English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Epilepsy is a neurological disorder caused due to abnormal excessive activity of neurons in brain. In this paper, epileptic seizure is detected by dynamics undergone by the attractors in EEG signals of patients/subjects. EEG signal is represented in high dimensional phase space. The complexity in high dimension is reduced by principal component analysis (PCA). Then the Poincaré section is used to obtain intersection points from the lower dimensional PCA output. A new 1D sequence is constructed from intersection points. Non-linear features are extracted from the constructed 1D sequence. Two layers of classifier are used. The output of first layer SVM classifier is given as the input to the second layer Naives Bayes classifier. The performance of the two layer classifier is better than that of the single layer classifier. The result is displayed as seizure or non-seizure for every 1 s, in order to accurately measure the seizure duration and the effectiveness of the seizure. The database used is CHB-MIT database having EEG signals for 23 subjects of different age groups. The proposed method is verified using the 23 subjects of CHB-MIT database and obtained the performance measures as 96.77% of accuracy, 95.011% of sensitivity and 97.97% of selectivity which are much better than available results in the literature.

RETRACTED ARTICLE: Epileptic seizure detection by analyzing high dimensional phase space via Poincaré section