Motion Intention Prediction Using Wireless Surface EMG Sensors - REPLACED VERSION

This paper has been replaced by https://doi.org/10.58245/ipsi.tir.2602.02Corr due to a high level of similarity with the Master’s thesis authored by the article’s first author, Jakub L'ach. The article was subsequently revised, reducing the similarity index to below 9%. This paper investigates the prediction of finger motion intention using surface electromyography (sEMG) signals and supervised machine learning models. sEMG sensors provide a noninvasive means of capturing muscle activity, enabling applications in prosthetics, rehabilitation, and human-computer interface. The study explores signal preprocessing techniques, time-frequency domain transformations, and machine learning algorithms, including SVM, Random Forest, and XGBoost. The results highlight the challenges posed by noise and variability in sEMG signals, and suggest strategies for improving prediction accuracy and real-world applicability.