Signal fragmentation based feature vector generation in a model agnostic framework with application to glucose quantification using absorption spectroscopy

This paper proposes feature vector generation based on signal fragmentation equipped with a model interpretation module to enhance glucose quantification from absorption spectroscopy signals. For this purpose, near-infrared (NIR) and mid-infrared (MIR) spectra collected from experimental samples of varying glucose concentrations are scrutinised. Initially, a given spectrum is optimally dissected into several fragments. A base-learner then studies the obtained fragments individually to estimate the reference glucose concentration from each fragment. Subsequently, the resultant estimates from all fragments are stacked, forming a feature vector for the original spectrum. Afterwards, a meta-learner studies the generated feature vector to yield a final estimation of the reference glucose concentration pertaining to the entire original spectrum. The reliability of the proposed approach is reviewed under a set of circumstances encompassing modelling upon NIR or MIR signals alone and combinations of NIR and MIR signals at different fusion levels. In addition, the compatibility of the proposed approach with an underlying preprocessing technique in spectroscopy is assessed. The results obtained substantiate the utility of incorporating the designed feature vector generator into standard benchmarked modelling procedures under all considered scenarios. Finally, to promote the transparency and adoption of the propositions, SHapley additive exPlanations (SHAP) is leveraged to interpret the quantification outcomes.

Automated summary

This paper proposes a feature vector generation method based on signal fragmentation, combined with a model interpretation module, to enhance the quantification of glucose from absorption spectroscopy signals. The method dissects a given spectrum into fragments, and estimates the reference glucose concentration from each fragment using a base-learner. The estimates from all fragments are then stacked to form a feature vector, which is studied by a meta-learner to yield a final estimation of the glucose concentration. The proposed method is evaluated under different scenarios and found to be effective in benchmarked modelling procedures. SHapley additive exPlanations (SHAP) is leveraged for transparency and interpretation of the quantification outcomes.