Window length insensitive real-time EMG hand gesture classification using entropy calculated from globally parsed histograms
Open Access
- 14 February 2023
- journal article
- research article
- Published by SAGE Publications in Measurement and Control
- Vol. 56 (7-8) , 1278-1291
Abstract
Electromyography (EMG) signal classification is vital to diagnose musculoskeletal abnormalities and control devices by motion intention detection. Machine learning assists both areas by classifying conditions or motion intentions. This paper proposes a novel window length insensitive EMG classification method utilizing the Entropy feature. The main goal of this study is to show that entropy can be used as the only feature for fast real-time classification of EMG signals of hand gestures. The main goal of this study is to show that entropy can be used as the only feature for fast real-time classification of EMG signals of hand gestures. Additionally, the entropy feature can classify feature vectors of different sliding window lengths without including them in the training data. Many kinds of entropy feature succeeded in electroencephalography (EEG) and electrocardiography (ECG) classification research. However, to the best of our knowledge, the Entropy Feature proposed by Shannon stays untested for EMG classification to this day. All the machine learning models are tested on datasets NinaPro DB5 and the newly collected SingleMyo. As an initial analysis to test the entropy feature, classic Machine Learning (ML) models are trained on the NinaPro DB5 dataset. This stage showed that except for the K Nearest Neighbor (kNN) with high inference time, Support Vector Machines (SVM) gave the best validation accuracy. Later, SVM models trained with feature vectors created by 1 s (200 samples) sliding windows are tested on feature vectors created by 250 ms (50 samples) to 1500 ms (300 samples) sliding windows. This experiment resulted in slight accuracy differences through changing window length, indicating that the Entropy feature is insensitive to this parameter. Lastly, Locally Parsed Histogram (LPH), typical in standard entropy functions, makes learning hard for ML methods. Globally Parsed Histogram (GPH) was proposed, and classification accuracy increased from 60.35% to 89.06% while window length insensitivity is preserved. This study shows that Shannon’s entropy is a compelling feature with low window length sensitivity for EMG hand gesture classification. The effect of the GPH approach against an easy-to-make mistake LPH is shown. A real-time classification algorithm for the entropy features is tested on the newly created SingleMyo dataset.Keywords
This publication has 40 references indexed in Scilit:
- EMPress2016
- Proportional EMG control of ankle plantar flexion in a powered transtibial prosthesis2013
- Building the Ninapro database: A resource for the biorobotics community2012
- Log Energy Entropy-Based EEG Classification with Multilayer Neural Networks in SeizureAnnals of Biomedical Engineering, 2009
- Clustering Algorithms II: Hierarchical Algorithms2009
- Effect of elbow joint angle on force–EMG relationships in human elbow flexor and extensor musclesJournal of Electromyography and Kinesiology, 2008
- Support Vector Machine-Based Classification Scheme for Myoelectric Control Applied to Upper LimbIEEE Transactions on Biomedical Engineering, 2008
- Characterization of Surface EMG Signal Based on Fuzzy EntropyIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2007
- A Mathematical Theory of CommunicationBell System Technical Journal, 1948
- Ueber verschiedene für die Anwendung bequeme Formen der Hauptgleichungen der mechanischen WärmetheorieAnnalen der Physik, 1865