تشخیص خودکار صرع گراندمال و بازشناسی اعمال عادی در ویدئو با تلفیق تکنیک‌های بینایی ماشین و یادگیری ماشین
محورهای موضوعی : مهندسی برق و کامپیوترامین حکیمی راد 1 * , نصراله مقدم چركری 2
1 - دانشگاه تربیت مدرس
2 - دانشگاه تربیت مدرس
کلید واژه: صرع گراندمال تشخیص خودکار ویژگی‌های هندسی ماشین بردار پشتیبان چندکلاسه,
چکیده مقاله :
متداول‌ترین روش در تشخیص تشنجات صرعی روش مبتنی بر پردازش سیگنال‌های EEG حاصل از انجام الکتروآنسفالوگرافی می‌باشد که به دلیل نیاز به اتصال الکترودهایی به نواحی مختلف از سر فرد مشکلات حرکتی زیادی به وجود می‌آورد. هدف این تحقیق تشخیص خودکار و هوشمندانه صرع گراندمال و نیز بازشناسی اعمال عادی فرد مبتلا به عارضه از طریق نظارت ویدئویی می‌باشد. در این مقاله از ترکیب دو تکنیک بینایی ماشین و یادگیری ماشین به منظور تشخیص صرع گراندمال و بازشناسی اعمال عادی برای فردی استفاده می‌شود که روی زمین و یا تخت دراز کشیده است. بعد از حذف پس‌زمینه از دنباله قاب‌های ویدئویی و جداسازی شبح تصاویر، ویژگی‌های هندسی مناسب استخراج شده و به عنوان ورودی به دسته‌بند ماشین بردار پشتیبان چندکلاسه اعمال گردید تا عمل دسته‌بندی ویدئوها و تخصیص برچسب رفتاری مناسب به صورت خودکار انجام شود. تمامی پیاده‌سازی‌های این تحقیق در محیط نرم‌افزار Matlab نسخه a.2011 انجام شده است. در این سیستم هوشمند، میانگین دقت تشخیص و بازشناسی 21/90 درصد می‌باشد. به کارگیری این سیستم علاوه بر کاهش ناظر انسانی، کمک زیادی در تشخیص به موقع و همیشگی عارضه می‌نماید. این روش به دلیل نیاز به یک دوربین فیلم‌برداری ساده و یک سیستم کامپیوتری معمولی، روشی مقرون به صرفه بوده و برای قشرهای درآمدی مختلف قابل تهیه است. علاوه بر آن غیر تماسی بودن سیستم پیشنهادی، عاملی برای حذف مشکلات حرکتی است. دقت بالا تأییدکننده کارایی مناسب این سیستم می‌باشد.
The most relevant method to detect epileptic seizures is the electroencephalogram (EEG) based signal processing method which, due to the need for installing some electrodes on different places of the person's head, causes many movement problems. The aim of this research is to automatically and intelligently detect grand-mal epileptic seizures and also to recognize normal activities of a person suffering from the disease by video surveillance. In this paper we have used the combination of machine vision and machine learning techniques to automatically detect grand-mal epileptic seizure when the person is lying on the ground or on the bed. After subtracting the background from video frame sequences and extracting the image silhouette, appropriate geometrical features have been extracted and fed to the multi-class support vector machine as the input for automatically classifying the videos and assigning proper activity label. All the implementations have been done on MATLAB R2011a. In this intelligent system the accuracy of detecting and recognizing activities is 90.21%. Using this system in addition to reducing the number of human observers is very helpful for the on time and constant detection of the condition. The need for just a conventional video camera and a computer system makes it affordable for people with different incomes. Because it needs not to be in contact with the person's body, there is no movement problem too. High accuracy verifies the optimal performance of the system.
[1] G. C. A. Epilepsy, "Atlas: epilepsy care in the world 2005," Programme for Neurological Diseases and Neuroscience, Department of Mental health and Substance Abuse, World Health Organization.
[2] K. Cuppens, L. Lagae, B. Ceulemans, S. Van Huffel, and B. Vanrumste, "Detection of nocturnal frontal lobe seizures in pediatric patients by means of accelerometers," in Proc. Annual Int. Conf. of the IEEE Engineering in Medicine and Biology Society, pp. 6608-6611, 3-6 Sep. 2009.
[3] T. M. E. Nijsen, P. J. M. Cluitmans, J. B. A. M. Arends, and P. A. M. Griep, "Detection of subtle nocturnal motor activity from 3-D accelerometry recordings in epilepsy patients," IEEE Trans. on Biomedical Engineering, vol. 54, no. 11, pp. 2073-2081, Nov. 2007.
[4] P. Jallon, S. Bonnet, M. Antonakios, and R. Guillemaud, "Detection system of motor epileptic seizures through motion analysis with 3D accelerometers," in Proc. Annual Int. Conf. of the IEEE Engineering in Medicine and Biology Society, pp. 2466-2469, 3-6 Sep. 2009.
[5] I. Conradsen et al., "Multi-modal intelligent seizure acquisition (MISA) system - a new approach towards seizure detection based on full body motion measures," in Proc. Annual Int. Conf. of the IEEE Engineering in Medicine and Biology Society, pp. 2591-2595, 3-6 Sep. 2009.
[6] R. Yadav, Automatic Detection and Classification of Neural Signals in Epilepsy, Concordia University, 2012.
[7] A. Shoeb et al., "Patient - specific seizure onset detection," Epilepsy & Behavior, vol. 5, no. 4, pp. 483-498, Aug. 2004.
[8] K. Cuppens, L. Lagae, B. Ceulemans, S. Van Huffel, and B. Vanrumste, "Automatic video detection of body movement during sleep based on optical flow in pediatric patients with epilepsy," Medical and Biological Engineering and Computing, vol. 48, no. 9, pp. 923-931, Sep. 2010.
[9] K. Cuppens, B. Vanrumste, B. Ceulemans, L. Lagae, and S. Van Huffel, "Detection of epileptic seizures using video data," in Proc. Sixth Int. Conf. on Intelligent Environments, IE 2010, pp. 372-373, 19-21 Jul. 2010.
[10] Q. Liu, R. Sclabassi, and M. Sun, "A new change detection method and its application to epilepsy monitoring video," in Proc. of the IEEE 30th Annual Northeast Bioengineering Conf., pp. 59-60, 17-18 Apr. 2004.
[11] Q. Liu, R. Sclabassi, and M. Sun, "Change detection in epilepsy monitoring video based on Markov random field theory," in Proc. of 2004 Int. Symp. on Intelligent Signal Processing and Communication Systems, ISPACS'04, pp. 63-66, 18-19 Nov. 2004.
[12] N. B. Karayiannis et al., "Automated detection of videotaped neonatal seizures based on motion segmentation method," Clinical Neurophysiology, vol. 117, no. 7, pp. 1585-1594, Jul. 2006.
[13] H. Lu, H. L. Eng, B. Mandal, D. W. S. Chan, and Y. L. Ng, "Markerless video analysis for movement quantification in pediatric epilepsy monitoring," in Proc. Annual Int. Conf. of the IEEE Engineering in Medicine and Biology Society, pp. 8275-8278, 2011.
[14] R. Hammoud, Interactive Video: Algorithms and Technologies, Springer-Verlag New York, Inc, 2006.
[15] D. G. Stork, R. O. Duda, and P. E. Hart, Pattern Classification, 2nd. ed., New York: John Wiley & Sons, 2001.
[16] V. Vapnik, The Nature of Statistical Learning Theory, Springer, 1999.
[17] T. Y. Wang and H. M. Chiang, "Fuzzy support vector machine for multi-class text categorization," Information Processing & Management, vol. 43, no. 4, pp. 914-929, Jul. 2007.
[18] T. Joachims, "Text categorization with support vector machines: learning with many relevant features," Machine Learning: ECM-98, vol. 1398, pp. 137-142, 1998.
[19] J. Salomon, Support Vector Machines for Phoneme Classification, Master's Thesis, University of Edinburgh, 2001.
[20] M. Pontil and A. Verri, "Support vector machines for 3D object recognition," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 20, no. 6, pp. 637-646, Jun. 1998.
[21] K. Takeuchi and N. Collier, Bio - Medical Entity Extraction Using Support Vector Machines, Association for Computational Linguistics, 2003.
[22] G. M. Foody and A. Mathur, "A relative evaluation of multiclass image classification by support vector machines," IEEE Trans. on Geoscience and Remote Sensing, vol. 42, no. 6, pp. 1335-1343, Jun. 2004.
[23] F. Melgani and L. Bruzzone, "Classification of hyperspectral remote sensing images with support vector machine," IEEE Trans. on Geoscience and Remote Sensing, vol. 42, no. 8, pp. 1778-1790, Aug. 2004.
[24] C. W. Hsu and C. J. Lin, "A comparison of methods for multiclass support vector machines," IEEE Trans. on Neural Networks, vol. 13, no. 2, pp. 415-425, Mar. 2002.