Key result
Lightweight EEG-based classifiers achieve ~97% accuracy in recognizing mixed emotions.
Why the study?
Advanced emotion monitoring and intervention systems require recognizing mixed emotions for human-machine cooperation, but methods using EEG signals were lacking.
Lightweight classifiers including Random Forest, PNN, and GRNN can achieve high accuracy (up to 96.7%) in recognizing mixed emotions from EEG signals.
May support mental state assessment tools; leaves open prospective validation before clinical use.
Advanced emotion monitoring and intervention systems are critical for human-machine cooperation to finish specific tasks in which recognizing mixed emotions is essential. This study is the first to propose intelligent recognition methods of mixed emotions based on EEG signals, thus endowing machines with higher emotional intelligence. We extracted differential entropy (DE), differential asymmetry (DASM), and rational asymmetry (RASM) as features. To better serve the system application and promotion, this study selected three lightweight classifiers, including Random Forest (RF), Probabilistic Neural Networks (PNN), and Generalized Regression Neural Networks (GRNN), all of which achieved good classification performance. The highest classification accuracy is 96.7%. The results of this study can be applied in the fields of mental state assessment, psychological assistance, and clinical psychotherapy.
No takes yet. Share an insight, caveat, or question.
Pei et al. (2023) studied Mixed emotions. Intelligent recognition methods based on EEG signals using lightweight classifiers (RF, PNN, GRNN) was evaluated on Classification accuracy. Intelligent recognition methods of mixed emotions based on EEG signals using lightweight classifiers achieved a highest classification accuracy of 96.7%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: