相关实验视频

Updated: Mar 18, 2026

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements

Published on: June 28, 2016

用VIS-NIR光谱和机器学习技术将Lupinus种子分为甜味和苦味类别进行分类

Josefa Díaz-Álvarez¹, Francisco A Galea-Gragera², Francisco Chávez de la O³

¹Departamento de Tecnología de los Computadores y Comunicaciones, Centro Universitario de Mérida, Universidad de Extremadura, Mérida, Spain.

Frontiers in artificial intelligence

|March 16, 2026

概括

这项研究引入了一种使用可见近红外 (VIS-NIR) 光谱和机器学习的非破坏性方法,用于区分甜味和苦味狼 (Lupinus) 种子,为传统测试提供可持续的替代方案.

科学领域:

农业科学农业科学
分析化学分析化学
生物技术是生物技术.

背景情况:

狼 (Lupinus) 的生殖质包括甜味和苦味品种,通过特定的苦味化合物进行区分.
传统的分辨甜狼和苦狼的方法往往具有破坏性,限制了它们的实际应用.
开发非破坏性技术对于高效的狼繁殖和质量控制至关重要.

研究的目的:

评估可见近红外 (VIS-NIR) 光谱学与机器学习相结合的可见近红外 (VIS-NIR) 光谱学的有效性,用于狼种子的非破坏性分类.
为了比较不同机器学习算法和光谱转换技术的性能,将狼种子分类为甜或苦.
为了解决数据集中的类失衡问题,使用重新抽样方法来提高分类准确性.

主要方法:

获取7种狼物种的VIS-NIR光谱数据 (反射率和吸收率).
应用五种机器学习算法 (例如LGR,SVC,RF) 来分类种子.
利用光谱转换技术和重新采样方法来优化分类性能.

主要成果:

实现了高分类准确度,支持矢量分类 (SVC) 和随机森林 (RF) 模型表现出卓越的性能.
在吸收率数据上,SVC实现了93.2%的准确性,而在反射率数据上,线性梯度回归 (LGR) 和SVC分别达到92.5%和92.0%.
混合光谱转换和重新采样技术显著改善了歧视并减少了过拟合,特别是在不平衡的数据集中.

结论:

与机器学习相结合的VIS-NIR光谱学提供了一种可行且非破坏性的方法,用于区分甜色和苦色狼品种.
这种方法比传统的破坏性测试方法有了显著的进步.
这些发现支持这项技术在狼繁殖计划和食品行业用于质量评估的潜在应用.

关键词:

吸收性光谱的使用方法人工智能的人工智能是人工智能.食品的可持续性食品的可持续性重新抽样的方法.种子的表型化种子的表型化这是光谱反射率.

更多相关视频

Pure Shift Nuclear Magnetic Resonance: a New Tool for Plant Metabolomics

Pure Shift Nuclear Magnetic Resonance: a New Tool for Plant Metabolomics

Published on: July 31, 2021

Author Spotlight: A Tailor-Made Sample Preparation Approach for Enhanced MALDI-IMS Analysis of Hard Palm Seeds

Author Spotlight: A Tailor-Made Sample Preparation Approach for Enhanced MALDI-IMS Analysis of Hard Palm Seeds

Published on: June 30, 2023

相关概念视频

Light Acquisition

Light Acquisition

In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.

Classification of Signals

Classification of Signals

In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...