Surface Mechanomyography (MMG) is the recording of mechanical activity of muscle tissue. MMG measures the mechanical signal (vibration of muscle) that generated from the muscles during contraction or relaxation action. This project is determined to focus on the study and develop suitable procedures and methods to analyze and classify muscle activity during biceps exercise using MMG Signals. There are two channels of MMG signal has been placed into biceps brachii muscles (Short Head Biceps Brachii and Long Head Biceps Brachii) by using VMG sensor (TSD250A) with two different weights. Five features have been selected and utilized to proceed with analysis and classification in this project. These features were root mean square (RMS), standard deviation (STD), root sum square (RSSQ), peak to peak value, and peak absolute value to root mean square ratio. The analysis and classification is divided into two sections, which are comparison between different training data set proportion for Back-Propagation Artificial Neural Network (BPANN) and analysis of MMG signal with different weights. The finding of the result shows, the BPANN proposed was able to classify all samples in to the target output with an average accuracy above 80%.
