相关实验视频

Updated: Jul 9, 2026

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

整合视觉语言模型以加速高通量营养查

Peihua Ma¹, Yixin Wu², Ning Yu³

¹Department of Nutrition and Food Science, College of Agriculture and Natural Resources, University of Maryland, College Park, MD, 20742, USA.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)

|July 8, 2024

概括

这项研究引入了视觉语言模型 (VLMs),用于更快,更准确的食品营养分析. 新方法显著加速营养估计,同时保持高精度,帮助医疗保健和食品工业.

科学领域:

食品科学食品科学食品科学
计算化学的计算化学
人工智能的人工智能

背景情况:

准确的营养分析对医疗保健和食品工业至关重要.
营养分析的传统方法可能耗时,并且缺乏高吞吐量.
将先进的计算模型与化学分析相结合,有可能提高效率.

研究的目的:

开创视觉语言模型 (VLMs) 与营养分析的化学分析的整合.
开发一款尖端的VLM,以提高营养估计的速度和准确性.
建立营养数据编制精度的新基准.

主要方法:

使用UMDFood-90k数据库与一个新的视觉语言模型 (VLM).
集成VLM与传统的化学分析技术进行验证.
评估模型性能使用宏AUCROC用于脂质量定量.

主要成果:

在脂质量测量中获得了0.921的宏观AUCROC.
在超过82%的食品中,与传统化学分析相比,差异低于10%.
在学生测试中,营养查加速了36.9%.

结论:

开发的VLM为营养分析提供了快速,高吞吐量的解决方案.
这种方法显著提高了营养估计的速度和准确性.
这项研究通过计算和化学整合,在食品科学方面取得了重大进展.

关键词:

食品分析食品分析高通量选的高通量选机器学习是机器学习.精准营养精准营养精准营养视觉语言模型的模型

更多相关视频

Iterative Development of an Innovative Smartphone-Based Dietary Assessment Tool: Traqq

Iterative Development of an Innovative Smartphone-Based Dietary Assessment Tool: Traqq

Published on: March 19, 2021

Concept Development and Use of an Automated Food Intake and Eating Behavior Assessment Method

Concept Development and Use of an Automated Food Intake and Eating Behavior Assessment Method

Published on: February 19, 2021

相关概念视频

Vision

Vision

Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.