期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2016
卷号：5
期号：9
页码：16347
DOI：10.15680/IJIRSET.2016.0509111
出版社：S&S Publications
摘要：Seizure is a chronic neurological disorder. Seizures are the result of transient and unexpected electricaldisturbances in the brain. Seizure is more likely to occur in young children or people over the age of 65 years; however,it can occur at any age. The detection of seizure is possible by analyzing EEG (electroencephalogram) signals. Theelectroencephalogram (EEG) signal is very important in the diagnosis of seizure. Long-term EEG recordings of aseizure patient contain a huge amount of EEG data. The detection of seizure activity is, therefore, a very demandingprocess that requires a detailed analysis of the entire EEG data, usually performed by an expert. This paper describes anautomated classification of EEG signals for the detection of seizures using wavelet transform and support vectormachines. The decision making process consists of three main stages: (a) filtering operation by FIR filter, (b) featureextraction based on discrete wavelet transform (DWT) and (c) classification by support vector machines (SVM)classifiers. The proposed methodology is applied on EEG data sets that belong to two subject groups: a) healthysubjects and b) seizure subjects. Based on the data sets the boundaries of all the features are identified for the properdetection of the test signal. After processing all the data sets, the test signal is given to the system. Decision is made bycomparing the features of the test signal with the maximum and minimum values of all the features of data sets. TheEEG feature extraction and seizure detection system is verified by Verilog in ISim simulator and implemented onXilinx Spartan6.
