{"title":"Epileptic seizure detection from EEG signals by using wavelet and Hilbert transform","authors":"Hasan Polat, M. S. Ozerdem","doi":"10.1109/MEMSTECH.2016.7507522","DOIUrl":null,"url":null,"abstract":"In this study, EEG signals recorded from healthy individuals and EEG signals recorded from epileptic patients during epileptic seizures were classified. In the classification process, the Hilbert and wavelet transform were applied separately for the extraction of features from the EEG signals. The same statistical parameters were used in order to reduce the size of the feature vectors obtained via both approaches. K-nearest neighborhood (kNN) was used as classification algorithm. The obtained feature vector based on wavelet and Hilbert transform were classified separately via the kNN algorithm.","PeriodicalId":102420,"journal":{"name":"2016 XII International Conference on Perspective Technologies and Methods in MEMS Design (MEMSTECH)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 XII International Conference on Perspective Technologies and Methods in MEMS Design (MEMSTECH)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/MEMSTECH.2016.7507522","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 8
Abstract
In this study, EEG signals recorded from healthy individuals and EEG signals recorded from epileptic patients during epileptic seizures were classified. In the classification process, the Hilbert and wavelet transform were applied separately for the extraction of features from the EEG signals. The same statistical parameters were used in order to reduce the size of the feature vectors obtained via both approaches. K-nearest neighborhood (kNN) was used as classification algorithm. The obtained feature vector based on wavelet and Hilbert transform were classified separately via the kNN algorithm.