Patnaik, LM and Manyam, Ohil K (2008) Epileptic EEG detection using neural networks and post-classification. In: Computer Methods and Programs in Biomedicine, 91 (2). pp. 100-109.
Full text not available from this repository. (Request a copy)Abstract
Electroencephalogram (previous termEEG)next term has established itself as an important means of identifying and analyzing previous termepilepticnext term seizure activity in humans. In most cases, identification of the previous termepileptic EEGnext term signal is done manually by skilled professionals, who are small in number. In this paper, we try to automate the previous termdetectionnext term process. We use wavelet transform for feature extraction and obtain statistical parameters from the decomposed wavelet co-efficients. A feed-forward backpropagating artificial previous termneural networknext term (ANN) is used for the previous termclassification.next term We use genetic algorithm for choosing the training set and also implement a previous termpost-classificationnext term stage using harmonic weights to increase the accuracy. Average specificity of 99.19%, sensitivity of 91.29% and selectivity of 91.14% are obtained.
| Item Type: | Journal Article |
|---|---|
| Publication: | Computer Methods and Programs in Biomedicine |
| Publisher: | Elsevier |
| Additional Information: | Copyright of this article belongs to Elsevier. |
| Keywords: | Electroencephalogram (previous termEEG)next term;Artificial previous termneural networknext term (ANN);Genetic algorithm;Resilient backpropagation;Discrete wavelet transform (DWT). |
| Department/Centre: | Division of Interdisciplinary Sciences > Supercomputer Education & Research Centre |
| Date Deposited: | 19 Aug 2008 |
| Last Modified: | 27 Aug 2008 13:43 |
| URI: | http://eprints.iisc.ac.in/id/eprint/15580 |
Actions (login required)
 |
View Item |
