Classification of glucose concentration in diluted urine using the low-resolution Raman spectroscopy and kernel optimization methods

Abstract

In order to detect minute amounts of glucose in diluted urine, we applied the Raman spectroscopy method. To simulate abnormal diluted urine in a toilet bowl, we diluted normal urine ten-fold with water and added glucose up to 8 mg dl(-1). Data were collected using a low-resolution Raman spectrometer that was preprocessed with the optimizing kernel method. We also applied the neural network algorithm to classify abnormal and normal urine samples according to their glucose concentrations. The kernel optimizing method was very effective in the classification of the tested subjects as it increased the accuracy of classification by 92%. This method suggests the possibility of caring for patients by daily monitoring their urine components in a manner non-invasive to ordinary life.