eprintid: 10206105 rev_number: 7 eprint_status: archive userid: 699 dir: disk0/10/20/61/05 datestamp: 2025-03-14 12:12:41 lastmod: 2025-03-14 12:12:41 status_changed: 2025-03-14 12:12:41 type: article metadata_visibility: show sword_depositor: 699 creators_name: Yao, Tianyang creators_name: Wu, Yu creators_name: Jiang, Dai creators_name: Bayford, Richard creators_name: Demosthenous, Andreas title: Forearm Motion and Hand Grasp Prediction Based on Target Muscle Bioimpedance for Human–Machine Interaction ispublished: pub divisions: UCL divisions: B04 divisions: F46 keywords: Bioimpedance, multi-degree of freedom (DoF), human–machine interaction (HMI), forearm motion, hand grasp, robotic control, regression model, long short-term memory (LSTM) note: Copyright © 2025 The Authors. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/. abstract: This paper introduces a novel methodology for simultaneously predicting hand grasp and forearm motion using target muscle bioimpedance measurements and regression models. A total of six channels, formed by nine electrodes, are employed for this multi-degree of freedom (DoF) prediction. Given the time-dependent nature of bioimpedance variation, the long short-term memory (LSTM) regression model is more competent in multi-DoF prediction, compared to linear regression (LR), support vector regression (SVR) and multilayer perceptron (MLP). In intra-subject cross-validation, MLP yields an average coefficient of determination (R2) of 0.9256 for predicting hand grasping angle, while LSTM achieves an average R2 of 0.9483 for predicting random simultaneous forearm two-DoF motion. Operation by amputees without the need to train the regression models is possible by mapping muscle bioimpedance variation directly to the prediction angle, allowing for the approximate estimation of single-DoF motion. The efficacy of these prediction approaches is demonstrated in a real-time object grasping task. date: 2025-02-04 date_type: published publisher: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC official_url: https://doi.org/10.1109/tnsre.2025.3538609 oa_status: green full_text_type: pub language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 2360094 doi: 10.1109/TNSRE.2025.3538609 lyricists_name: Demosthenous, Andreas lyricists_name: Jiang, Dai lyricists_name: Yao, Tianyang lyricists_id: ACDEM08 lyricists_id: DJIAN68 lyricists_id: TYAOX10 actors_name: Yao, Tianyang actors_id: TYAOX10 actors_role: owner funding_acknowledgements: EP/W524335/1 [Engineering and Physical Sciences Research Council (EPSRC)]; EP/T001259/1 [Engineering and Physical Sciences Research Council (EPSRC)]; EP/T001240/1 [Engineering and Physical Sciences Research Council (EPSRC)] full_text_status: public publication: IEEE Transactions on Neural Systems and Rehabilitation Engineering volume: 33 pagerange: 760-769 pages: 10 issn: 1534-4320 citation: Yao, Tianyang; Wu, Yu; Jiang, Dai; Bayford, Richard; Demosthenous, Andreas; (2025) Forearm Motion and Hand Grasp Prediction Based on Target Muscle Bioimpedance for Human–Machine Interaction. IEEE Transactions on Neural Systems and Rehabilitation Engineering , 33 pp. 760-769. 10.1109/TNSRE.2025.3538609 <https://doi.org/10.1109/TNSRE.2025.3538609>. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10206105/1/Forearm_Motion_and_Hand_Grasp_Prediction_Based_on_Target_Muscle_Bioimpedance_for_HumanMachine_Interaction.pdf