A grid-based tool for optimal performance monitoring of a glycemic regulator

Abstract

Summary Recent technology breakthroughs towards a fully automated artificial pancreas give rise to the need of new monitoring tools aiming at increasing both reliability and performance of a closed‐loop glycemic regulator. Based on error grid analysis, an insightful monitoring tool is proposed to assess if a given closed‐loop implementation respects its specification of an optimally performing glycemic regulator under uncertainty. The optimal behavior specification is obtained using linearly solvable Markov decision processes, whereby the Bellman optimality equation is made linear through an exponential transformation that allows obtaining the optimal control policy in an explicit form. The specification for the desired glucose dynamics is learned using Gaussian processes for state transitions in an optimally performing artificial pancreas. By means of the proposed grid, the specification is vis‐à‐vis compared with glucose sensor readings so that any significant deviation from the expected closed‐loop performance under abnormal or faulty scenarios can be detected. Copyright © 2015 John Wiley & Sons, Ltd.

Nash game‐based adaptive robust control design optimization for the underactuated mechanical system with fuzzy evidence theory

“…25 Unlike the classical probability theory, the evidence theory defines a set of events by probability values and belief functions, so it is widely used in multi-sensor fusion and reliability analysis. [26][27][28] For uncertainty modeling, the evidence theory is more appropriate than the stochastic approach when the collected data information is scarce and vague. 29 Hence, this article aims to integrate the fuzzy set theory with evidence theory into the fuzzy evidence theory for modeling uncertainty.…”

“…As a generalization of the possibility theory, the evidence theory is built on the belief function, that is, the degrees of belief for one focal member on probability and the basic probability assignment (BPA) assigned to focal elements 25 . Unlike the classical probability theory, the evidence theory defines a set of events by probability values and belief functions, so it is widely used in multi‐sensor fusion and reliability analysis 26‐28 . For uncertainty modeling, the evidence theory is more appropriate than the stochastic approach when the collected data information is scarce and vague 29 .…”

Robust insulin estimation under glycemic variability using Bayesian filtering and Gaussian process models

“…BG levels between 70 and 140 [mg/dl]. To this aim, a number of control and monitoring strategies [2][3][4][5][6] has been proposed to compute optimal exogenous insulin infusion profiles on the basis of plasma glucose and plasma insulin estimation. For BG determination this is achieved by a continuous glucose monitor (CGM) that senses the glucose concentration in the interstitial area, and later on by considering the dynamics between this determination and the actual plasmatic concentration [7].…”