This study aims to develop a deep learning model to monitor rice serving amounts in institutional foodservice, enhancing personalized nutrition management. The goal is to identify the best convolutional neural network (CNN) for detecting rice quantities on serving trays, addressing balanced dietary intake challenges. Both a vanilla CNN and 12 pre-trained CNNs were tested, using features extracted from images of varying rice quantities on white trays. Configurations included optimizers, image generation, dropout, feature extraction, and fine-tuning, with top-1 validation accuracy as the evaluation metric. The vanilla CNN achieved 60% top-1 validation accuracy, while pre-trained CNNs significantly improved performance, reaching up to 90% accuracy. MobileNetV2, suitable for mobile devices, achieved a minimum 76% accuracy. These results suggest the model can effectively monitor rice servings, with potential for improvement through ongoing data collection and training. This development represents a significant advancement in personalized nutrition management, with high validation accuracy indicating its potential utility in dietary management. Continuous improvement based on expanding datasets promises enhanced precision and reliability, contributing to better health outcomes.

Low sodium (1,300 mg) containing menu items and recipes applicable to institutional food services were developed while maintaining taste and nutrition contents. These developed recipes were used in a total of 258 dish items, including 39 onedish meals, 43 guk or jjigae (soups or pot stews), 59 meat or fish side-dishes, 94 vegetable side-dishes, 9 jeons (pan-fried dishes), and 14 kimchis or pickles. A total of 90 menu items using 258 dishes were categorized into one-dish menu items or Korean dining table-setting items. They were re-sorted to soup or pot stew containing or not containing items. The protein content was significantly higher in one-dish menus than in Korean dining table-setting menus (p<0.05), whereas the energy, carbohydrates, lipids, and sodium did not differ significantly between them. Menus including guk showed no significant differences in energy, carbohydrates, lipids, or sodium when compared with menus not including guk. For practical application of these developed low sodium menu items for institutional food services, education manuals for nutrition should be developed, and networks among governmental agencies, institutional food services and research institutions should be established.