Many emerging pervasive health-care applications require the determination of a variety of context attributes of an individual's activities and medical parameters and her surrounding environment. Context is a high-level representation of an entity's state, which captures activities, relationships, capabilities, etc. In practice, high-level context measures are often difficult to sense from a single data source and must instead be inferred using multiple sensors embedded in the environment. A key challenge in deploying context-driven health-care applications involves energy-efficient determination or inference of high-level context information from low-level sensor data streams. Because this abstraction has the potential to reduce the quality of the context information, it is also necessary to model the tradeoff between the cost of sensor data collection and the quality of the inferred context. This article describes a model of context inference in pervasive computing, the associated research challenges, and the significant practical impact of intelligent use of such context in pervasive health-care environments.
Health Information Technology | Software Engineering
Software and Cyber-Physical Systems
IEEE Systems Man and Cybernetics Magazine
ROY, Nirmalya; JULIEN, Christine; MISRA, Archan; and DAS, Sajal.
Quality and context-aware smart health care: Evaluating the cost-quality dynamics. (2016). IEEE Systems Man and Cybernetics Magazine. 2, (2), 15-25. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/3580
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.