Automatic assessment of problem behavior in individuals with developmental disabilities
Proceedings of the 2012 ACM Conference on Ubiquitous Computing
The break-time barometer: an exploratory system forworkplace break-time social awareness
Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing
Proceedings of the 2013 International Symposium on Wearable Computers
Automatic correction of annotation boundaries in activity datasets by class separation maximization
Proceedings of the 2013 ACM conference on Pervasive and ubiquitous computing adjunct publication
Hi-index | 0.00 |
Many with developmental disabilities, especially severe Autism, exhibit what is clinically known as 'problem behaviour', which includes persistent episodes of self-injury, aggression and disruption. Current treatments rely upon manually counting the individual episodes over a period of several weeks, which presents challenges in respect of accuracy, feasibility, and scalability. Situated in the domain of Human Activity Recognition, the goal of this PhD Project is to develop a system that automatically recognizes different types and degrees of problem behaviour on the basis of accelerometer sensor data. The proposed approach is detailed and justified, including how the field of Human Activity Recognition itself can be advanced, together with a clear plan of how the project is to be conducted.