Design and Implementation of GUI Package for the Muscle Diseases Recognition Based on EMG Signals
Yousif I. Al Mashhadany1, Eman Huassan2, Aseel Najeeb3
1Asst. Prof. Dr. Yousif Ismail Al Mashhadany, Electrical Engineering Depatment, Engineering College, University of Anbar, Anbar, Iraq.
2Eng. Eman Huassan and Eng. Aseel Najeeb, Electrical Engineering Depatment, Engineering College, University of Anbar, Anbar, Iraq.
3Eng. Eman Huassan and Eng. Aseel Najeeb, Electrical Engineering Depatment, Engineering College, University of Anbar, Anbar, Iraq.
Manuscript received on May 03, 2014. | Revised Manuscript received on May 03, 2014. | Manuscript published on May 05, 2014. | PP: 40-44 | Volume-4 Issue-2, May 2014. | Retrieval Number: B2191054214/2014©BEIESP
Open Access | Ethics and Policies | Cite
©The Authors. Published By: 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: 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.
Keywords: Electromyography (EMG) signals; Graphical User Interface (GUI), EMGLab software.