PUCK: an automated prompting system for smart environments: toward achieving automated prompting—challenges involved

Abstract

The growth in popularity of smart environments has been quite steep in the last decade and so has the demand for smart health assistance systems. A smart home-based prompting system can enhance these technologies to deliver in-home interventions to users for timely reminders or brief instructions describing the way a task should be done for successful completion. This technology is in high demand given the desire of people who have physical or cognitive limitations to live independently in their homes. In this paper, with the introduction of the “PUCK” prompting system, we take an approach to automate prompting-based interventions without any predefined rule sets or user feedback. Unlike other approaches, we use simple off-the-shelf sensors and learn the timing for prompts based on real data that is collected with volunteer participants in our smart home test bed. The data mining approaches taken to solve this problem come with the challenge of an imbalanced class distribution that occurs naturally in the data. We propose a variant of an existing sampling technique, SMOTE, to deal with the class imbalance problem. To validate the approach, a comparative analysis with Cost Sensitive Learning is performed.

Contextual Bandit Learning for Activity-Aware Things-of-Interest Recommendation in an Assisted Living Environment

“…Various learning models can be adopted at this stage to determine when the user needs a prompt during her activities. For example, Das et al [25] test several classification methodologies on the PUCK dataset, including Support Vector Machines(SVM) [26], Decision Tree [27] and Boosting [28]. In particular, Boosting applies a classification algorithm to re-weight the training data versions sequentially and then extracted a weighted majority vote of the previous sequentially classifiers.…”

Regression tree classification for activity prediction in smart homes

“…al. [4] applied data sampling techniques to address the imbalance between prompt and non-prompt situations and improve prompting performance.…”

Flexible context aware interface for ambient assisted living

“…AALFI offers a person simple prompts as intervention messages to suggest the person carries out a corrective action in response to detected events. In comparison PUCK [41] makes use of simple prompts to guide a person to carry out tasks and does not identify issues that may need to be corrected. AALFI is situational and contextually aware as contextual change events are processed, from this intervention messages are issued and feedback is generated.…”