Upper Limb Movements Identification through EMG Signal using Artificial Neural Network
M. Karuna1, A. Sampath Dakshina Murthy2, G. Thiagarajan3, Sitaramanjaneya Reddy Guntur3
1M. Karuna, Department of Electronics and Communication Engineering, Vignan’s Institute of Information Technology, Visakhapatnam (A.P), India.
2A. Sampath Dakshina Murthy, Department of Electronics and Communication Engineering, Vignan’s Institute of Information Technology, Visakhapatnam (A.P), India.
3G. Thiagarajan, Department of Electronics and Communication Engineering, Vignan’s Institute of Information Technology, Visakhapatnam (A.P), India.
4Sitaramanjaneya Reddy Guntur, Associat Professor, Dept. of Electronics and Communication Engineering, Vignan Foundation for Science, Technology and Research, Visakhapatnam (A.P), India.
Manuscript received on 18 June 2019 | Revised Manuscript received on 25 June 2019 | Manuscript published on 30 June 2019 | PP: 1284-1286 | Volume-8 Issue-5, June 2019 | Retrieval Number: E6905068519/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Nowadays, analysis of electromyography (EMG) signal is one of the powerful areas of interest in medical, rehabilitation, robotic and industrial fields. The measurement refers to the recording of electric signals that appear during muscle contraction. As these signals are related to human process of action, because of uncertainty of EMG signals proper prediction of a specific motion is difficult. An Identification of a specific wrist motion by means of the EMG signal pattern will help in controlling prosthetic hand. A movement recognition technique is required to segregate different wrist movements for instance extension, flexion, pronation, supination. In this direction the EMG signal pattern recognition includes feature extraction and classification of proper EMG signals obtained from human forearm muscles using Artificial Neural Network to establish control over the prosthetic hand. Training of ANN was performed using four input neurons, four output layers, and with 10 hidden layers achieved 90% overall accuracy.
Keywords: Electromyography Signal, EMG, Feature Extraction, Artificial Neural Network.
Scope of the Article: Artificial Intelligence