Sharif University of Technology Scientia Iranica 1026-3098 Articles in Press 2025 02 04 Deep LSTM Neural Networks in Kinematic Estimation of the Finger Interphalangeal Joint’s Angles Using Surface Electromyogram Signals 23808 10.24200/sci.2025.65319.9419 EN Masoud Saheb Jameyan Biomedical Eng. Department, Amirkabir University of Tech, 424 Hafez Ave., Tehran, Iran. IRAN Mohammad Ali Ahmadi-Pajouh biomedical engineering, Amirkabir university of technology,Tehran, Iran Mohammad Hassan Moradi Department of Biomedical Engineering, Amirkabir University of Technology Journal Article 2024 09 13 Objectives: In rehabilitation, hand robotics, and kinesiology, a crucial challenge is establishing a connection between surface electromyogram (sEMG) signals and the kinematics of joints and upper limbs.<br />Methods: The present research introduces a deep recurrent neural network regressor that uses LSTM (Long Short Term Memory) and GRU (Gated Recurrent Unit) cells, leveraging sEMG signals to estimate finger joint angles. This investigation used the DB2 series of the Ninapro dataset. <br />Results: Remarkably, many joint angles can be estimated with up to 97% accuracy when based on the correlation coefficient criterion. This indicates a strong positive correlation between the estimated values and the actual values of these joints. However, it is significant to note that there is a trade-off between accuracy, learning time, and the number of parameters used, which varies based on the type of cells employed in the network. <br />Conclusions: Using deep LSTM neural networks, it is possible to estimate the interphalangeal joint angles of the fingers with an accuracy of 97%. LSTM cells offer more precise predictions but require more learning time and parameters than GRU cells. The study also explores the significance of efficient muscles in executing movements, potentially influencing the varying estimation accuracy among different joints. https://scientiairanica.sharif.edu/article_23808_40851036bdb555e33e7086a8674aa781.pdf