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.

翻译：在受控环境之外的非侵入式血糖监测主要面临低信噪比（SNR）的挑战：硬件漂移、环境变化以及生理因素会抑制近红外（NIR）信号中的血糖特征。我们提出了一种噪声压力近红外模拟器，该模拟器注入12位ADC量化、LED漂移、光电二极管暗噪声、温度/湿度变化、接触压力噪声、Fitzpatrick I-VI型皮肤黑色素以及血糖变异性，从而创建一个低相关性体系（血糖-近红外相关系数ρ = 0.21）。利用此平台，我们对六种方法进行了基准测试：增强型比尔-朗伯定律（物理工程化岭回归）、原始PINN、优化PINN、RTE启发式PINN、选择性RTE PINN以及一个浅层DNN。物理工程化的比尔-朗伯模型在低信噪比条件下实现了最低误差（13.6 mg/dL RMSE），仅使用56个参数和0.01 ms的推理时间，性能优于更深的PINN模型和SDNN基线。本研究将任务重新定义为弱信号下的噪声抑制，并表明在此体系下，精心设计的物理特征可以超越更高容量的模型。