Improved and Secured Electromyography in the Internet of Health Things.

Physiological signals are of great importance for clinical analysis but are prone to diverse interferences. To enable practical applications, biosignal quality issues, especially contaminants, need to be dealt with automated processes. For example, after processing surface electromyography (sEMG), fatigue analysis can be done by looking into muscle contraction and expansion for clinical diagnosis. Contaminants can make this diagnosis difficult for the clinician. In real scenarios, there is a possibility of the presence of multiple contaminants in a biosignal. However, most of the work done until now focuses on the presence of a single contaminant at a time. This paper proposes a new method for the identification and classification of contaminants in sEMG signals where multiple contaminants are present simultaneously. We train a 1D convolutional neural network (1D-CNN) to classify different contaminant types in sEMG signals without prior feature extraction. The network is trained on simulated and real sEMG signals to identify five types of contaminants. Additionally, we train and test 1D-CNN to identify multiple contaminants when present simultaneously. Furthermore, to securely and accurately transfer the data to the clinician, we also present experimental results to securely route the data in a proposed Internet of health things (IoHT) by using received signal strength indicators (RSSI) to generate link fingerprints (LFs). The results show higher accuracy of the classification system at low signal-to-noise ratios (SNR) and witness lightweight security of the IoHT.