首页|Data on Machine Learning Discussed by a Researcher at Mugla Sitki Kocman University (Decoding Functional Brain Data for Emotion Recognition: A Machine Learning Approach)
Data on Machine Learning Discussed by a Researcher at Mugla Sitki Kocman University (Decoding Functional Brain Data for Emotion Recognition: A Machine Learning Approach)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Data detailed on artificial intelligen ce have been presented. According to newsreporting originating from Mugla, Turk ey, by NewsRx correspondents, research stated, “The identification of emotions i s an open research area and has a potential leading role in the improvement of s ocio-emotionalskills such as empathy, sensitivity, and emotion recognition in h umans.”The news editors obtained a quote from the research from Mugla Sitki Kocman Univ ersity: “Thecurrent study aimed to use Event Related Potential (ERP) components (N100, N200, P200, P300, earlyLate Positive Potential (LPP), middle LPP, and l ate LPP) of EEG data for the classification of emotionalstates (positive, negat ive, neutral). EEG data were collected from 62 healthy individuals over 18 electrodes. An emotional paradigm with pictures from the International Affective Pict ure System (IAPS) wasused to record the EEG data. A linear Support Vector Machi ne (C=0.1) was used to classify emotions, anda forward feature selection approa ch was used to eliminate irrelevant features. The early LPP component,which was the most discriminative among all ERP components, had the highest classificatio n accuracy(70.16%) for identifying negative and neutral stimuli. T he classification of negative versus neutral stimulihad the best accuracy (79.8 4%) when all ERP components were used as a combined feature set, fo llowedby positive versus negative stimuli (75.00%) and positive ve rsus neutral stimuli (68.55%).”
NETL
NSTL
