Emotional brain network decoded by biological spiking neural network

Introduction Emotional disorders are essential manifestations of many neurological and psychiatric diseases. Nowadays, researchers try to explore bi-directional brain-computer interface techniques help the patients. However, related functional brain areas biological markers still unclear, dynamic connection mechanism is also unknown. Methods To find effective regions different emotion recognition intervention, our research focuses on finding emotional EEG networks using spiking neural network algorithm with binary coding. We collected data while human participants watched videos (fear, sadness, happiness, neutrality), analyzed connections between electrodes rhythms emotions. Results The analysis has shown that local high-activation fear sadness mainly in parietal lobe area. high-level happiness prefrontal-temporal lobe-central Furthermore, α frequency band could effectively represent negative emotions, be used as a marker happiness. decoding accuracy three emotions reached 86.36%, 95.18%, 89.09%, respectively, fully reflecting excellent performance self- backpropagation. Discussion introduction self-backpropagation improves model. Different exhibit distinct neuro-oscillatory-based markers. These may provide important hints for technique exploration disease recovery.