A context-aware sensing strategy with deep reinforcement learning for smart healthcare

• Published in: Pervasive and mobile computing 2022-07, Vol.83, p.101588, Article 101588
• Main Authors: Wang, Lili, Xi, Siyao, Qian, Yuwen, Huang, Cheng
• Format: Article
• Language: English
• Subjects: Context recognition; Deep reinforcement learning; Health sensing; Sensing schedule
• ISSN: 1574-1192; 1873-1589
• DOI: 10.1016/j.pmcj.2022.101588

Health sensing system (HSS), offering a variety of health services, has attracted considerable research attention in the area of smart healthcare. However, continuous sensing inevitably brings dramatic energy consumption of mobile sensing devices. On the other hand, the reduction of sensing time duration causes excessive delay in sensing a user state change and the missing of critical physiologic signal. Thus, the trade-off between energy consumption and delay constitutes a primary challenge in the design of HSS. In this paper, we propose an adaptive sensing strategy to intelligently determine the trigger time for sensing physiological parameters at a HSS. Furthermore, human context recognition (HCR) is adopted to design context-aware sensing strategy, where the health condition, sensing requirements, and dependence on physiological data are considered simultaneously. To devise the sensing strategy, we first generate a dynamic observation model. Next, we propose a sort retention double-DQN based sensing strategy. In comparison to traditional double-DQN, the proposed approach can effectively enhance learning stability and sample efficiency. With SRD-DQN, we can obtain the optimized solution for the schedule of the successive window according to the current state. We implement blood pressure and heart rate monitoring simulations to evaluate the performance of the proposed sensing strategy. Simulation results reveal that the sensing strategy can effectively restrain energy consumption and delay, and SRD-DQN converges faster than traditional DQN. •We have proposed a context-aware sensing strategy based on our sort retention double-DQN for health sensing systems.•A novel observation window model for measuring the state of human health context is derived.•We utilize real datasets on human blood pressure and heart rate to validate the proposed strategy.