Application of machine learning for estimating label nutrients using USDA Global Branded Food Products Database, (BFPD)

Abstract Automatic, accurate, and robust prediction of food attributes using emerging machine learning techniques including artificial intelligence may be helpful to rapid food analyze, and personal dietary record. In this paper we have, for the first time, evaluated 5 machine learning models for quantitatively predicting nutrients from foods based on their ingredients. Based on the USDA Global Branded Food Products Database (BFPD), we prepared a machine-readable dataset for two domains - nutrient and ingredient. Based on these datasets, we investigated five prominent models, including AdaBoost, Bayesians, Linear Support Vector Machine (SVM), Multi-Layer Perceptron (MLP) and one tailored-improved MLP called MLPcr to predict 13 label nutrients included in BFPD based on their ingredients. We report on 3 varied nutrients in this paper – carbohydrates, protein, and sodium. The prediction based on the neural network model, MLP, and MLPcr achieved the most accuracy, as high as 0.900 for carbohydrates. A detailed evaluation of the prediction results found that the data distribution and multi-factor complexity have an essential impact on the accuracy of the final prediction. Our research shows the possibility of using neural networks for prediction of nutrients using food ingredients, as well as potential use of neural network applications to the broader scope of food research.