Detection of walking phases by EEG signal processing and using neural networks based on deep learning
محل انتشار: هشتمین کنفرانس بین المللی پژوهش در علوم و مهندسی و پنجمین کنگره بین المللی عمران، معماری و شهرسازی آسیا
سال انتشار: 1402
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 82
فایل این مقاله در 7 صفحه با فرمت PDF قابل دریافت می باشد
- صدور گواهی نمایه سازی
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
ICRSIE08_120
تاریخ نمایه سازی: 18 فروردین 1403
چکیده مقاله:
EEG-based BCI was recently applied to lower limb exoskeleton robots. Various machine learning decoders have shown high accuracy performance on classifying the gait state whether the subject is walking or standing. However, there is a trade-off between the accuracy and the responsiveness due to the delay time. The delay time is critical when controlling the exoskeleton robots with EEG decoders online (real-time). In this research, we propose spatio-spectral convolutional neural networks with relatively short segment of EEG data (۰.۲s) having ۸۳.۴% accuracy on gait state recognition. The gait intention recognition that detects the subject’s gait intention prior to the actual gait had ۷۷.۳% accuracy. We were able to classify EEG data of both healthy subjects and stroke patients at sub-acute and chronic phases.
کلیدواژه ها:
نویسندگان
Saied Piri
Research Center for Computational Cognitive Neuroscience, System & Cybernetic Laboratory, Imam Reza International University, Mashhad, Iran
Arefeh Dinarvand
UAST-University of Applied Science and Technology X-IBM Institute, Tehran, Iran
Kazem Sohrabi
Bachelor of Aerospace Engineering majoring in air structures, Shahid Sattari Aeronautical University, Tehran, Iran