Emotion Recognition Based on AMIGOS and DEAP dataset
Access IC Design Lab supervised by Prof. An-Yeu Wu
Access IC Design Lab
supervised by Prof. An-Yeu Wu
Develope an emotion recognition framework with signal processing techniques.
Figure 1. Overall view of the processing flow.
Due to the growing importance of the Human Computer Interface system, understanding human’s emotion states has become a consequential ability for the computer. In this research, we aim to improve the performance of emotion recognition by conducting the complexity analysis of Electrodermal Activity based on AMIGOS and DEAP dataset. The overall processing flow is shown above on Figure 1.
Figure 2. Electrodermal activity decomposition.
EDA signal consists of two components: a tonic (skin conductance level, SCL) represents a slowly varying baseline conductivity; a phasic (skin conductance response, SCR) shows a fast varying reaction to specific arousing stimulus and can be visible as bursts or peaks. We aimed to analyze differnt decomposition techniques to improve our recognition performance. For more information, please refer to our slide and our code is also publically available on GitHub.