Motion Patterns Recognition Based on Surface Electromyography Data and Machine Learning Classifiers: Preliminary Study

Objective: The aim of this preliminary study was to recognize motion patterns by classifying time series features obtained from electromyography (EMG) data of the upper limb muscles. Methods: In this study we tested six models Machine Learning (ML) classification models (Decision Trees, Support Vector Machines, Linear Discriminant, Quadratic Discriminant, K-Nearest Neighbors, and Efficient Logistic Regression) to classify time series features extracted from processed EMG data that were acquired from eight superficial muscles of two upper limbs over performing given physical activities in two main stages (supination and neutral forearm configuration) in initial and target (isometric) positions. Results: Findings indicate that aiming to classify stages of the upper limb with the highest performance following ML models should be used: 1) K-NN cityblock (F1 equals 0.973/0.992), K-NN seuclidean (0.971/0.996), K-NN minkowski (0.966 /0.992), K-NN co-sine (0.962/0.969) for the left limb; 2) K-NN euclidean (0.970 /0.989), K-NN cityblock (0.966 /0.986), K-NN seuclidean (0.959/0.985), K-NN minkowski (0.957/0.986) for the right limb. Conclusion: Motion patterns tested in this study can be recognized with the highest performance by applying following ML models to classify EMG data: K-NN city-block, K-NN seuclidean, and K-NN minkowski models.