Cross entropy-based automatic thresholds setting-up method for sleep staging system

Abstract

Sleep staging is a fundamental step in diagnosis and treatment of sleep disorders. In current sleep staging systems, normally a set of thresholds should be set up to determine the boundaries in differentiating different linguistic or symbolic features. However, as far as we know, there are no fully satisfying automatic method to do this task. Thresholds are mostly set up manually. In this paper, an automatic thresholds setting-up method based on Cross Entropy is proposed. Person-dependent thresholds can be provided automatically by using Cross Entropy and used in personalized sleep staging analysis while considering individual variability. The feasibility of Cross Entropy has also been evaluated, computational results exhibit that the Cross Entropy-based method is an efficient, convenient and applicable stochastic method for automatically setting-up thresholds in sleep staging system. Compared with manual method, average F-Measures are improved more than 10% for all the stages and up-to 74% for stage N3 by using proposed method.

Socio-technical barriers affecting large-scale deployment of AI-enabled wearable medical devices among the ageing population in China

“…WMDs empowered by AI will not just assist elderly people in managing their own health status more effectively (Price-Haywood et al, 2017;Shin and Biocca, 2017), but can also help caregivers and clinicians to select optimal treatments and proactive interventions for individual patients (Tran et al, 2019). In light of this AI wave, our extensive review of the literature identified an increasing number of articles that demonstrate new WMD prototypes containing a front-end IoTbased hardware and a back-end AI application with innovative deep learning algorithms (Chen et al, 2016;Inan et al, 2018;Lin et al, 2019;Jeyaraj and Nadar, 2019). Further to the hardware features discussed above, this second stream of research enables us to better understand potential use cases and scenarios where AI tools and applications can enhance the power of wearable medical devices.…”

Towards a Hybrid Expert System Based on Sleep Event’s Threshold Dependencies for Automated Personalized Sleep Staging by Combining Symbolic Fusion and Differential Evolution Algorithm

“…4. Then, these symbolic features are used in classifying stage W, N1 and R. In previous work [19], [20], [28], [29], values of EMGTh1 and EMGTh2 are the same for each stage without considering thresholds dependencies.…”

“…There exists several typical SSAs, like Tabu Search, Gur Game, Simulated Annealing, Switching Particle Swarm Optimization, Differential Evolution and Cross Entropy, each algorithm has its own pros and cons. Instead of building a mathematical model or a threshold function from scratch, new solutions to solve thresholds setting-up problems have been presented in [28] and [29] by using stochastic search algorithms. The thresholds setting-up problems can be described as a combinatorial optimization problem that aims at finding the optimal thresholds combination among possible thresholds combinations space regarding the objective value of sleep staging systems.…”