TA DIGITAL
Rancang Bangun Sistem Pemantauan Glukosa Darah Non-Invasive Menggunakan Machine Learning Dan Internet Of Things (IoT) = Design and Development of a Non-Invasive Blood Glucose Monitoring System Using Machine Learning and the Internet of Things (IoT)
Non-invasive blood glucose monitoring remains a critical challenge in diabetes management, as conventional invasive techniques are constrained by patient discomfort, infection risk, and recurring operational costs. This study proposes Gluver, an IoT framework for non-invasive blood glucose estimation. Gluver integrates a fingertip optical biosensor to acquire photoplethysmographic (PPG) signals (IR, RED, and heart rate) and transmits them to a cloud database. Six regression algorithms were compared for real-time glucose prediction. The cloud-deployed Random Forest Regression model achieved the best performance with a Mean Absolute Error of 2.832 mg/dL, a Root Mean Squared Error of 3.704 mg/dL, and an ????2 of 0.9596, outperforming k-Nearest Neighbors (????2 = 0.9357). Estimations are displayed via a mobile app and local screen. These results demonstrate the feasibility of combining optical sensing, ensemble learning, and IoT for continuous glucose monitoring, though clinical validation remains necessary prior to medical deployment.
Tidak tersedia versi lain
Karya Umum 
Filsafat 
Agama 
Ilmu-ilmu Sosial 
Bahasa 
Ilmu-ilmu Murni 
Ilmu-ilmu Terapan 
Kesenian, Hiburan, dan Olahraga 
Kesusastraan 
Geografi dan Sejarah