-
[show abstract]
[hide abstract]
ABSTRACT: Empirical linear dynamic models have been identified from ambulatory data from two type 1 diabetes subjects in order to determine approximately how far into the future the models could be expected to make reasonably accurate predictions. For a prediction horizon of 30 minutes, FIT values (related to R<sup>2</sup> values) of the model predictions for validation data were 46% for one subject and 60% for the other subject. These FIT values correspond to root mean square errors of 14 and 24 mg/dL, respectively. Longer prediction horizons resulted in substantially worse predictions for these ambulatory subject data.
American Control Conference, 2008; 07/2008
-
[show abstract]
[hide abstract]
ABSTRACT: In order for an "artificial pancreas" to become a reality for ambulatory use, a practical closed-loop control strategy must be developed and critically evaluated. In this paper, an improved PID control strategy for blood glucose control is proposed and evaluated in silico using a physiologic model of Hovorka et al. The key features of the proposed control strategy are: (i) a switching strategy for initiating PID control after a meal and insulin bolus; (ii) a novel time-varying setpoint trajectory, (iii) noise and derivative filters to reduce sensitivity to sensor noise, and (iv) a systematic controller tuning strategy. Simulation results demonstrate that the proposed control strategy compares favorably to alternatives for realistic conditions that include meal challenges, incorrect carbohydrate meal estimates, changes in insulin sensitivity, and measurement noise
Engineering in Medicine and Biology Society, 2006. EMBS '06. 28th Annual International Conference of the IEEE; 10/2006
-
[show abstract]
[hide abstract]
ABSTRACT: A virtual sensor that estimates product compositions in a middle-vessel batch distillation column has been developed. The sensor is based on a recurrent artificial neural network, and uses information available from secondary measurements (such as temperatures and flow rates). The criteria adopted for selecting the most suitable training data set and the benefits deriving from pre-processing these data by means of principal component analysis are demonstrated by simulation. The effects of sensor location, model initialization, and noisy temperature measurements on the performance of the soft sensor are also investigated. It is shown that the estimated compositions are in good agreement with the actual values.
Chemical Engineering Research and Design 79(6):689-696. · 1.97 Impact Factor
