Human-Horse Interaction Multimodal system for Affective Detection
Affect recognition is the task of detecting the emotional state of humans under various conditions. The development of efficient and robust algorithms for automated emotion (affect) recognition is a major challenge and may have great implications on the way users interact with computers, as well as on fields like medicine, education, multimedia, etc. In this work, we aim to study the potential use of affect recognition techniques for assisting the interaction between humans and horses. We propose a multimodal portable system for physiological signal acquisition such as the electrocardiogram (ECG), electromyography (EMG), and electroencephalogram (EEG). The proposed system was used to acquire signals while users were interacting with horses. The captured signals will then be used in order to quantifiably evaluate human and equine interaction by mapping the signals to the emotional state of the subjects using machine learning techniques.