首页|Mahidol University Reports Findings in Artificial Intelligence (Automated Artifi cial Intelligence-Based Thai Food Dietary Assessment System: Development and Val idation)
Mahidol University Reports Findings in Artificial Intelligence (Automated Artifi cial Intelligence-Based Thai Food Dietary Assessment System: Development and Val idation)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Artificial Intelligenc e is the subject of a report. According to news reporting originating in Nakorn Panom, Thailand, by NewsRx journalists, research stated, “Dietary assessment is a fundamental component of nutrition research and plays a pivotal role in managi ng chronic diseases. Traditional dietary assessment methods, particularly in the context of Thai cuisine, often require extensive training and may lead to estim ation errors.” The news reporters obtained a quote from the research from Mahidol University, “ To address these challenges, Institute of Nutrition, Mahidol University (INMU) i Food, an innovative artificial intelligencebased Thai food dietary assessment s ystem, allows for estimating the nutritive values of dishes from food images. IN MU iFood leverages state-of-the-art technology and integrates a validated automa ted Thai food analysis system. Users can use 3 distinct input methods: food imag e recognition, manual input, and a convenient barcode scanner. This versatility simplifies the tracking of dietary intake while maximizing data quality at the i ndividual level. The core improvement in INMU iFood can be attributed to 2 key f actors, namely, the replacement of Yolov4-tiny with Yolov7 and the expansion of noncarbohydrate source foods in the training image data set. This combination si gnificantly enhances the system’s ability to identify food items, especially in scenarios with closely packed food images, thus improving accuracy. Validation r esults showcase the superior performance of the INMU iFood integrated V7-based s ystem over its predecessor, V4-based, with notable improvements in protein and f at estimation. Furthermore, INMU iFood addresses limitations by offering users t he option to import additional food products via a barcode scanner, thus providi ng access to a vast database of nutritional information through Open Food Facts. This integration ensures users can track their dietary intake effectively, with expanded access to over 3000 food items added to or updated in the Open Food Fa cts database covering a wide variety of dietary choices.”
Nakorn PanomThailandAsiaArtificial IntelligenceDiet and NutritionEmerging TechnologiesFood DietHealth and MedicineMachine Learning
NETL
NSTL
