{"ID":2871776,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.12253","arxiv_id":"2509.12253","title":"Physics-Informed Neural Networks vs. Physics Models for Non-Invasive Glucose Monitoring: A Comparative Study Under Noise-Stressed Synthetic Conditions","abstract":"Non-invasive glucose monitoring outside controlled settings is dominated by low signal-to-noise ratio (SNR): hardware drift, environmental variation, and physiology suppress the glucose signature in NIR signals. We present a noise-stressed NIR simulator that injects 12-bit ADC quantisation, LED drift, photodiode dark noise, temperature/humidity variation, contact-pressure noise, Fitzpatrick I-VI melanin, and glucose variability to create a low-correlation regime (rho_glucose-NIR = 0.21). Using this platform, we benchmark six methods: Enhanced Beer-Lambert (physics-engineered ridge regression), Original PINN, Optimised PINN, RTE-inspired PINN, Selective RTE PINN, and a shallow DNN. The physics-engineered Beer Lambert model achieves the lowest error (13.6 mg/dL RMSE) with only 56 parameters and 0.01 ms inference, outperforming deeper PINNs and the SDNN baseline under low-SNR conditions. The study reframes the task as noise suppression under weak signal and shows that carefully engineered physics features can outperform higher-capacity models in this regime.","short_abstract":"Non-invasive glucose monitoring outside controlled settings is dominated by low signal-to-noise ratio (SNR): hardware drift, environmental variation, and physiology suppress the glucose signature in NIR signals. We present a noise-stressed NIR simulator that injects 12-bit ADC quantisation, LED drift, photodiode dark n...","url_abs":"https://arxiv.org/abs/2509.12253","url_pdf":"https://arxiv.org/pdf/2509.12253v2","authors":"[\"Riyaadh Gani\"]","published":"2025-09-12T12:18:00Z","proceeding":"eess.IV","tasks":"[\"eess.IV\",\"cs.AI\",\"cs.LG\"]","methods":"[]","has_code":false}