Cross-validation of a classification method applied in a database of sEMG contractions collected in a body interaction videogame

Abstract

paper presents the evaluation and cross-validation of four pattern recognition classifiers, with the objective of finding the best one for classify surface electromyography (sEMG) signals combined with information extracted from videogame’s variables. The classifiers, a linear classifier, a quadratic classifier, a k-nearest-neighbor classifier, and a support vector machine, were computed on a data matrix created with the recorder signal collected from 12 subjects in a body interaction videogame that used a sEMG as a control strategy for upper limbs virtual rehabilitation. Although the classifiers of sEMG signal had a widespread study, there is not evidence of how to deal with the information of sEMG signals combined with game variables. The classification task is related with discern each subject as “good player” or “bad player”, looking to following the performance of the videogame’s users through the game sessions. A cross-validation of 10 iterations was computed, PCA and Relieff were used as feature extraction and selection methods. The evaluation was developed using the percentage of accuracy, defined as the well-predicted points. The best accuracy in the classification task was found using an SVM with a misclassification parameter of 400 and an RBF kernel regularization parameter of 60. Base on this result, the SVMs showed to be the appropriate classifier to be used on sEMG signal combined with videogame variables and should be implemented to follow the user’s performance.

Virtual/Augmented Reality for Rehabilitation Applications Using Electromyography as Control/Biofeedback: Systematic Literature Review

“…A total of 67.5% (27) of the articles included abled-bodied healthy subjects in their trials. All the articles (40) used visual feedback through the VR or AR interfaces, but a few used a second type of feedback, such as 2 articles that included fatigue and closed-loop feedback to regulate intensity [51,52], while another 2 papers used audio feedback [47,53], 2 relied on tactile feedback [53][54][55], 1 had haptic feedback, and 1 asked the subject to think of the movement (to be detected through electroencephalography (EEG)) as well as to perform it [56]. Just 3 articles mentioned exoskeletons for movement assistance triggered by sEMG signals [56][57][58], and 1 article used functional electrical stimulation (FES) for movement assistance [59]; all 4 of them belong to neurorehabilitation applications.…”

“…Support vector machine is used in 4 (10%) articles, only 3 of them report performance (with 96.3%, 95%, and 99.5% (healthy subjects)/94.75% (stroke patients), respectively) [9,51,52,55]. Another 4 (10%) articles use neural networks, and 1 reports a 97.5% performance using a convolutional neural network [63], while another 1 uses a deep learning model [73], and 1 more a probabilistic neural network [64].…”