MyoSync the Art of Synchronysing Actuators to Muscles

Myoelectric prosthetic control has advanced significantly with the application of machine learning, deep learning, and bio-signal processing. This literature survey investigates patient-specific movement regimes, deep learning-based motor intent decoding, and enhanced sEMG-based gesture classification methods for prosthetic limb control improvement. Various approaches, including dynamic time warping (DTW), artificial neural networks (ANNs), and convolutional neural networks (CNNs), have been developed to optimize signal processing and improve classification accuracy. Furthermore, advances in low-cost prosthetic hand development together with force feedback integration are discussed in terms of affordability and user experience. The survey also reviews the role of tactile perception in prosthetics, touching on how mechanical characterization, human experimentation, and computational modeling can enhance sensory feedback. This survey reviews developing trends, existing limitations, and potential future directions on intelligent prosthetic control. Those trends are emphasizing the need for adaptive learning, real-time processing, and user-centered design.