Application of One Dimensional Convolutional Neural Network in Gait Phase Recognition During Level Ground Walking Using sEMG Signals

سال انتشار: 1400
محل انتشار: بیست و نهمین همایش سالانه بین المللی انجمن مهندسان مکانیک ایران و هشتمین همایش صنعت نیروگاه های حرارتی
کد COI اختصاصی: ISME29_113
زبان مقاله: انگلیسی
تعداد مشاهده: 387

دانلود فایل این مقاله

نویسندگان

Saeed Rezaeian

Center of Advanced Systems and Technologies (CAST), University of Tehran, Tehran

Aghil Yousefi-Koma

Center of Advanced Systems and Technologies (CAST), University of Tehran, Tehran

Pezhman Abdolahnezhad

Center of Advanced Systems and Technologies (CAST), University of Tehran, Tehran

Shahriar Sheikh Abumasoudi

Center of Advanced Systems and Technologies (CAST), University of Tehran, Tehran

چکیده

Nowadays, there is no doubt about the application of gait analysis in biomechanics especially assistive robotics such as prosthesis and exoskeletons. For these applications, Surface electromyography (sEMG) signals play an important role that can interact with users and predict their intentions. Two criteria that should be considered in every method of classification especially in human applications are accuracy and power of generalization. In this paper, the concept of one-dimensional Convolutional Neural Network (CNN) is employed to classify the gait cycle into two main sub-phases: swing and stance. Surface electromyography (sEMG) signals and Force-Sensing Resistor (FSR) data are collected from four locations of under knee muscles and sole respectively during level-ground walking. Then, these signals feed into CNN in an appropriate format. The power of prediction of this method (using only sEMG signals for gait event detection) is remarkable which is over ۹۰ percent. Consequently, the results of this research approve the theory that this method of classification has more preferences than methods that have been used in former researches.

کلیدواژه ها

Gait Phase Detection, sEMG signal, Convolutional Neural Networks (CNN), Inertial Measurement Unit

مقالات مرتبط جدید

اطلاعات بیشتر در مورد COI

COI مخفف عبارت CIVILICA Object Identifier به معنی شناسه سیویلیکا برای اسناد است. COI کدی است که مطابق محل انتشار، به مقالات کنفرانسها و ژورنالهای داخل کشور به هنگام نمایه سازی بر روی پایگاه استنادی سیویلیکا اختصاص می یابد.

کد COI به مفهوم کد ملی اسناد نمایه شده در سیویلیکا است و کدی یکتا و ثابت است و به همین دلیل همواره قابلیت استناد و پیگیری دارد.