To interact naturally and achieve mutual sympathy between humans and machines, emotion recognition is one of themost important function to realize advanced human-computer interaction devices. Due to the high correlation between emotionand involuntary physiological changes, physiological signals area prime candidate for emotion analysis. However, due to the need of a huge amount of training data for a high-quality machine learning model, computational complexity becomes amajor computational bottleneck. To overcome this issue, brain-inspired hyperdimensional (HD) Computing, an energy-efficientand fast learning computational paradigm, has a high potentialto achieve a computational balance between accuracy and the amount of training data. We propose an HD Computing-based Multimodality Emotion Recognition (HDC-MER). HDC-MER maps real-valued features to binary HD vectors using a random nonlinear function, and further encodes them over time, and fuses across different modalities including GSR, ECG, and EEG.
Citation: En-Jui Chang, Abbas Rahimi, Luca Benini, and An-Yeu (Andy) Wu, “Hyperdimensional Computing-based Multimodality Emotion Recognition with Physiological Signals,” in Proc. IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS 2019), March 2019.