9 January 2019: A project, led by the University of Canberra, will look at teaching computers to better understand the complexity of human emotions.
The five-strong research team, with Professor Roland Goecke from UC’s Faculty of Science and Technology as the lead researcher, have secured a $380,000 grant from the Australian Research Council. The team is investigating multimodal affective sensing techniques that can sense very subtle expressions in human moods and emotions.
Professor Goecke’s research team includes a colleague from the University of Canberra, two researchers from the United States and one from Germany.
The project will address the issue of specificity through novel analysis of very subtle cues in facial and vocal expressions of affect embedded in a multimodal deep learning framework.
This project will tackle the much more difficult problem of developing advanced affective sensing technology to simultaneously handle homogeneous and heterogeneous affect classes, as well as continuous range estimates of affect intensity.
Humans often have a complex overlay of emotions. This project will look at training computers to detect the nuances.
The research will effectively lay the groundwork for the future. In a similar scenario to the benefits of a blood pressure monitor, computers could become a diagnostic aide for physiologists through analysis of emotions when dealing with patients with mental health, Alzheimer’s, anxiety and depression.
The potential contribution of this project to health care is enormous.