VLSI implementation for epileptic seizure prediction system based on wavelet and chaos theory

Shao Hang Hung*, Chih Feng Chao, Shu Kai Wang, Bor-Shyh Lin, Chin-Teng Lin

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

9 Scopus citations

Abstract

This paper presents a very large scale integration (VLSI) circuit implementation for Epileptic Seizure Prediction System based combination of wavelet and chaos theory. The system consists with operation units of discrete wavelet transform (DWT), correlation dimension (CD), and correlation coefficient. This work discovered by certain bandwidth of signal extraction with DWT, and the combination with Chaotic features analysis, it can achieve a higher accuracy of epileptic prediction. Furthermore, the correlation coefficient between two correlation dimensions with different embedding dimensions was proposed as a novel feature for epileptic seizure prediction in this study. The proposed system was evaluated with intracranial Electrocorticography (ECoG) recordings from a set of eleven patients with refractory temporal lobe epilepsy (TLE). The accuracy of experiment result for all subjects can achieve 87%, and a false prediction rate is 0.24/h. In average warning time occur about 27 min ahead the ictal.

Original languageEnglish
Title of host publicationTENCON 2010 - 2010 IEEE Region 10 Conference
Pages364-368
Number of pages5
DOIs
StatePublished - 1 Dec 2010
Event2010 IEEE Region 10 Conference, TENCON 2010 - Fukuoka, Japan
Duration: 21 Nov 201024 Nov 2010

Publication series

NameIEEE Region 10 Annual International Conference, Proceedings/TENCON

Conference

Conference2010 IEEE Region 10 Conference, TENCON 2010
CountryJapan
CityFukuoka
Period21/11/1024/11/10

Keywords

  • Correlation Dimension
  • Discrete Wavelet Transform
  • ECoG
  • Seizure Prediction

Fingerprint Dive into the research topics of 'VLSI implementation for epileptic seizure prediction system based on wavelet and chaos theory'. Together they form a unique fingerprint.

Cite this