Design and Implementation of GUI Package for the Muscle Diseases Recognition Based on EMG Signals

An artificial neural network (ANN) provides a comprehensive and specialized service for the diagnosis and care of muscle diseases. Medical consultations are offered at the neuromuscular clinics, which are staffed by neurologists with special expertise in muscle diseases. This work presents the design and implementation of muscle diseases detection based on real electromyography (EMG) signals. This paper consists of three main parts. The first part presents the measurement of the signals of real human arm muscles (EMG signal). The data are then rearranged and recorded using EMGLab software. Surface electrodes are used to measure the real EMG signals. The suitable features of signal are extracted for classification. The second part applies signal requirements, such as filtering amplification and normalization, using MATLAB or any software. Muscle diseases were classified using an ANN package based on the features of EMG signals, amplitude of signals, and period of signals to identify the diseases. The third part explains the design of the graphical user interface based on MATLAB to implement the classification on real EMG signals. Satisfactory results are obtained from numerous executions with different cases of human arm muscles, thus ensuring the feasibility of this design for practical implement in hospitals or private clinics. Index Term- Electromyography (EMG) signals; Graphical User Interface (GUI); EMGLab software.

[1]  O. Bida Influence of Electromyogram (EMG) Amplitude Processing in EMG-Torque Estimation , 2005 .

[2]  N. P. Reddy,et al.  Neural network committees for finger joint angle estimation from surface EMG signals , 2009, Biomedical engineering online.

[3]  Todd A. Kuiken,et al.  A multiple-layer finite-element model of the surface EMG signal , 2002, IEEE Transactions on Biomedical Engineering.

[4]  yousif al mashhadany Design and Analysis of Virtual Human Arm Driven by Emg Signal , 2010 .

[5]  Toshio Tsuji,et al.  Pattern classi " cation of time-series EMG signals using neural networks , 2000 .

[6]  Dario Farina,et al.  Simulation of surface EMG signals generated by muscle tissues with inhomogeneity due to fiber pinnation , 2004, IEEE Transactions on Biomedical Engineering.

[7]  Osamah A. Alsayegh EMG-based human-machine interface system , 2000, 2000 IEEE International Conference on Multimedia and Expo. ICME2000. Proceedings. Latest Advances in the Fast Changing World of Multimedia (Cat. No.00TH8532).

[8]  Anne K. G. Murphy Effective Information Display and Interface Design for Decomposition-based Quantitative Electromyography , 2002 .

[9]  Toshio Tsuji,et al.  Pattern classification of time-series EMG signals using neural networks , 2000 .

[10]  Daniel W. Stashuk,et al.  Physiologically based simulation of clinical EMG signals , 2005, IEEE Transactions on Biomedical Engineering.

[11]  Yousif I. Al-Mashhadany MEASUREMENT OF HUMAN LEG JOINT ANGLE THROUGH MOTION BASED ON ELECTROMYGRAPHY (EMG) SIGNAL1 , 2011 .

[12]  M. Z. Al-Faiz,et al.  Human Arm Movements Recognition Based on EMG Signal , 2022 .

[13]  Toshio Tsuji,et al.  EMG-Based Motion Discrimination Using a Novel Recurrent Neural Network , 2003, Journal of Intelligent Information Systems.

[14]  Ashok A. Ghatol,et al.  Design of Adaptive Filter Using Jordan/Elman Neural Network in a Typical EMG Signal Noise Removal , 2009, Adv. Artif. Neural Syst..

[15]  F. Mohd-Yasin,et al.  Techniques of EMG signal analysis: detection, processing, classification and applications , 2006, Biological Procedures Online.