Automated emotion classification in the early stages of cortical processing: An MEG study

作者：

Highlights：

• The automated classification of human emotions is feasible in very early time-intervals within 100–300 ms post-stimulus.

• MEG is well suited to automatically classify human emotions very early with high performances.

• This study suggests that the human brain might differentiate emotional versus neutral stimuli within 100–150 ms.

• Our study is the first to automatically classify human emotions very early, at least 700 ms earlier than in other studies.

摘要

•The automated classification of human emotions is feasible in very early time-intervals within 100–300 ms post-stimulus.•MEG is well suited to automatically classify human emotions very early with high performances.•This study suggests that the human brain might differentiate emotional versus neutral stimuli within 100–150 ms.•Our study is the first to automatically classify human emotions very early, at least 700 ms earlier than in other studies.

论文关键词：Classification,Emotion,Genetic algorithm,Linear discriminant analysis,MEG

论文评审过程：Received 16 July 2019, Revised 16 December 2020, Accepted 29 March 2021, Available online 31 March 2021, Version of Record 10 April 2021.

论文官网地址：https://doi.org/10.1016/j.artmed.2021.102063