Emotion recognition via affective EEG signals: State of the art

Abstract

With advancements in brain–computer interface technology, research on emotion recognition based on electroencephalogram (EEG) signals has gained significant attention. This review systematically explores signal acquisition, feature extraction, classification methods, and applications related to emotion recognition. We begin by reviewing the acquisition of affective EEG signals, including emotion models, emotion induction methods, signal acquisition techniques, and popular public datasets. Second, we provide a detailed discussion of feature extraction methods for emotional EEG signals, including time-domain, frequency-domain, time–frequency domain, and spatial domain features, as well as feature fusion techniques. The classification methods section highlights recent developments in machine learning, deep learning, and multimodal learning, exploring their applications in emotion recognition tasks. Additionally, we assess practical applications of emotion recognition technologies in areas such as cognitive workload, fatigue estimation, neuropsychiatric condition assessment, and affective care. Finally, the article summarizes the major challenges currently faced and the future development opportunities. By synthesizing existing research, we provide valuable insights and guidance for further studies on EEG-based emotion recognition and its applications in various fields such as education, transportation, and healthcare.