EEG Subband Analysis using Approximate Entropy for the Detection of Epilepsy
Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2014, Vol 16, Issue 5
Abstract
Abstract: Epilepsy is a neurological disorder which affects the nervous system. Epileptic seizures are due tosudden hyperactivity in certain parts of the brain. Electroencephalogram (EEG) is the commonly used modality for the detection of epilepsy. Automatic seizure detection helps in diagnosis and monitoring of epilepsy especially during long term recordings of EEG. This paper presents non linear analysis of EEG for the detection of epilepsy using approximate entropy (ApEn). The proposed method involves ApEn measured from EEG subbands applied as features to an artificial neural network (ANN) classifier. The ApEn measured from delta, theta, alpha, beta and gamma subbands of normal EEG, ictal and inter ictal EEGs are used as features. In the present work detection of epilepsy is considered as a two class problem. In the first case the classification is done between normal and ictal EEGs and in the second case, classification is done between normal and interictal EEGs. For both cases artificial neural networks with back propagation training are used as classifiers. The classification accuracy of 100% is obtained for normal and ictal groups and that of 98.9% is obtained for normal and inters ictal EEGs.
Authors and Affiliations
G. R. Kiranmayi , V. Udayashankara
Keywords
Related Articles
- EP ID EP142355
- DOI -
- Views 105
- Downloads 0
Efficient Information Retrieval System with Higher Priority for User Preference
Abstract: A search engine is a software system or a tool that is designed to search for information. Web search engines return lists of web pages ranked by the page’s relevance to the user query and by number of ti...
A Novel Approach for Semi Supervised Document Clustering with Constraint Score based Feature Supervision
Abstract: Text document clustering provides an effective technique to manage a huge amount of retrieval outcome by grouping documents in a small number of meaningful classes. In unsupervised clustering method the unlabel...
Hierarchical Dirichlet Process for Dual Sentiment Analysis with Two Sides of One Review
Abstract: Sentiment categorization is a fundamental process in sentiment examination, by means of it’s intended to categorize the sentiment into either positive or negative for given text. The wide-ranging perform in sen...
Analysis of C4.5 and K-Nearest Neighbor (KNN) Method on Algorithm of Clustering For Deciding Mainstay Area
Development as a sustainable activity needs a good plan, so the programs can be effective and have a clear objective. Therefore, a model to help the analysis is significantly needed in determining the priority area...
Text Classification by Augmenting Bag of Words (BOW) Representation with Co-occurrence Feature
Text classification is the task of assigning predefined categories to free-text documents based on their content. Traditional approaches used unigram based models for text classification. Unigram based models suc...