?url_ver=Z39.88-2004&rft_id=UET-AVITECH-2019002&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.relation=https%3A%2F%2Feprints.uet.vnu.edu.vn%2Feprints%2Fid%2Feprint%2F3444%2F&rft.title=Simultaneous+tensor+decomposition+for+EEG+epileptic+spike+detection&rft.creator=Le%2C+Trung+Thanh&rft.creator=Nguyen%2C+Thi+Anh+Dao&rft.creator=Nguyen%2C+Viet+Dung&rft.creator=Nguyen%2C+Linh+Trung&rft.creator=Abed-Meraim%2C+Karim&rft.subject=Electronics+and+Communications&rft.subject=Information+Technology+(IT)&rft.description=Objective%3A+Epilepsy+is+one+of+the+most+common+brain+disorders.+For+epilepsy+diagnosis+or+treatment%2C+the+neurologist+needs+to+observe+epileptic+spikes+from+electroencephalography+(EEG)+data.+Since+multi-channel+EEG+records+can+be+naturally+represented+by+multi-way+tensors%2C+it+is+of+interest+to+see+whether+tensor+decomposition+is+able+to+analyze+EEG+epileptic+spikes.%0D%0AApproach%3A+In+this+report%2C+we+first+proposed+the+problem+of+simultaneous+multilinear+low-rank+approximation+of+tensors+(SMLRAT)+and+proved+that+SMLRAT+can+obtain+local+optimum+solutions+by+using+two+well-known+tensor+decomposition+algorithms+(HOSVD+and+Tucker-ALS).+Second%2C+we+presented+a+new+system+for+automatic+epileptic+spike+detection+based+on+SMLRAT.%0D%0AMain+results%3A+We+compared+the+proposed+tensor+analysis+method+with+other+common+tensor+methods+in+analyzing+EEG+signal+and+compared+the+proposed+feature+extraction+method+with+Phan%E2%80%99s+method.+Experimental+results+indicated+that+our+proposed+method+is+able+to+detect+epileptic+spikes+with+good+performance.%0D%0ASignificance%3A+To+suitably+deal+with+EEG+spikes%2C+we+developed+a+local+solution+for+nonnegative+SMLRAT.+For+practical+implementation%2C+we+proposed+the+generalized+SMLRAT+algorithm+to+effectively+solve+the+SMLRAT+and+nonnegative+SMLRAT+problems.+An+efficient+EEG+feature+extraction+framework+was+proposed%2C+based+on+estimating+the+%E2%80%9Ceigenspikes%E2%80%9D+from+the+nonnegative+generalized+SMLRAT+algorithm.&rft.publisher=University+of+Engineering+and+Technology%2C+Vietnam+National+University&rft.date=2019-04-18&rft.type=Technical+Report&rft.type=NonPeerReviewed&rft.format=application%2Fpdf&rft.language=en&rft.identifier=https%3A%2F%2Feprints.uet.vnu.edu.vn%2Feprints%2Fid%2Feprint%2F3444%2F1%2FEEG_Ten_Technical_Report_Final.pdf&rft.identifier=++Le%2C+Trung+Thanh+and+Nguyen%2C+Thi+Anh+Dao+and+Nguyen%2C+Viet+Dung+and+Nguyen%2C+Linh+Trung+and+Abed-Meraim%2C+Karim++(2019)+Simultaneous+tensor+decomposition+for+EEG+epileptic+spike+detection.++Technical+Report.+University+of+Engineering+and+Technology%2C+Vietnam+National+University%2C+Hanoi%2C+Vietnam.+++++&rft.relation=UET-AVITECH-2019002