{"title":"应用EEG- fMRI整合检测癫痫发作","authors":"S. V. Raut, D. M. Yadav","doi":"10.1109/CCGE50943.2021.9776356","DOIUrl":null,"url":null,"abstract":"Epilepsy is a chronic nontransmissible brain disease that affects all ages people. Worldwide epilepsy burden is about 50 million making it a common neurological disease (WHO). Generally, Epilepsy is detected using history and EEG analysis. But this method is time and data-consuming as EEG signals appear to be normal after some time in the conversions. This paper proposed a methodology for the detection of Epilepsy by integrating the fMRI and EEG analysis. Features (mean, standard deviation, and power spectral density) are extracted and provided to the SVM classifier. SVM classifies the data with 94.44% of accuracy. The proposed method is found to have more accuracy than SCA, DCM, and DeepID existing methodologies. Further, accuracy can be improved by increasing the number of subjects and features.","PeriodicalId":130452,"journal":{"name":"2021 International Conference on Computing, Communication and Green Engineering (CCGE)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Detection of Epileptic Seizure using EEG- fMRI Integration\",\"authors\":\"S. V. Raut, D. M. Yadav\",\"doi\":\"10.1109/CCGE50943.2021.9776356\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Epilepsy is a chronic nontransmissible brain disease that affects all ages people. Worldwide epilepsy burden is about 50 million making it a common neurological disease (WHO). Generally, Epilepsy is detected using history and EEG analysis. But this method is time and data-consuming as EEG signals appear to be normal after some time in the conversions. This paper proposed a methodology for the detection of Epilepsy by integrating the fMRI and EEG analysis. Features (mean, standard deviation, and power spectral density) are extracted and provided to the SVM classifier. SVM classifies the data with 94.44% of accuracy. The proposed method is found to have more accuracy than SCA, DCM, and DeepID existing methodologies. Further, accuracy can be improved by increasing the number of subjects and features.\",\"PeriodicalId\":130452,\"journal\":{\"name\":\"2021 International Conference on Computing, Communication and Green Engineering (CCGE)\",\"volume\":\"21 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-09-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 International Conference on Computing, Communication and Green Engineering (CCGE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CCGE50943.2021.9776356\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 International Conference on Computing, Communication and Green Engineering (CCGE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CCGE50943.2021.9776356","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Detection of Epileptic Seizure using EEG- fMRI Integration
Epilepsy is a chronic nontransmissible brain disease that affects all ages people. Worldwide epilepsy burden is about 50 million making it a common neurological disease (WHO). Generally, Epilepsy is detected using history and EEG analysis. But this method is time and data-consuming as EEG signals appear to be normal after some time in the conversions. This paper proposed a methodology for the detection of Epilepsy by integrating the fMRI and EEG analysis. Features (mean, standard deviation, and power spectral density) are extracted and provided to the SVM classifier. SVM classifies the data with 94.44% of accuracy. The proposed method is found to have more accuracy than SCA, DCM, and DeepID existing methodologies. Further, accuracy can be improved by increasing the number of subjects and features.