Design of a BR-ABC Algorithm-Based Fuzzy Model for Glucose Detection

• Published in: Augmented human research 2020-12, Vol.5 (1), Article 17
• Main Authors: Gupta, Bhumika, Verma, Agya Ram
• Format: Article
• Language: English
• Subjects: Biomedical Engineering and Bioengineering; Cognitive Psychology; Computational Intelligence; Emerging trends in Computational Intelligence and Complexity; Engineering; Human Physiology; Original Paper; Robotics and Automation; User Interfaces and Human Computer Interaction
• ISSN: 2365-4317; 2365-4325
• DOI: 10.1007/s41133-019-0026-1

This paper presents a modeling approach for defining a measured data set obtained from an optical sensing circuit based on the use of a fuzzy reasoning system. A simple but effective optical sensor is designed for in vitro determination of glucose concentrations in an aqueous solution. The measured data used in this study include analog voltages that reflect the absorbance values of three wavelengths measured in different concentrations of glucose from an RGB light-emitting diode (LED). The parameters of the fuzzy models are optimized using the bounded-range artificial bee colony (BR-ABC) algorithm to achieve the desired model performance. The results indicate that the optimized fuzzy model demonstrates high performance quality. The minimum mean square error (MSE) obtained from the singleton fuzzy model with the BR-ABC algorithm is 0.00014, which is better than the reported MSE value achieved with the Takagi–Sugeno fuzzy model.