{"title":"脑电信号中情绪的双向LSTM分类","authors":"Ashley Nand, I. Jebadurai, Ocheni Jeremiah, Getzi Jeba Leelipushpam Paulraj, Jebaveerasingh Jebadurai","doi":"10.1109/ICAISS55157.2022.10010827","DOIUrl":null,"url":null,"abstract":"In the field of neuroscience research, the analysis of EEG signals is crucial for comprehending both human behavior and the workings of the brain. The majority of research is being done to find out how EEG signals are usually used to distinguish between various psychological states and emotions. The proposed study has applied the Bi-LSTM approach for emotion categorization, which significantly raises the accuracy of emotion categorization based on the brain waves obtained from EEG. The results show that the system is reliable as the data has been trained by using a variety of classifiers but with the DEAP dataset, the proposed method obtains a higher and quicker accuracy rate with a training period of about 5ms and an average accuracy rate of 94.12%, and is working to classify the emotion such as valence, arousal, and dominance with single electrode channel with the highest accuracy.","PeriodicalId":243784,"journal":{"name":"2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Bi-Directional LSTM Classification of Emotions in EEG Signals\",\"authors\":\"Ashley Nand, I. Jebadurai, Ocheni Jeremiah, Getzi Jeba Leelipushpam Paulraj, Jebaveerasingh Jebadurai\",\"doi\":\"10.1109/ICAISS55157.2022.10010827\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In the field of neuroscience research, the analysis of EEG signals is crucial for comprehending both human behavior and the workings of the brain. The majority of research is being done to find out how EEG signals are usually used to distinguish between various psychological states and emotions. The proposed study has applied the Bi-LSTM approach for emotion categorization, which significantly raises the accuracy of emotion categorization based on the brain waves obtained from EEG. The results show that the system is reliable as the data has been trained by using a variety of classifiers but with the DEAP dataset, the proposed method obtains a higher and quicker accuracy rate with a training period of about 5ms and an average accuracy rate of 94.12%, and is working to classify the emotion such as valence, arousal, and dominance with single electrode channel with the highest accuracy.\",\"PeriodicalId\":243784,\"journal\":{\"name\":\"2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS)\",\"volume\":\"47 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICAISS55157.2022.10010827\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICAISS55157.2022.10010827","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Bi-Directional LSTM Classification of Emotions in EEG Signals
In the field of neuroscience research, the analysis of EEG signals is crucial for comprehending both human behavior and the workings of the brain. The majority of research is being done to find out how EEG signals are usually used to distinguish between various psychological states and emotions. The proposed study has applied the Bi-LSTM approach for emotion categorization, which significantly raises the accuracy of emotion categorization based on the brain waves obtained from EEG. The results show that the system is reliable as the data has been trained by using a variety of classifiers but with the DEAP dataset, the proposed method obtains a higher and quicker accuracy rate with a training period of about 5ms and an average accuracy rate of 94.12%, and is working to classify the emotion such as valence, arousal, and dominance with single electrode channel with the highest accuracy.