Eeg-based emotion recognition with brain network using independent components analysis and granger causality

Chen Dongwei, Wu Fang, Wang Zhen, Li Haifang, Chen Junjie
2013 2013 International Conference on Computer Medical Applications (ICCMA)  
With the continuous development of brain network technology, it has become a hot area of neuroscience and information technology to research the human emotion changes, cognitive status and psychiatric disorders by means of brain network. In recent years, any smart device can be used as a terminal sensor in the Internet of Things for information interaction. It will be the new research aspect for brain-computer Interface (BCI) to regard the human brain (the most intelligent "device") as a
more » ... l sensor in the Internet of Things and to construct a network based on the human brains (we name it as Internet of Brains). In this paper, a causal connectivity brain network (CCBN) was firstly constructed based on multivariate autoregressive (MVAR) modeling, independent component analysis (ICA) and partial directed coherence (PDC). Then the different features of three emotional states (positive, neutral, negative) were respectively extracted by graph theoretical analysis based on the CCBN estimated by granger causality analysis. The relationship between characteristics of EEG pattern and emotional states was disclosed. Result suggested that a classification rate of about 88.75% was achieved in the human subject studied, thus it is feasible to discriminate emotional states with causal connectivity brain network and is a promising non-invasive approach for studying the model of affective computing. Furthermore the model of wearable affective computing was estimated based on above relationship with the portable EEG acquisition device, and prototype system of Internet of Brains would be achieved for BCI.
doi:10.1109/iccma.2013.6506157 fatcat:r56phaswozcuxn4ftqav2igdou