“…Time and frequency domain features of muscle activity are often used for movement, position, and gesture classification of hand prostheses to varying degrees of success [13,14]. In an analogous way to sensory feedback, individual differences, 1 Morenike Reni Magbagbeola and Rui Loureiro are with the Wellcome-EPSRC Centre for Interventional and Surgical Science (WEISS) and with Aspire Centre for Rehabilitation Engineering and Assistive Technology (CREATe), University College London, United Kingdom email:{ morenike.magbagbeola.16@ucl.ac.uk , r.loureiro@ucl.ac.uk} 2 Mark Miodownik is with the department of Mechanical Engineering, University College London, United Kingdom 3 Stephen Hailes is with the department of Computer Science, University College London, United Kingdom along with sensor placement and electrical noise, affect the quality of the signal recorded. Modern techniques in machine learning and deep learning, such as recurrent neural network (RNN) or, in some cases, convolutional neural network (CNN) algorithms, have shown promising results in feature extraction and sequence classification of these types of signals [15,16].…”