相关实验视频

Updated: May 31, 2025

O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression

O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression

Published on: November 8, 2019

机器学习驱动的基板Vis/NIR光谱仪用于在线检测混合品质的混合

Tao Jiang¹, Weidan Zuo¹, Jianjun Ding¹

¹State Key Laboratory of Food Science and Resources, Jiangnan University, Wuxi, Jiangsu Province, China; School of Food Science and Technology, Jiangnan University University, Wuxi, Jiangsu Province, China; Collaborative Innovation Center of Food Safety and Quality Control in Jiangsu Province, Jiangnan University, China.

Food research international (Ottawa, Ont.)

|January 24, 2025

概括

可见和近红外 (Vis/NIR) 光谱与机器学习准确预测混合的质量. 多区域光谱数据和特定的预处理方法,如萨维茨基-戈莱平滑-部分最小平方 (SGS-PLS) 显示了大规模在线检测的巨大潜力.

科学领域:

农业科学农业科学
频谱学是一种光谱学.
机器学习机器学习

背景情况:

对混合的准确质量评估对于农业和商业用途至关重要.
确定可溶性固体度 (SSC) 和可定位酸度 (TA) 的传统方法往往耗时且具有破坏性.
可见和近红外 (Vis/NIR) 光谱为快速质量分析提供了一种非破坏性的替代方案.

研究的目的:

研究Vis/NIR光谱学与机器学习相结合的应用,用于预测混合中的SSC和TA.
评估不同频谱区域 (腹,赤道,多区域) 和机器学习模型的有效性.
优化光谱预处理技术,以提高预测准确度.

主要方法:

从混合果样本采集了Vis/NIR光谱,使用了基板设备.
来自不同区域 (,赤道,多区域) 的光谱使用各种机器学习模型进行了分析:部分最小平方 (PLS),随机森林 (RF),k-最近邻居 (KNN),支持向量机 (SVM) 和多层前神经网络 (MFNN).
应用和评估了光谱预处理技术,包括萨维茨基-戈莱平滑 (SGS),最大规范化 (MN),乘法散射校正 (MSC),线性基线校正 (LBC) 和第一个导数 (1stD).

主要成果:

与单个区域数据相比,多区域光谱数据收集提高了SSC和TA的预测准确性.
使用SGS光谱的PLS模型 (SGS-PLS) 在SSC预测方面表现出卓越的性能 (R_P2 = 0.875,RMSEP = 0.572%,MAEP = 0.469%).
使用原始光谱 (Raw-MFNN) 的MFNN模型显示了TA预测的优异结果 (R_P2 = 0.800,RMSEP = 0.0322%,MAEP = 0.0249%),表明强大的概括能力.

结论:

与机器学习相结合的Vis/NIR光谱是一种高效的,非破坏性的方法,用于评估混合的质量.
多区域光谱收集策略和优化的预处理 (SSC的SGS-PLS,TA的Raw-MFNN) 显著提高了预测准确性.
这种方法具有巨大的潜力,可以在类产业中进行大规模的在线质量检测.

关键词:

基板Vis/NIR光谱法基板Vis/NIR光谱法混合类的混合类.机器学习机器学习质量预测质量预测

更多相关视频

Fruit Volatile Analysis Using an Electronic Nose

Fruit Volatile Analysis Using an Electronic Nose

Published on: March 30, 2012

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

相关概念视频

Applications of IR Spectroscopy: Overview

Applications of IR Spectroscopy: Overview

The non-destructive nature and ability to provide valuable chemical information make IR spectroscopy a versatile technique with broad applications in various scientific and industrial fields. IR spectroscopy is commonly used to identify and characterize organic and inorganic compounds. It provides information about the functional groups present in a molecule and the bonding between atoms. This helps in the structural elucidation of compounds during organic synthesis, pharmaceutical research,...

Ultraviolet and Visible (UV–Vis) Spectroscopy: Overview

Ultraviolet and Visible (UV–Vis) Spectroscopy: Overview

Ultraviolet–visible (UV–visible or UV–Vis) spectroscopy is an analytical technique that investigates the interaction between matter and UV–Vis light within the electromagnetic spectrum. This method is widely used for its versatility, simplicity, and relatively quick data acquisition, making it valuable for both qualitative and quantitative analysis. When UV–Vis radiation passes through a material, molecules absorb light depending on the energy required for...

Key Elements for Plant Nutrition

Key Elements for Plant Nutrition

Like all living organisms, plants require organic and inorganic nutrients to survive, reproduce, grow and maintain homeostasis. To identify nutrients that are essential for plant functioning, researchers have leveraged a technique called hydroponics. In hydroponic culture systems, plants are grown—without soil—in water-based solutions containing nutrients. At least 17 nutrients have been identified as essential elements required by plants. Plants acquire these elements from the...