基于机器学习的预测模型的构建,用于品种--
Mengjie Ma1, Zhengbiao Gu2, Li Cheng2
1State Key Laboratory of Food Science and Resources, Jiangnan University, Wuxi 214122, Jiangsu Province, China; School of Food Science and Technology, Jiangnan University, Wuxi 214122, China.
Food research international (Ottawa, Ont.)
|November 21, 2025
概括
这项研究开发了一种机器学习框架,将米的特性,和饮食联系起来. 它可以预测和肉质的特性,从而实现优化大米加工和量身定制的食品设计.
科学领域:
- 食品科学与技术 食品科学与技术
- 机器学习在食品加工中的应用
- 感官科学 感官科学
背景情况:
- 了解大米特性,和口腔加工之间的联系对于食品产品的开发至关重要.
- 目前用于预测口腔处理结果的方法有限.
- 需要采用多层面的方法来整合影响大米消费的各种因素.
研究的目的:
- 建立基于机器学习的预测框架,以量化大米物理化学特性,条件和口服加工之间的关系.
- 开发和比较各种机器学习模型来预测和玻尿酸性质.
- 为了实现从投入到口服结果的端到端预测,以优化大米产品设计.
主要方法:
- 描述了56种大米品种的纹理,形态和粉含量.
- 测量了体内的参数 (时间,次数,唾液量) 和玻尿酸性质 (颗粒大小,降低糖含量).
- 开发和评估了五种预测模型:多重线性回归,极端梯度增强 (XGBoost),支持矢量机 (SVM),长短期记忆网络 (LSTM) 和卷积神经网络.
主要成果:
- 硬度,性和性是行为 (r > 0.7) 的关键决定因素.
- 颗粒长宽比对玻尿酸颗粒大小 (r > 0.7) 有负面影响.
- LSTM实现了最佳的预测 (测试R2 = 0.9499),SVM在玻尿酸性质预测方面表现出色 (R2 = 0.9168),XGBoost捕获了和质感的相互作用 (R2 = 0.8161).
结论:
- 机器学习框架可以根据物理化学特征和条件有效地预测米的和肉质特性.
- 级联模型 (XGBoost-LSTM,XGBoost-SVM) 允许从到口腔加工进行全面的预测.
- 这一框架促进了大米加工和感官质量的数字优化,促进了定制食品设计.
更多相关视频
06:19Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
Published on: August 16, 2024
808
09:43Author Spotlight: Streamlining Rice Breeding with CRISPR/Cas for Obtaining Optimal Phenotypic and Agronomic Traits
Published on: January 3, 2025
3.3K
相关概念视频
Plant Breeding and Biotechnology
21.4K
Crop cultivation has a long history in human civilization, with records showing the cultivation of cereal plants beginning at around 8000 BC. This early plant breeding was developed primarily to provide a steady supply of food.
21.4K
Predicting Products: Substitution vs. Elimination
13.7K
When a nucleophile and an alkyl halide react, nucleophilic substitution and β-elimination reactions compete to generate products.
The following factors can influence the mechanisms competing against each other:
The following factors can influence the mechanisms competing against each other:
13.7K
