Media.Player

Wearable Devices and Algorithms for Self-harming Activity Detection

Detailed Technology Description

None

Others

*Abstract

In the United States, there are more than 35,000 reported suicides withapproximately 1,800 of them being psychiatric inpatients. Staff performintermittent or continuous observation in order to prevent suchtragedies, but a study of 98 articles over time showed that20% to 62% of suicides happened while inpatients were onan observation schedule. Reducing the instances of suicides of inpatientsis a problem of critical importance to both patients and healthcare providers. In this disclosure, we introduce SHARE - A Self-Harm Activity Recognition Engine, which attempts to infer self-harming activities from sensing accelerometerdata using smart devices worn on a subject's wrist. Preliminary classification accuracy of80% was achieved using data acquired from 4 subjects performing a seriesof activities (both harmful and not). The results, application, and proposedtechnology platform are discussed in-depth.

*Principal Investigator

Name: Sriram Chellappan, Assistant Professor

Department:

Name: Levi Malott

Department:

Name: Nicholas Hilbert

Department:

Name: Pratool Bharti

Department:

Country/Region

USA