Guide: Towards Understanding Daily Life via Auto- Identification and Statistical Analysis

Abstract

Many recent studies have underscored the applicability to healthcare of a system able to observe and understand day-to-day human activities. The Guide project is aimed at building just such a system. The project combines novel sensing technology, expressive but scalable learners and unsupervised mining of activity models from the web to address the problem. An early prototype, Carnac, has shown considerable promise. This paper provides a high-level overview of the Guide approach, briefly discusses Carnac, and details our expectations of the workshop.