Computational Modeling of Human Interaction Behavior Towards Clinical Translation in Mental Health

Dr. Daniel Bone

Signal Analysis and Interpretation Lab, University of Southern California, USA

Abstract:
Machine intelligence provides a unique, objective and scalable opportunity to understand and model human behavior over time. This will positively impact the way patients are diagnosed, monitored, and treated, not only through population level findings, but by making health care more personalized. Signal processing and machine learning are expanding opportunities to address some of the most pressing health conditions of our time, those affecting the mind. This talk will consider how sensor data is being used to gain insights into and provide support for a variety of psychiatric conditions, discussing specific case studies in autism spectrum disorder (population prevalence of 1 in 68 in United States) and depression. Given the critical decisions these still-in-development computational tools will help make, I will provide an overview of challenges and opportunities ranging from formulating the problem, avoiding pitfalls, and developing fruitful collaborations between all stakeholders.

Research keywords : Behavioral signal processing, Affective computing, Statistical signal processing, Technologies for health applications