“…Most of these studies tried to extract time and frequency domain features such as mean, standard deviation, skewness, and FFT peaks from raw signals to feed them to a classifier for activity identification [21,22]. According to the achieved results in human activity recognition systems, applying pattern recognition on the collected data by IMU sensors can reliably and accurately detect physical activities which are an evidence for the possibility of applying such techniques to automatically detect SMMs in ASD children [23,24,25,26,27,28,29,30,31,32,33,34,35,36]. Despite meaningful amount of research in this direction, few challenges for automatic SMM detection using wearable sensors still remain unsolved especially in real-time applications.…”