QuActive: A Quality of Activities Monitoring and Notification System

In order to notify users about potentially unsafe situations and to track mistakes or efficiency performing activities, it is important to monitor the quality of performing an activity and identify the missing/wrong steps. However, the state-of-the-art activity recognition frameworks ignore such details and impose constraints on sensor values, the types of detected activities (no parallel/interleaved/joint activities), or the number of users, which reduce the robustness of the system in the real world settings. Therefore, we present QuActive, a grammar based general purpose framework for modeling activities and micro-activities that retains the details of the activity steps, quantifies activity quality, and notifies users about missing steps and unsafe situations. In order to show the versatility of QuActive, we evaluate the framework on three different public datasets that have interleaved activities, parallel and co-operative activities, and activities of cognitively declined patients with quality information labeled. In all cases, QuActive outperforms the state-of-the-art techniques applied on these data sets. In addition, we have deployed the system in a real home and collected data in a semi-controlled setting to evaluate the performance of the system in real settings. The results show that QuActive recognizes more than 90% of the defined micro-activities and the grammar detects almost all the defined activities from the recognized micro-activities.