Application of SVM Based on Optimization of Newton Raphson's Algorithm in Non‐Invasive Blood Glucose Detection

• DOI: 10.1002/ima.70100
• Publication Date: 2025-05-20T12:48:42Z
• Authors: Yingnian Wu; Meiqi Sheng; Ding Wang; Shiwei Gao; Hao Tan

ABSTRACT Traditional invasive blood glucose monitoring methods carry risks such as wound infections and patient discomfort. To address these issues, we propose a non‐invasive method based on facial infrared thermography, aiming to enhance comfort improve the accuracy convenience of detection. data imbalance problem, wavelet‐based sample pairing fusion technique was used thermal imaging dataset. Features extracted by MobileNetV3 network were input into an SVM model for training, Newton–Raphson optimization algorithm applied optimize parameters performance. Compared with standalone model, MobileNetV3‐NRBO‐SVM regression exhibits better performance in terms maximum error root mean square (RMSE). The predicted values our proposed are all within region A Clark grid deviation less than 10%. These results indicate that detection thermography this study achieves clinically acceptable accuracy.