EEG-based Emotion Recognition with Spatial and Functional Brain Mapping of CNS and PNS Signals

TL;DR

This paper introduces a novel EEG-based emotion recognition model that integrates CNS and PNS signals using 3D brain mapping and a 4D-CNN, addressing overfitting and improving accuracy.

Contribution

It proposes a combined physiological signal approach with 3D brain mapping and baseline filtering, enhancing emotion recognition accuracy over existing methods.

Findings

Performance comparable to state-of-the-art algorithms

Effective overfitting mitigation through sigmoid baseline filtering

Successful integration of CNS and PNS signals in emotion recognition

Abstract

Emotion plays a significant role in our daily life. Recognition of emotion is wide-spread in the field of health care and human-computer interaction. Emotion is the result of the coordinated activities of cortical and subcortical neural processes, which correlate to specific physiological responses. However, the existing emotion recognition techniques failed to combine various physiological signals as one integrated feature representation. Meanwhile, many researchers ignored the problem of over-fitting model with high accuracy, which was actually false high accuracy caused by improper pre-processing. In this paper, sigmoid baseline filtering is conducted to solve the over-fitting problem from source. To construct a physiological-based algorithm, a 3D spatial and functional brain mapping is proposed based on human physiological mechanism and international electrode system, which combines the signals of the central and peripheral nervous system together. By combining the baseline filtering, 3D brain mapping, and simple 4D-CNN, a novel emotion recognition model is finally proposed. Experiment results demonstrate that the performance of the proposed model is comparable to the state of art algorithms.