Emotion Charting Using Real-time Monitoring of Physiological Signals

Emotions are fundamental to humans. They affect perception and everyday activities such as communication, learning and decision making. Various emotion recognition devices have been developed incorporating facial expressions, body postures and speech recognitions as a means of recognition. The accuracy of most of the existing devices is dependent on the expressiveness of the user and can be fairly manipulated. We proposed a physiological signal based solution to provide reliable emotion classification without possible manipulation and user expressiveness. Electrocardiogram (ECG) and Galvanic Skin Response (GSR) signals are extracted using shimmer sensors and are used for recognition of seven basic human emotions (happy, fear, sad, anger, neutral, disgust and surprise). Classification of emotions is performed using Convolutional Neural Network. Using AlexNet architecture and ECG signals, emotion classification accuracy of 91.5% for AMIGOS dataset and 64.2% for a real-time dataset is achieved. Similarly, the accuracy of 92.7% for AMIGOS dataset and 68% for a real-time dataset is achieved using GSR signals. Through combining both ECG and GSR signals the accuracy of both, AMIGOS and real-time datasets is improved to 93% and 68.5% respectively.