A Bayesian Network and Rule-Base Approach Towards Activity Inference

We describe an activity recognition system capable of monitoring user activities in home environments. Activities are monitored by processing information from various sensors embedded in the environment that provide information pertinent to user's actions. We utilise the concept of self-organising object networks to gather and hierarchically process information related to user actions in a distributed manner. This information is then fed to the decision module which matches this information in the user's activity map in order to deduce user's activity. The decision module comprises a Bayesian network coupled with a rule-based engine which is used to provide accurate activity inference process.