DEVELOPMENT OF ANDROID APPLICATION AND MACHINE LEARNING-BASED CONVERSION ALGORITHM OF A NON-INVASIVE BLOOD GLUCOSE MONITORING DEVICE USING NIR-SPECTROSCOPY METHOD

• Main Author: Fajar Ramadhan, Galih
• Format: Final Project
• Language: Indonesia
• Online Access: https://digilib.itb.ac.id/gdl/view/42845
• Institution: Institut Teknologi Bandung

According to International Diabetes Federation, Indonesia ranked 6th in country with highest diabetes patient in the world. Now, the measurement of blood glucose in Indonesia mostly done in invasive manner, which is expensive, painful, and impractical. Even though, according to Indonesia’s Ministry of Health, there are more diabetes patient in rural areas, who have economic shortages and limited access to health care, than people in urban areas. So, a cheap and easy to use non-invasive blood glucose measurement system is needed to solve this problem. One of the current trend of the non-invasive blood glucose monitor development is the using of Near-Infrared Spectroscopy. The device discussed in this paper use a pair of LED and photo diode which transmit and receive light with wavelength of 940 nm as the sensor. Then, the sensor will receive the light intensity and then gives the result of the reading to the smart-phone. In the smart-phone application, the reading result will be converted to blood glucose level using a machine learning model embedded in the apps. The model used in this final project is a Sequential model, a layer-based neural network model provided by Keras. The model builtand trained on top of TensorFlow, and then converted for mobile use with the help of Tensor Flow Lite. The model achieved an acceptable result with Mean Absolute Error (MAE) of 5.855 mg/dL.