Classification of selected finger movements with single-channel electromyography by decision tree

  • سال انتشار: 1403
  • محل انتشار: اولین کنفرانس بین المللی دوسالانه هوش مصنوعی و علوم داده
  • کد COI اختصاصی: DSAI01_010
  • زبان مقاله: انگلیسی
  • تعداد مشاهده: 266
دانلود فایل این مقاله

نویسندگان

Ali Ghanbar

Department of Medical Engineering, Faculty of Medical Sciences and Technologies, Islamic Azad University Research and Sciences Branch,Tehran, Iran

Shiva Kazembeigibarzi

Department of Medical Engineering, Faculty of Medical Sciences and Technologies, Islamic Azad University Research and Sciences Branch,Tehran, Iran

Amirali Alilooie

Department of Medical Engineering, Faculty of Medical Sciences and Technologies, Islamic Azad University Research and Sciences Branch,Tehran, Iran

Sarvin Tohidi

Department of Medical Engineering, Faculty of Medical Sciences and Technologies, Islamic Azad University Research and Sciences Branch,Tehran, Iran

Babak Rezaee Afshar

PhD in Medical Engineering, Department of Orthotics and Prosthetics, Faculty of Rehabilitation Iran University of Medical Science, Tehran, Iran

چکیده

Electromyography signals are used in areas such as artificial limbs, rehabilitation, diagnostic medicine, and wearable and control instruments. In this paper, we present a method for classifying the ۱۲ most widely used everyday movements for controlling modern artificial hands and making them smart. The sEMG signals were recorded from ten volunteers and classified after the noise removal process using Butterworth Filter ۳, classification, and window placement. In this study, ۲۴ features extracted in the time-frequency domain were used. The results show that using the decision tree classifier one channel sEMG signal was classified with ۹۱.۴% accuracy. In future studies, a combination of other biological signals such as electroencephalography could be used to improve detection and reduce the time of segregation.

کلیدواژه ها

Signal Processing; Electromyography; Decision Tree; Intelligent Orthotics and Artificial Prosthetics; Classification; Machine Learning

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.