Non-invasive Glucose Monitoring System Utilizing Near-Infrared Technology

Abstract

Regular monitoring of glucose concentration is essential and urgency, especially diabetics. However, those methods which involve finger puncturing are invasive, expensive as well as painful. Also, there are risks of infectious diseases using these techniques due to the contact of the needle on human skin. This paper proposed a non-invasive glucose monitoring system utilizing the near-infrared (NIR) light to measure the glucose concentration in the human blood. The designed system uses a 980 nm-wavelength NIR LED transmitting through d-glucose phantom samples, a photo-sensor for analyzing the transmitting optical parameters, a filter & an amplifier circuit, and a Nano Arduino microcontroller. For calculating the values of glucose concentration, the R programming with the methodology of the artificial neural network (ANN) was applied. This type of methodology is considered as one of the most useful technique in the world of data analysis and because it is adaptive, learns from the provided information and optimizes for better prediction outcomes. The ANN is used to predict the correlation equation between collected voltage and glucose concentration. The obtained glucose level is demonstrated directly on the system’s screen or further sent to the user’s mobile phone. The result obtained shows a correlation between the transmittance and the concentration of d-glucose solution. The correlation parameter of the technique is R² = 0.9957. Despite having the acceptable results, there are still some improvements that could be carried out for more accurate measurement (angle of the LED, a procedure of filtering and amplifying, usage of an optical instrument…). For further investigation and development, it is predicted that the result can be more accurate, precise and sensitivity as much as possible.