C. Eswaran, N. Sriraam, "Artificial neural network based epileptic detection using time-domain and frequency-domain features", Journal of Medical Systems, Vol. 12, pp. 647-660, 2005.
[25] N. Sadati, H. Mohseni, A. Maghsoudi, "Epileptic seizure detection using neural fuzzy networks", Proceeding of the IEEE/FUZZY, pp. 596-600, Vancouver, BC, 2006.
[26] A. Subasi, "EEG signal classification using wavelet feature extraction and a mixture of expert model", Expert Systems with Applications, Vol. 32, pp. 1084-1093, 2007.
[27] K. Polat, G. Salih, "Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast Fourier transform", Applied Mathematics and Computation, Vol. 187, pp. 1017-1026, 2007.
[28] A.T. Tzallas, M.G. Tsipouras, D.I. Fotiadis, "Automatic seizure detection based on time-frequency analysis and artificial neural networks", Comput Intell Neurosci, 2007.
[29] V. Srinivasan, C. Eswaran, N. Sriraam, "Approximate entropy-based epileptic EEG detection using artificial neural networks", IEEE Trans. on Information Technology in Biomedicine, Vol. 11, pp. 288-295, 2007.
[30] P. Kemal, G. Salih, “Artificial immune recognition system with fuzzy resource allocation mechanism classifier, principal component analysis and FFT method based new hybrid automated identification system for classification of EEG signals”, Expert Systems with Applications, Vol. 34, pp. 2039-2048, 2008.
[31] K. Polat, G. Salih, "A novel data reduction method: Distance based data reduction and its application to classification of epileptiform EEG signals", Applied Mathematics and Computation, Vol. 200, pp. 10-27, 2008.
[32] H. Ocak, "Automatic detection of epileptic seizures in EEG using discrete wavelet transform and approximate entropy", Expert Systems with Applications, Vol 36, pp. 2027-2036, 2009.
[33] L. Guo, et al, "Classification of EEG signals using relative wavelet energy and artificial neural networks", Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation, 2009.
[34] L. Guo, R. Daniel, P. Alejandro, "Epileptic seizure detection using multiwavelet transform based approximate entropy and artificial neural networks", Journal of Neuroscience Methods, Vol. 193, pp. 156-163, 2010.
[35] L. Guo, et al, "Automatic epileptic seizure detection in EEGs based on line length feature and artificial neural networks", Journal of Neuroscience Methods, Vol. 191, pp. 101-109, 2010.
[36] A. Subasi, G.M. Ismail, "EEG signal classification using PCA, ICA, LDA and support vector machines", Expert Systems with Applications, Vol. 37, pp. 8659-8666, 2010.
[37] E. Übeyli, "Least squares support vector machine employing model-based methods coefficients for analysis of EEG signals", Expert Systems with Applications, Vol. 37, pp. 233-239, 2010.
[38] C. Lima, C. André, E. Marcio, "Tackling EEG signal classification with least squares support vector machines: A sensitivity analysis study", Computers in Biology and Medicine, Vol. 40, pp. 705-714, 2010.
[39] L. Guo, et al, "Automatic feature extraction using genetic programming: An application to epileptic EEG classification", Expert Systems with Applications, Vol. 38, pp. 10425-10436, 2011.
[40] D. Wang, M. Duoqian, X. Chen, "Best basis-based wavelet packet entropy feature extraction and hierarchical EEG classification for epileptic detection", Expert Systems with Applications, Vol. 38, pp. 14314-14320, 2011.
[41] Z. Iscan, D. Zümray, D. Tamer, "Classification of electroencephalogram signals with combined time and frequency features", Expert Systems with Applications, Vol. 38, pp. 10499-10505, 2011.
[42] U. Orhan, M. Hekim, M. Ozer, "EEG signals classification using the K-means clustering and a multilayer perceptron neural network model", Expert Systems with Applications, Vol. 38, pp. 13475–13481, 2011.
[43] L. Charles, J. Webber, N. Marwan, "Recurrence quantification analysis: Theory and best practices", Springer, 2014.
[44] J. Webber, L. Charles, J.P. Zbilut, "Recurrence quantification analysis of nonlinear dynamical systems", Tutorials in Contemporary Nonlinear Methods for the Behavioral Sciences, pp. 26-94, 2005.
_||_