نوع مقاله : مقاله کامل پژوهشی

نویسندگان

1 مربی، دانشگاه آزاد اسلامی، واحد شیراز، گروه مهندسی کامپیوتر

2 دانشیار، گروه مهندسی پزشکی، دانشکده مهندسی، دانشگاه شیراز

3 دانشیار، گروه علوم و مهندسی کامپیوتر، دانشکده مهندسی، دانشگاه شیراز

10.22041/ijbme.2010.13296

چکیده

پیش‌بینی زمان وقوع حملات صرع در بیماران از جمله موضوعاتیست که مورد توجه محققان است. حملات صرع به طور نامنظم و غیر قابل پیش‌بینی شده‌ای اتفاق می‌افتند. بنابراین تشخیص حملات صرع از روی سیگنال‌های EEGکه در بازة زمانی طولانی گرفته می‌شوند؛ بسیار حائز اهمیت است. این امر تشخیصی به دو مرحله مجزای استخراج ویژگی‌ها از قطعات سیگنال EEGو اعمال الگوریتم طبقه‌بندی بر روی بردارهای ویژگی تقسیم می‌شود. به همین منظور در مرحله اول با استفاده از تحلیل زمان- فرکانس بر روی قطعات سیگنال EEGو به‌دست آوردن صفحه زمان- فرکانس هر قطعه، استخراج ویژگی‌ها از سیگنال‌ها انجام می‌شود. در مرحله دوم با استفاده از الگوریتم نزدیک‌ترین همسایه کار تشخیص حملات صورت می‌گیرد. اما قبل از اعمال الگوریتم طبقه‌بندی، برای اصلاح فضای ویژگی‌ها و یادگیری معیار فاصله، از الگوریتم AIS-RCAاستفاده شده است. این الگوریتم برای به‌دست آوردن ماتریس تبدیل W، داده‌ها را به صورت مجموعه‌ای از دسته‌ها در نظر می‌گیرد و با ارائه الگوریتم جدید AD-AIRSو با الهام گرفتن از سیستم ایمنی بدن دسته‌ها را می‌یابد. آزمایش‌های انجام شده نشان دهندة دقت 100% و بهبود نتایج در مقایسه با برخی روش‌های انتقال موجک، آنتروپی، معیار بی‌نظمی و تبدیل انتقال فوریه سریع را نشان می‌دهد.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

AIS-RCA: An Efficient Feature Reduction Method to Improve the Seizure Detection Rate

نویسندگان [English]

  • Amin Zare 1
  • Reza Boostani 2
  • Mansour Zolghadr Jahromi 3

1 Instructor, Department of Computer Engineering, Shiraz Branch, Islamic Azad University

2 Associate Professor, Biomedical Engineering Group, Department of Computer Sciences and Engineering, Shiraz University

3 Associate Professor, Department of Computer Sciences and Engineering, Shiraz University

چکیده [English]

There is a growing interest to improve seizure prediction by online analyzing of electroencephalogram (EEG) signals in epileptic patients. Seizure attack is occurred infrequently and unpredictably; hence, automatic detection of seizure during long-term is highly recommended. In this paper a novel Feature Reduction method namely AIS-RCA which adopted from the immunity system is proposed to improve the seizure detection rate. The automatic seizure detection can be performed in two successive stages: 1) The feature extraction/selection stage from EEG signals and 2) classifying the feature vectors by an efficient classifier. In this study, first, pseudo-Wigner-Ville distribution was applied to each window of the EEG signals and then the extracted features were transformed by AIS-RCA transform to represent the features in a more separable space. The AIS-RCA transformation matrix is estimated by using chunklets (a chunklet is defined as a subset of points that are known to be same). AIS-RCA using the proposed Artificial Immune System algorithm named Adaptive Distance-AIRS to discover the chunklets in the data space. Finally KNN classifier was applied to the transformed features to classify the seizure and non-seizure windows. The experimental results show that the proposed method yields epileptic detection accuracy rate up to 99.9% which is better than the results achieved by other types of features such as FFT, Wavelet transform, entropy and chaotic measures.

کلیدواژه‌ها [English]

  • EEG signal
  • Time-Frequency Analysis
  • Spectrum
  • Epileptic seizures
  • AIS-RCA
  • AD-AIRS
  • RCA
  • Artificial Immune System (AIS)
[1]      Subasi A., Alkan A., Koklukaya E., Kiymik M.K., Wavelet neural network classification of EEG signals by using AR model with MLE preprocessing; Neural Networks, 2005; 18(7): 985–997.
[2]      Subasi A., EEG signal classification using wavelet feature extraction and a mixture of expert model; Expert Systems with Applications, 2007; 32(4): 1084–1093.
[3]      Sadati N., Mohseni H.R., Maghsoudi A., Epileptic seizure detection using neural fuzzy networks; in Proceedings of IEEE International Conference on Fuzzy Systems (FUZZY ’06), 2006: 596–600.
[4]      Guo L., Rivero D., Pazos A., Epileptic seizure detection using multiwavelet transform based approximate entropy and artificial neural networks; Journal of Neuroscience Methods, 2010; 193(1): 156–163.
[5]      Tzallas A.T., Karvelis P.S., Katsis C.D., Fotiadis D.I., Giannopoulos S., Konitsiotis S., A method for classification of transient events in EEG recordings: application to epilepsy diagnosis; Methods of Information in Medicine, 2006; 45(6): 610–621.
[6]      Argoud F.I.M., de Azevedo F.M., Neto J.M., Grillo E., SADE3: an effective system for automated detection of epileptic form events in long-term EEG based on context information; Medical and Biological Engineering and Computing, 2006; 44(6): 459–470.
[7]      Murro A.M., King D.W., Smith J.R., Gallagher B.B., Flanigin H.F., Meador K., Computerized seizure detection of complex partial seizures; Electroencephalography and Clinical Neurophysiology, 1991; 79(4): 330–333.
[8]      Lerner D.E., Monitoring changing dynamics with correlation integrals: case study of an epileptic seizure; Physica D:NonlinearPhenomena,1996;97(4):563–576.
[9]      Lehnertz K., Elger C.E., Spatio-temporal dynamics of the primary epileptogenic area in temporal lobe epilepsy characterized by neuronal complexity loss; Electroencephalography and Clinical Neurophysiology, 1995; 95(2): 108–117.
[10]   G¨uler N.F., Ubeyli E.D., G¨uler I., Recurrent neural networks employing Lyapunov exponents for EEG signals classification; Expert Systems with Applications, 2005; 29(3): 506–514.
[11]   Kannathal N., Choo M.L., Acharya U.R., Sadasivan P.K., Entropies for detection of epilepsy in EEG; Computer Methods and Programs in Biomedicine, 2005; 80(3): 187–194.
[12]   Ocak H., Automatic detection of epileptic seizures in EEG using discrete wavelet transform and approximate entropy; Expert Systems with Applications, 2009; 36(2): 2027–2036.
[13]   Paivinen N., Lammi S., Pitkanen A., Nissinen J., Penttonen M., Gronfors T., Epileptic seizure detection: a nonlinear viewpoint; Computer Methods and Programs in Biomedicine, 2005; 79(2): 151–159.
[14]   Kannathal N., Acharya U.R., Lim C.M., Sadasivan P.K., Characterization of EEG—a comparative study;Computer Methods and Programs in Biomedicine, 2005; 80(1): 17–23.
[15]   Polat K., G¨unes S., Classification of epileptic form EEG using a hybrid system based on decision tree classifier and fast Fourier transform; Applied Mathematics and Computation, 2007; 187(2): 1017–1026.
[16]   Mohseni H., Maghsoudi A., Kadbi M., Hashemi J., Ashourvan A., Automatic detection of epileptic seizure using time–frequency distributions; In: IET 3rd International Conference on Advances in Medical Signal and Information Processing MEDSIP, 2006: 1–4.
[17]   Gardner A.B., Krieger A.M., Vachtsevanos G., Litt B., One-class novelty detection for seizure analysis from intracranial EEG; Journal of Machine Learning Research, 2006, 7: 1025–1044.
[18]   Übeyli E.D., Support vector machines for detection of electrocardiographic changes in partial epileptic patients; Engineering Applications of Artificial Intelligence, 2008; 21(8): 1196– 1203.
[19]   Temko A., Thomas E., Marnane W., Lightbody G., Boylan G., EEG-based neonatal seizure detection with Support Vector Machines; Clinical Neurophysiology, 2011; 122(3): 464–473.
[20]   Boashash B., Mesbah M., Golditz P., Time frequency detection of EEG abnormalities; in Time-Frequency Signal Analysis and Processing: A Comprehensive Reference, 2003; 15: 663-670.
[21]   Hassanpour H., Mesbah M., Boashash B., Time frequency based newborn EEG seizure detection using low and high frequency signatures; Physiological Measurement, 2004; 25(4): 935–944.
[22]   Boashash B., Mesbah M., Time-frequency methodology for newborn electroencephalographic seizure detection; in Applications in Time-Frequency Signal Processing, 2003; 9: 339–369.
[23]   Tzallas A.T., Tsipouras M.G., Fotiadis D.I., Automatic Seizure Detection Based on Time-Frequency Analysis and Artificial Neural Networks; Computational Intelligence and Neuroscience, 2007: 1-13.
[24]   He X., King O., Ma W.Y., Li M., Zhang H. J., Learning a semantic space from user’s relevance feedback for image retrieval; IEEE Trans on Circuits and Systems for Video Technology, 2003; 13(1): 39-48.
[25]   Muller H., Pun T., Squire D., Learning from user behavior in image retrieval: Application of market basket analysis; International Journal of Computer Vision, 2004; 56(1-2): 65-77.
[26]   Hastie T., Tibshirani R., Discriminant adaptive nearest neighbor classification; IEEE Pattern Analysis and Machine Intelligence, 1996; 18(6): 607-616.
[27]   Tenenbaum J., Freeman W., Separating Style and content with bilinear models; neural computation, 2000; 12(6): 1247-1283.
[28]   Bar-Hillel A., Hertz T., Shental N., Weinshall D., Learning Distance Functions using Equivalence Relations; in: Proceedings of the Twentieth International Conference on Machine Learning, 2003: 11-18.
[29]   Watkins A., Timmis J., Artificial Immune Recognition System (AIRS): Revisions and Refinements; International Conference on Artificial Immune Systems, 2002: 173-181.
[30]   Watkins A., AIRS: A resource limited artificial immune classifier; M.S. thesis, 2001.
[31]   Watkins A., Boggess L., A new classifier based on resource limited artificial immune systems; Proceedings of the Evolutionary Computation, 2002; 2: 1546-1551.
[32]   Andrzejak R.G., Lehnertz K., Mormann F., Rieke C., David P., Elger C.E., Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: dependence on recording region and brain state; Physical Review E, 2001; 64(6): 8-23.
[33]   Srinivasan V., Eswaran C., Sriraam A.N., Artificial neural network based epileptic detection using time-domain and frequency-domain features; Journal of Medical Systems, 2005; 29(6): 647–660.
[34]   Guo L., Rivero D., Seoane J., Pazos A., Classification of EEG signals using relative wavelet energy and artificial neural networks; In: Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation, 2009: 177–84.
[35]   Guo L., Rivero D., Dorado J., Rabunal J.R., Pazos A., Automatic epileptic seizure detection in EEGs based on line length feature and artificial neural networks; Journal of Neuroscience Methods, 2010; 191(1): 101–109.
[36]   Sivasankari N., Thanushkodi K., Automated Epileptic Seizure Detection in EEG Signals Using FastICA and Neural Network; Advanced Soft Computing and Application, 2009; 1(2): 91-104.
[37]   Chan M., Sun T., Boto H., Wingeier M., Automated seizure onset detection for accurate onset time determination in intracranial EEG; Clinical Neurophysiology, 2008; 119 (12): 2687–2696.
[38]   Mohseni H.R., Maghsoudi A., Shamsollahi M.B., Seizure Detection in EEG signals: A Comparison of Different approaches; Engineering in Medicine and Biology Society EMBS '06, 2006: 6724 – 6727.
[39]   Allen R.L., Mills D.W., Signal Analysis: Time, Frequency, Scale, and Structure; Wiley-IEEE Press 2004.
[40]   Auger F., Flandrin P., Goncalv`es P., Lemoine O., Time- Frequency Toolbox; Rice University and CNRS France, 1996.
[41]   Shental N., Hertz T., Weinshall D., Pavel M., Adjustment learning and relevant component analysis; in Proc. of the European Conference on Computer Vision, 2002:776–792.
[42]   BarHillel A., Hertz T., Shental N., Weinshall D., Learning distance functions using equivalence relations; in Proc. International Conference on Machine Learning, 2003: 11-18.
[43]   Shental N., Hertz T., Weinshall D., Pavel M., Adjustment Learning and Relevant Component Analysis; Proceedings of the 7th European Conference on Computer Vision, 2002: 776-792.
[44]   Wang J., Neskovic P., Cooper L., Improving nearest neighbor rule with a simple adaptive distance measure; Pattern Recognition Letters, 2007; 28(2): 207–213.
[45]   Nigam V., Graupe D., A neural-network-based detection of epilepsy; Neurological Research, 2004; 26(1): 55–60.