Gesture Recognition by Ensemble Extreme Learning Machine Based on Surface Electromyography Signals

Abstract

In the recent years, gesture recognition based on the surface electromyography (sEMG) signals has been extensively studied. However, the accuracy and stability of gesture recognition through traditional machine learning algorithms are still insufficient to some actual application scenarios. To enhance this situation, this paper proposed a method combining feature selection and ensemble extreme learning machine (EELM) to improve the recognition performance based on sEMG signals. First, the input sEMG signals are preprocessed and 16 features are then extracted from each channel. Next, features that mostly contribute to the gesture recognition are selected from the extracted features using the recursive feature elimination (RFE) algorithm. Then, several independent ELM base classifiers are established using the selected features. Finally, the recognition results are determined by integrating the results obtained by ELM base classifiers using the majority voting method. The Ninapro DB5 dataset containing 52 different hand movements captured from 10 able-bodied subjects was used to evaluate the performance of the proposed method. The results showed that the proposed method could perform the best (overall average accuracy 77.9%) compared with decision tree (DT), ELM, and random forest (RF) methods.

Ensemble Extreme Learning Machine Method for Hemoglobin Estimation Based on PhotoPlethysmoGraphic Signals

“…The ELM algorithm performs well in regression tasks with relatively short training runtimes [ 18 ]. However, the weights from the input layer to the hidden layer are randomly initialized, so different initializations may lead to different regression results, indicating that the training process of ELM is unstable.…”

Unveiling EMG semantics: a prototype-learning approach to generalizable gesture classification

“…We conduct a comprehensive comparison of our proposed gesture classification method with existing CNN-based gesture classification models, including GengNet [42], Cheng et al [43], Wei et al [44], E2CNN [45], Yang et al [46], Zhai et al [25], Ding et al [47], Chen et al [26], Vitale et al [48], Peng et al [49], AtzoriNet [50], CNNLM [51], EVCNN [24], Hu et al [52], Pizzolato et al [53], MSCNet [54], DVMSCNN [55], and MV-CNN [41]. These models, like ours, are CNN-based classifiers that independently classify each frame of EMG data.…”

“…This transformation emphasizes the encapsulated correlations among different channels and features. During kernel processing in the convolution layer, features extracted from the designated region of interest are integrated, consolidating feature and sensor elements GengNet [42] 77.80 ---Cheng et al [43] 82.54 ---Wei et al [44] 85.00 ---E2CNN [45] 91.27 ---Yang et al [46] 93.52 ---Zhai et al [25] -78.71 --Ding et al [47] -78.86 --Chen et al [26] ---69.62 Vitale et al [48] ---74.00 Peng et al [49] ---77.90 AtzoriNet [50] 66.60 75.27 --CNNLM [51] 79.26 78.71 --EVCNN [24] 81.57 66.64 --Hu et al [52] 87.00 82.20 --Pizzolato et al [53] 69…”

An Introduction to Electromyography Signal Processing and Machine Learning for Pattern Recognition: A Brief Overview

“…ELM has been used to develop a model for the estimation of handgrip force [25]. It has also been used to enhance the gesture recognition using sEMG [26].…”

“…; Vol. 3, Issue 1, pp: [24][25][26][27][28][29][30][31][32][33][34][35][36][37]2023 can handle this type of data. ML models can recognize EMG signals that are associated with certain conditions, helping in early detection and treatment [3,4].…”