Comparison of Surface Electromyogram Signal for Prosthetic Applications

Background: Since surface electromyogram (SEMG) signal plays a vital role in prosthetic designs, hence the evaluation of these signals for identifying the upper arm motions leading to myoelectric control based design of artificial devices is presented. Methods: A total of two upper limb locations were chosen for recording of data, thereafter the evaluation and interpretation of signal was done for the estimation of extracted parameters using simulated algorithm (four arm activities were performed). A statistical algorithm of two way ANOVA for estimating the effectiveness of recorded signal followed by a discriminant classifier for pattern recognition task was investigated. Results: Outcome of the proposed study after analyzing the effectiveness of recorded data supports the formularize reparability of the classification approach for signal accuracies (97.50%). Conclusion: Finally, the simulation study based on muscle modeling allowed us to explore the parameters that affect the muscle-force relationship prior to prostheses design. Further, the proposed study will also help researchers in understanding the nature of these complex signals particularly in biomedical applications.