Time domain multi-feature extraction and classification of human hand movements using surface EMG
(2017) 4th International Conference on Advanced Computing and Communication Systems, ICACCS 2017- Abstract
Hand movement recognition from electromyogram (EMG) signals is a crucial element for design of electrically controlled limb prostheses and for developing human computer interfaces (HCIs). The study focuses on extraction of significant features from raw EMG signals corresponding to six different grasping hand movements and then using them to classify the respective hand movements using different classifiers. We propose a hybrid multi-feature set comprising of Autoregressive (AR), Root Mean Square (RMS), Zero Crossing (ZC), Slope Sign Change (SSC), Waveform Length (WL) and Mean Absolute Value (MAV) time domain features. We use four different classifiers (k-NN, LDA, QDA and Subspace Discriminant Ensemble) for this experiment. Different set... (More)
Hand movement recognition from electromyogram (EMG) signals is a crucial element for design of electrically controlled limb prostheses and for developing human computer interfaces (HCIs). The study focuses on extraction of significant features from raw EMG signals corresponding to six different grasping hand movements and then using them to classify the respective hand movements using different classifiers. We propose a hybrid multi-feature set comprising of Autoregressive (AR), Root Mean Square (RMS), Zero Crossing (ZC), Slope Sign Change (SSC), Waveform Length (WL) and Mean Absolute Value (MAV) time domain features. We use four different classifiers (k-NN, LDA, QDA and Subspace Discriminant Ensemble) for this experiment. Different set of features yield varying accuracies depending upon the choice of classifiers. Conventional AR feature set provides maximum accuracy of 80.83% with LDA classifier. Similarly, the feature set excluding AR obtains maximum accuracy of 72.5% with k-NN classifier. Our proposed multi-feature set of all six features provides the highest accuracy of 83.33% with Ensemble classifier which is significantly higher than the accuracy values of other feature sets. We validate the results on a large dataset of 600 sEMG signals corresponding to 6 different grasping hand movements.
(Less)
- author
- Bhattacharya, Avik ; Sarkar, Anasua LU and Basak, Piyali
- publishing date
- 2017-08-22
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- keywords
- EMG classification, Ensemble, hand movements, kNN, LDA, QDA
- host publication
- 2017 4th International Conference on Advanced Computing and Communication Systems, ICACCS 2017
- article number
- 8014594
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 4th International Conference on Advanced Computing and Communication Systems, ICACCS 2017
- conference location
- Coimbatore, India
- conference dates
- 2017-01-06 - 2017-01-07
- external identifiers
-
- scopus:85030236872
- ISBN
- 9781509045594
- DOI
- 10.1109/ICACCS.2017.8014594
- language
- English
- LU publication?
- no
- id
- 789d0cf2-663c-41cb-a52b-5fd9ae59f7f1
- date added to LUP
- 2018-09-13 10:14:17
- date last changed
- 2022-04-25 17:11:16
@inproceedings{789d0cf2-663c-41cb-a52b-5fd9ae59f7f1, abstract = {{<p>Hand movement recognition from electromyogram (EMG) signals is a crucial element for design of electrically controlled limb prostheses and for developing human computer interfaces (HCIs). The study focuses on extraction of significant features from raw EMG signals corresponding to six different grasping hand movements and then using them to classify the respective hand movements using different classifiers. We propose a hybrid multi-feature set comprising of Autoregressive (AR), Root Mean Square (RMS), Zero Crossing (ZC), Slope Sign Change (SSC), Waveform Length (WL) and Mean Absolute Value (MAV) time domain features. We use four different classifiers (k-NN, LDA, QDA and Subspace Discriminant Ensemble) for this experiment. Different set of features yield varying accuracies depending upon the choice of classifiers. Conventional AR feature set provides maximum accuracy of 80.83% with LDA classifier. Similarly, the feature set excluding AR obtains maximum accuracy of 72.5% with k-NN classifier. Our proposed multi-feature set of all six features provides the highest accuracy of 83.33% with Ensemble classifier which is significantly higher than the accuracy values of other feature sets. We validate the results on a large dataset of 600 sEMG signals corresponding to 6 different grasping hand movements.</p>}}, author = {{Bhattacharya, Avik and Sarkar, Anasua and Basak, Piyali}}, booktitle = {{2017 4th International Conference on Advanced Computing and Communication Systems, ICACCS 2017}}, isbn = {{9781509045594}}, keywords = {{EMG classification; Ensemble; hand movements; kNN; LDA; QDA}}, language = {{eng}}, month = {{08}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{Time domain multi-feature extraction and classification of human hand movements using surface EMG}}, url = {{http://dx.doi.org/10.1109/ICACCS.2017.8014594}}, doi = {{10.1109/ICACCS.2017.8014594}}, year = {{2017}}, }