An Event-Based Approach for Discovering Activities of Daily Living by Hidden Markov Models

Smart Home technologies may improve the comfort and the safety of frail people into their home. To achieve this goal, models of Activities of Daily Living (ADL) are often used to detect dangerous situations or behavioral changes in the habits of these persons. In this paper, an approach is proposed to build a model of ADLs, under the form of Hidden Markov Models (HMMs), from a training database of observed events emitted by binary sensors. The main advantage of our approach is that no knowledge of actions really performed during the learning period is required. Finally, we apply our approach to a real case study and we discuss the quality of the results obtained.