Nonlinear classification of emotion from EEG signal based on maximized mutual information
作者：
Highlights：
• Maximally informative dimension from EEG signals is derived for prediction.
• Feature vectors of the dataset are reoriented to the relevant directions.
• No hidden assumption and hence the method is generic in nature.
• Emotional Template is formed based on training set to assess emotion.
• Predicts 82% in 2-class emotion & max. Prediction is 95.87%.
摘要
•Maximally informative dimension from EEG signals is derived for prediction.•Feature vectors of the dataset are reoriented to the relevant directions.•No hidden assumption and hence the method is generic in nature.•Emotional Template is formed based on training set to assess emotion.•Predicts 82% in 2-class emotion & max. Prediction is 95.87%.
论文关键词：Electroencephalography,Emotion recognition,Maximally informative directions,Maximized mutual information
论文评审过程：Received 5 January 2021, Revised 1 July 2021, Accepted 11 July 2021, Available online 28 July 2021, Version of Record 2 August 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.115605
