A Context-Aware Recall Survey for Data Collection Using Ubiquitous Sensors in the Home

Identifying what people do in the home can both inform ubiquitous computing application design decisions and provide training data to the machine learning algorithms used in their implementation. Ideally, data collection in the home should be non-invasive, automatic and inexpensive, while data labeling should be scalable depending on user abilities. This paper describes an unsupervised technique in which contextual information gathered by ubiquitous sensors is used to help users label a multitude of anonymous activity episodes. This context-aware recall survey is a game-like computer program in which users attempt to correctly guess which activity is happening after seeing a series of symbolic images that represent sensor values generated during the activity. We report a user study of the system, focusing on how well subjects were able to recognize their own activities, the activities of others, and counterfeits that did not correspond to any activity. We present a series of “lessons learned” and describe future work incorporating these findings.