M. Avci, Rabia Hamurcu, Ozge Ada Bozbas, Ege Gurman, A. E. Cetin, Ebru Sayilgan
{"title":"Design of Steady-State Visually-Evoked Potential Based Brain-Computer Interface System","authors":"M. Avci, Rabia Hamurcu, Ozge Ada Bozbas, Ege Gurman, A. E. Cetin, Ebru Sayilgan","doi":"10.54856/jiswa.202212214","DOIUrl":null,"url":null,"abstract":"In this study, Steady-State Visual Evoked Potential (SSVEP)-based Brain-Computer Interface (BCI) system, which is popular in many sectors (game, defense, sports, etc.), especially in medicine, was composed. In addition, a robot hand was designed to be integrated into the BCI system, especially to help partially or completely disabled individuals. For this purpose, feature extraction was performed using discrete wavelet transform (Db6) from SSVEP signals recorded from seven different frequencies (6, 6.5, 7, 7.5, 8.2, 9.3, 10 Hz) and four different individuals. Extracted features were classified by support vector machine (SVM) and k-nearest neighbor (k-NN) algorithms. According to the classification results, the highest performance was obtained in the SVM algorithm with an accuracy of 84%.","PeriodicalId":112412,"journal":{"name":"Journal of Intelligent Systems with Applications","volume":"216 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Intelligent Systems with Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.54856/jiswa.202212214","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
In this study, Steady-State Visual Evoked Potential (SSVEP)-based Brain-Computer Interface (BCI) system, which is popular in many sectors (game, defense, sports, etc.), especially in medicine, was composed. In addition, a robot hand was designed to be integrated into the BCI system, especially to help partially or completely disabled individuals. For this purpose, feature extraction was performed using discrete wavelet transform (Db6) from SSVEP signals recorded from seven different frequencies (6, 6.5, 7, 7.5, 8.2, 9.3, 10 Hz) and four different individuals. Extracted features were classified by support vector machine (SVM) and k-nearest neighbor (k-NN) algorithms. According to the classification results, the highest performance was obtained in the SVM algorithm with an accuracy of 84%.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
