Machine Learning-Based Framework to Predict Finger Movement for Prosthetic Hand

Loss of limb is critical for human life. The prosthetic hand can be an alternate for biological hand up to some extent although it can never mimic the original. This letter presents a machine learning (ML) framework to detect finger movement for the prosthetic hand. The data generated corresponding to different movements of different fingers make the classification problem as multiclass. To address this problem, four ML-based classifiers—K-nearest neighbors, decision tree, random forest, and extreme gradient boosting—have been employed. These classifiers possess inherent property of handling the multiclass classification problem. The employed classifiers have been evaluated for finger movement prediction with respect to precision, recall, F1-score, and accuracy. The experiments show that the XGBoost classifier outperformed the other multiclass classifiers in terms of accuracy.