Epileptic Seizure Prediction by Exploiting Signal Transitions Phenomena

Mohammad Parvez, Manoranjan Paul

Research output: Book chapter/Published conference paperConference paper

Abstract

A seizure prediction method is proposed by extractingglobal features using phase correlation between adjacent epochs fordetecting relative changes and local features usingfluctuation/deviation within an epoch for determining fine changes ofdifferent EEG signals. A classifier and a regularization technique areapplied for the reduction of false alarms and improvement of theoverall prediction accuracy. The experiments show that the proposedmethod outperforms the state-of-the-art methods and provides highprediction accuracy (i.e., 97.70%) with low false alarm using EEGsignals in different brain locations from a benchmark data set.
Original languageEnglish
Title of host publicationICBBT 2015
Place of PublicationGreece
PublisherWorld Scientific and Engineering Academy and Society
Pages840-844
Number of pages5
Publication statusPublished - 2015
Event17th International Conference on Bioinformatics and Biological Engineering (ICBBE 2015) - Park Inn Stockholm Hammarby Sjöstad, Stockholm, Sweden
Duration: 13 Jul 201514 Jul 2015
https://waset.org/conference/2015/07/stockholm/ICBBE/home (Conference website)

Conference

Conference17th International Conference on Bioinformatics and Biological Engineering (ICBBE 2015)
CountrySweden
CityStockholm
Period13/07/1514/07/15
OtherThe ICBBE 2015: 17th International Conference on Bioinformatics and Biological Engineering aims to bring together leading academic scientists, researchers and research scholars to exchange and share their experiences and research results about all aspects of Bioinformatics and Biological Engineering. It also provides the premier interdisciplinary forum for researchers, practitioners and educators to present and discuss the most recent innovations, trends, and concerns, practical challenges encountered and the solutions adopted in the field of Bioinformatics and Biological Engineering.
Internet address

Fingerprint Dive into the research topics of 'Epileptic Seizure Prediction by Exploiting Signal Transitions Phenomena'. Together they form a unique fingerprint.

  • Cite this

    Parvez, M., & Paul, M. (2015). Epileptic Seizure Prediction by Exploiting Signal Transitions Phenomena. In ICBBT 2015 (pp. 840-844). World Scientific and Engineering Academy and Society.