Esther Kok ^* Aneesh Chauhan Michele Tufano Edith Feskens Guido Camps

• Wageningen Food & Biobased Research, Wageningen University and Research, Wageningen, Netherlands

Accurate measurement of dietary intake without interfering in natural eating habits is a longstanding problem in nutritional epidemiology. We explored the applicability of hyperspectral imaging and machine learning for dietary assessment of home-prepared meals, by building a proof-of-concept, which automatically detects food ingredients inside closed sandwiches. Individual spectra were selected from 24 hyperspectral images of assembled closed sandwiches, measured in a spectral range of 1116.14nm to 1670.62nm over 108 bands, preprocessed with Standard Normal Variate filtering, derivatives, and subsampling, and fed into multiple algorithms, amount which PLS-DA, multiple classifiers, and a simple neural network. The resulting best performing models had an accuracy score of ~80% for predicting type of bread, ~60% for butter, and ~28% for filling type. We see that the main struggle in predicting the fillings lies with the spreadable fillings, meaning the model may be focusing on structural aspects and not nutritional composition. Further analysis on non-homogeneous mixed food items, using computer vision techniques, will contribute towards a generalizable system. While there are still significant technical challenges to overcome before such a system can be routinely implemented in studies of free-living subjects, we believe it holds promise as a future tool for nutrition research and population intake monitoring.