Emotion Recognition of Autistic Children Based on EEG Signals

Abstract

With the increasing number of autistic children, the research on emotion recognition for autistic children is becoming more and more important. Emotion recognition refers to identifying a person's emotional state through information such as non-physiological signals or physiological signals. With the rapid development of brain-computer interface technology and human-computer interaction, the research on the use of EEG signals for emotion recognition has received widespread attention from scholars at home and abroad. In this experiment, a combination of video and music was used to induce emotions in children with autism and successfully collected the children's EEG data. In this paper, the collected EEG data is filtered and denoised, and then the emotional characteristics in the EEG signal are extracted, and finally we use the Adaboost algorithm and the random forest algorithm in machine learning to classify and identify the EEG data, and the classification accuracy is 79% and 88%.This experiment verifies the feasibility of using EEG signals to identify emotions in children with autism, and provides a new scheme for emotional intervention and regulation for children with autism in the future.