Automatic social interaction analysis based on wearable devices for people with depression

by Ossama Alshabrawy

16:00 (40 min) in USB 2.022

In the last decade, the utilisation of wearable computing technologies is a relatively new approach within healthcare and well-being application sector. The design and development of wearable sensor systems has gained increasing attention in both the scientific community and practitioners' care routines. The technology have recently advanced, making it easier to monitor and analyse human activities, with applications to, for example, mental care and psychological support.

Psychological illnesses are among the most pressing public healthcare concerns, with at least one in six adults meeting the criteria for a neuropsychological disorder at some time in their life. Beyond that, there is a clear consensus that the current clinical practice does not provide a realistic impression of a patient's condition and thus does not lead to sufficient assessment and care. In response to this issues, this project aims at monitoring and assessing the different aspects of social interactions using wearable devices with focus on naturalistic environments.

This project is based on an existing wearable sensing platform - the wearable acoustic monitor - that is an affordable and commodity-like wrist-worn device that includes tri-axial accelerometer for movement and activity analysis, and microphones for analysis of vocalised social interactions. The on-board memory allows continuous recording (for up to 1 week) and existing records from a large-scale depression study were used to develop algorithms for this project.