Tuesday, April 11, 2017 at 10:00 am in Rice 404
Committee: John A. Stankovic (Advisor), Hongning Wang (Chair), and Kai-Wei Chang; Minor Representatives: John Lach (ECE) and Laura Barnes (SYS).
Title: Towards Micro-Activity Recognition for Monitoring Activity Quality to Generate Notification
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 propose a novel grammar based general purpose framework for modeling activities and micro-activities that retains the details of the activity steps, quantifies activity quality, and identifies the missing/incorrect activity steps. We are naming this framework as QuActive. We are also proposing to build a system based on the framework for detecting micro-activities, recognizing activities, monitoring the activity quality, and generating notifications to users about missing steps and unsafe situations. This proposal provides an overview of QuActive framework, the details of system design, the research challenges and proposed approaches, proposed experiments, related works, and some preliminary results.