Classification of electroencephalogram signals using wavelet transform and particle swarm optimization
The electroencephalogram (EEG) is a signal measuring activities of the brain. Therefore, it contains useful information for diagnosis of epilepsy. However, it is a very time consuming and costly task to handle these subtle details by a human observer. In this paper, particle swarm optimization (PSO)...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Published: |
Springer Verlag
2014
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/52122/ https://link.springer.com/chapter/10.1007%2F978-3-319-11897-0_41 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The electroencephalogram (EEG) is a signal measuring activities of the brain. Therefore, it contains useful information for diagnosis of epilepsy. However, it is a very time consuming and costly task to handle these subtle details by a human observer. In this paper, particle swarm optimization (PSO) was proposed to automate the process of seizure detection in EEG signals. Initially, the EEG signals have been analysed using discrete wavelet transform (DWT) for features extraction. Then, the PSO algorithm has been trained to recognize the epileptic signals in EEG data. The results demonstrate the effectiveness of the proposed method in terms of classification accuracy and stability. A comparison with other methods in the literature confirms the superiority of the PSO. |
|---|