FFM: A Muscle Fatigue Index Extraction by Utilizing Fuzzy Network and Mean Power Frequency

Muscular fatigue refers to changes in the domain of amplitude and frequency for the muscle contractions. Muscle fatigue is important to the researchers for being familiar with muscle mechanism, rehabilitation, ergonomics, electrical functional stimulation and prosthesis control. Moreover, its significance to clinical research to identify weak muscle and demonstrate the strength training exercise efficiency. In the present article, we propose Fuzzy Fatigue Model (FFM) which impost muscle fatigue index by mean of the raw EMG signal. FFM consist of two parts or fuzzy-network: First network, mean power frequency (MPF) estimation. Second network, imposts fatigue index as demonstration of muscle power drop. The mean power frequency (MPF) was employed as an index to represent the background activity. The novelty of our FFM, it uses raw EMG signal as input without any necessity to normalize with signal processing. Moreover, mapping muscle fatigue index as output without any mathematical operation requirement. Our FFM succeed to overpass 0:999 in the regression and 10 -5 on root mean square error (MSE), which proves the qualification of the models. In addition, an investigation of the relationship between muscle fatigue and age was done in this study. According to our volunteer’s ages the percent of power drop is between 20% and 42% of biceps brachii muscle, as well as, increasing around 1% in muscle power decline for the triceps than biceps brachii muscles.