Integrating Vision‐Language Models for Accelerated High‐Throughput Nutrition Screening DOI Creative Commons
Peihua Ma, Yixin Wu, Ning Yu

и другие.

Advanced Science, Год журнала: 2024, Номер unknown

Опубликована: Июль 8, 2024

Addressing the critical need for swift and precise nutritional profiling in healthcare food industry, this study pioneers integration of vision-language models (VLMs) with chemical analysis techniques. A cutting-edge VLM is unveiled, utilizing expansive UMDFood-90k database, to significantly improve speed accuracy nutrient estimation processes. Demonstrating a macro-AUCROC 0.921 lipid quantification, model exhibits less than 10% variance compared traditional analyses over 82% analyzed items. This innovative approach not only accelerates screening by 36.9% when tested amongst students but also sets new benchmark precision data compilation. research marks substantial leap forward science, employing blend advanced computational validation offer rapid, high-throughput solution analysis.

Язык: Английский

The application progress and research trends of knowledge graphs and large language models in agriculture DOI

Ruizi Gong,

Xinxing Li

Computers and Electronics in Agriculture, Год журнала: 2025, Номер 235, С. 110396 - 110396

Опубликована: Апрель 19, 2025

Язык: Английский

Процитировано

0

PlantCareNet: an advanced system to recognize plant diseases with dual-mode recommendations for prevention DOI Creative Commons
Muhaiminul Islam, AKM Azad, Shifat E. Arman

и другие.

Plant Methods, Год журнала: 2025, Номер 21(1)

Опубликована: Апрель 23, 2025

Язык: Английский

Процитировано

0

Generative AI for Smallholder Agricultural Advice in Sub-Saharan Africa DOI
Joyce Nakatumba‐Nabende, Ann Lisa Nabiryo, Peter Nabende

и другие.

Oxford University Press eBooks, Год журнала: 2025, Номер unknown

Опубликована: Апрель 22, 2025

Abstract Smallholder farmers are prone to food insecurity due the devastating effects of viral crop diseases, pest outbreaks, and lack timely, targeted advice. Leveraging Large Language Models (LLMs) in agriculture offers significant potential bridge information gaps that smallholder face. This study discusses development an expert-reviewed agricultural question-answer dataset. We analysed responses from LLMs experts on crop- animal-related questions using relevancy, coherence, fluency metrics. Our results show GPT-4 outperforms other across these LLM-powered systems can act as virtual extension agents, assisting decision-making overcoming farming challenges.

Язык: Английский

Процитировано

0

Generative artificial intelligence in the agri-food value chain - overview, potential, and research challenges DOI Creative Commons
Christian Krupitzer

Frontiers in Food Science and Technology, Год журнала: 2024, Номер 4

Опубликована: Сен. 25, 2024

ChatGPT uses a so called Large Language Model (LLM) to provide textual output of analyzed data. Those LLMs are one example for Generative Artificial Intelligence (AI), which focuses on creating new content, e.g., text, images, or music, based learned patterns. Recently, applications in the food industry and agriculture started apply AI. This mini review provides an overview about AI agri-food supply chain discusses open research challenges, also combination with digital twins.

Язык: Английский

Процитировано

3

Integrating Vision‐Language Models for Accelerated High‐Throughput Nutrition Screening DOI Creative Commons
Peihua Ma, Yixin Wu, Ning Yu

и другие.

Advanced Science, Год журнала: 2024, Номер unknown

Опубликована: Июль 8, 2024

Addressing the critical need for swift and precise nutritional profiling in healthcare food industry, this study pioneers integration of vision-language models (VLMs) with chemical analysis techniques. A cutting-edge VLM is unveiled, utilizing expansive UMDFood-90k database, to significantly improve speed accuracy nutrient estimation processes. Demonstrating a macro-AUCROC 0.921 lipid quantification, model exhibits less than 10% variance compared traditional analyses over 82% analyzed items. This innovative approach not only accelerates screening by 36.9% when tested amongst students but also sets new benchmark precision data compilation. research marks substantial leap forward science, employing blend advanced computational validation offer rapid, high-throughput solution analysis.

Язык: Английский

Процитировано

2