Class discriminator-based EMG classification approach for detection of neuromuscular diseases using discriminator-dependent decision rule (D3R) approach
(2019) 1st International Symposium on Signal and Image Processing, ISSIP 2017 In Advances in Intelligent Systems and Computing 727. p.49-56- Abstract
Classification of EMG signals is essential for diagnosis of motor neuron diseases like neuropathy and myopathy. Although a number of strategies have been implemented for classification, none of them are efficient enough to be implemented in clinical environment. In the present study, we use ensemble approach of support vector machines for classification of three classes (normal, myopathic and neuropathic) of clinical electromyogram (EMG). Our proposed approach uses time and time–frequency features extracted from EMG signals. By employing two types of feature set for same class discriminators, we are able to select the best feature set-discriminator pairs. The decision made by each selected classifier is used to generate the final class... (More)
Classification of EMG signals is essential for diagnosis of motor neuron diseases like neuropathy and myopathy. Although a number of strategies have been implemented for classification, none of them are efficient enough to be implemented in clinical environment. In the present study, we use ensemble approach of support vector machines for classification of three classes (normal, myopathic and neuropathic) of clinical electromyogram (EMG). Our proposed approach uses time and time–frequency features extracted from EMG signals. By employing two types of feature set for same class discriminators, we are able to select the best feature set-discriminator pairs. The decision made by each selected classifier is used to generate the final class for an input EMG signal through majority voting. Our proposed method yields higher accuracy of 94.67% over 89.67% for multiclass SVM classifier.
(Less)
- author
- Bhattacharya, Avik ; Pahari, Purbanka ; Basak, Piyali and Sarkar, Anasua LU
- publishing date
- 2019
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Discriminator-dependent decision rule, Electromyogram, Ensemble framework, MUAP classification
- host publication
- Recent Trends in Signal and Image Processing
- series title
- Advances in Intelligent Systems and Computing
- volume
- 727
- pages
- 8 pages
- publisher
- Springer
- conference name
- 1st International Symposium on Signal and Image Processing, ISSIP 2017
- conference location
- Kolkata, India
- conference dates
- 2017-11-01 - 2017-11-02
- external identifiers
-
- scopus:85047400089
- ISSN
- 2194-5357
- ISBN
- 978-981-10-8863-6
- 9789811088629
- DOI
- 10.1007/978-981-10-8863-6_6
- language
- English
- LU publication?
- no
- id
- 864b16ed-45a0-475a-90a1-09035ffd9f84
- date added to LUP
- 2018-09-13 10:13:48
- date last changed
- 2024-09-17 02:26:37
@inproceedings{864b16ed-45a0-475a-90a1-09035ffd9f84, abstract = {{<p>Classification of EMG signals is essential for diagnosis of motor neuron diseases like neuropathy and myopathy. Although a number of strategies have been implemented for classification, none of them are efficient enough to be implemented in clinical environment. In the present study, we use ensemble approach of support vector machines for classification of three classes (normal, myopathic and neuropathic) of clinical electromyogram (EMG). Our proposed approach uses time and time–frequency features extracted from EMG signals. By employing two types of feature set for same class discriminators, we are able to select the best feature set-discriminator pairs. The decision made by each selected classifier is used to generate the final class for an input EMG signal through majority voting. Our proposed method yields higher accuracy of 94.67% over 89.67% for multiclass SVM classifier.</p>}}, author = {{Bhattacharya, Avik and Pahari, Purbanka and Basak, Piyali and Sarkar, Anasua}}, booktitle = {{Recent Trends in Signal and Image Processing}}, isbn = {{978-981-10-8863-6}}, issn = {{2194-5357}}, keywords = {{Discriminator-dependent decision rule; Electromyogram; Ensemble framework; MUAP classification}}, language = {{eng}}, pages = {{49--56}}, publisher = {{Springer}}, series = {{Advances in Intelligent Systems and Computing}}, title = {{Class discriminator-based EMG classification approach for detection of neuromuscular diseases using discriminator-dependent decision rule (D3R) approach}}, url = {{http://dx.doi.org/10.1007/978-981-10-8863-6_6}}, doi = {{10.1007/978-981-10-8863-6_6}}, volume = {{727}}, year = {{2019}}, }