Open AccessEfficient Control System Based on Hand Nerve Signals
Author(s) -
Ahmed Abbas,
Muayad Sadik Croock
Publication year - 2019
Publication title -
al-maǧallaẗ al-ʻirāqiyyaẗ li-handasaẗ al-ḥāsibāt wa-al-ittiṣālāt wa-al-sayṭaraẗ wa-al-naẓm
Language(s) - English
Resource type - Journals
eISSN - 2617-3352
pISSN - 1811-9212
DOI - 10.33103/uot.ijccce.19.3.3
Subject(s) - electromyography , computer science , flexibility (engineering) , controller (irrigation) , biceps , process (computing) , arduino , signal processing , artificial intelligence , signal (programming language) , computer hardware , speech recognition , pattern recognition (psychology) , digital signal processing , physical medicine and rehabilitation , medicine , mathematics , embedded system , programming language , statistics , agronomy , biology , operating system
Recent advances in the control applications based on hand nerve signals are able to meet the needs of users who suffer from restrictions in limb movement and also provide high performance control for those paralyzed people. These signals are represented as Electromyography (EMG) signals, which are biomedical ones, used for clinical/biomedical applications. In this work, a control signals generation system is proposed based on hand EMG measurements. The process of acquisition and processing of EMG signals is performed by only one channel surface EMG electrodes with one EMG processing unit as a muscle sensor. In this work, Arduino UNO is adopted as an analog to digital converter for these hand nerve signals to be easily analyzed in the classification process. These signals are measured from the skin surface of forearm and biceps muscles in two suggested case studies to be used in generating signals based on ten muscles movements. The main features that crystallized this research is building a smart control algorithm which increases the flexibility of generating precise control signals based on contracted hand movements with high simplicity of use and the low cost. The obtained results are compared to other systems results to show the ability of achieving 93.81% classification rate or accuracy among other systems.