Vis/NIR and FTIR spectroscopy supported by machine learning techniques to distinguish pure from impure Iranian rice varieties

IF 2 4区农林科学 Q2 AGRONOMY

International Agrophysics Pub Date : 2024-04-18 DOI:10.31545/intagr/185392

Hamed Zaresani, Amir Hossein Afkari Sayyah, H. Zareiforoush, Ali Khorramifar, Marek Gancarz, Sylwester Tabor, Hamed Karami

{"title":"Vis/NIR and FTIR spectroscopy supported by machine learning techniques to distinguish pure from impure Iranian rice varieties","authors":"Hamed Zaresani, Amir Hossein Afkari Sayyah, H. Zareiforoush, Ali Khorramifar, Marek Gancarz, Sylwester Tabor, Hamed Karami","doi":"10.31545/intagr/185392","DOIUrl":null,"url":null,"abstract":". Rice is an annual plant from the family of Oryzeae, provides the main food for about 2.5 billion people. The quality of this product is under the influence of various factors. Quality control and adulteration detection are among the main issues in the rice industry for which, various methods have been developed. Some of these methods are costly or with low accuracy. Therefore, this study aimed to investigate and detect adulteration with spectroscopic devices and chemometric methods as well as neural network approach. The results of this study indicated the highest accuracy (100%) in the detection of authentic rice for Fourier-transform infrared combined with C-support vector machine (linear and polynomial functions) and visible–near–infrared device with quadratic discriminant analysis, multivariate discriminant analysis, Bayesian, and Decision Tree. The lowest accuracy was also related to support vector machine method with Sigmoid function for both devices. Principal component analysis method also provided very high accuracy for both devices (accuracy of 100% for visible–near–infrared and 99% for Fourier-transform infrared).","PeriodicalId":13959,"journal":{"name":"International Agrophysics","volume":null,"pages":null},"PeriodicalIF":2.0000,"publicationDate":"2024-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Agrophysics","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.31545/intagr/185392","RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"AGRONOMY","Score":null,"Total":0}

引用次数: 0

Abstract

. Rice is an annual plant from the family of Oryzeae, provides the main food for about 2.5 billion people. The quality of this product is under the influence of various factors. Quality control and adulteration detection are among the main issues in the rice industry for which, various methods have been developed. Some of these methods are costly or with low accuracy. Therefore, this study aimed to investigate and detect adulteration with spectroscopic devices and chemometric methods as well as neural network approach. The results of this study indicated the highest accuracy (100%) in the detection of authentic rice for Fourier-transform infrared combined with C-support vector machine (linear and polynomial functions) and visible–near–infrared device with quadratic discriminant analysis, multivariate discriminant analysis, Bayesian, and Decision Tree. The lowest accuracy was also related to support vector machine method with Sigmoid function for both devices. Principal component analysis method also provided very high accuracy for both devices (accuracy of 100% for visible–near–infrared and 99% for Fourier-transform infrared).

查看原文本刊更多论文

机器学习技术辅助下的可见光/近红外和傅立叶变换红外光谱法区分纯净和不纯净的伊朗水稻品种

.水稻是一种一年生的木本植物，为大约 25 亿人提供主要食物。该产品的质量受到各种因素的影响。质量控制和掺假检测是大米行业的主要问题之一，为此开发了各种方法。其中一些方法成本较高或准确度较低。因此，本研究旨在利用光谱设备和化学计量学方法以及神经网络方法来调查和检测掺假情况。研究结果表明，傅立叶变换红外线结合支持向量机（线性和多项式函数）和可见近红外装置结合二次判别分析、多元判别分析、贝叶斯法和决策树检测大米真伪的准确率最高（100%）。在这两种设备上，使用 Sigmoid 函数的支持向量机方法的准确率也最低。主成分分析法也为两种设备提供了非常高的准确率（可见近红外准确率为 100%，傅立叶变换红外准确率为 99%）。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Agrophysics 农林科学-农艺学

CiteScore

3.60

自引率

9.10%

发文量

审稿时长

3 months

期刊介绍： The journal is focused on the soil-plant-atmosphere system. The journal publishes original research and review papers on any subject regarding soil, plant and atmosphere and the interface in between. Manuscripts on postharvest processing and quality of crops are also welcomed. Particularly the journal is focused on the following areas: implications of agricultural land use, soil management and climate change on production of biomass and renewable energy, soil structure, cycling of carbon, water, heat and nutrients, biota, greenhouse gases and environment, soil-plant-atmosphere continuum and ways of its regulation to increase efficiency of water, energy and chemicals in agriculture, postharvest management and processing of agricultural and horticultural products in relation to food quality and safety, mathematical modeling of physical processes affecting environment quality, plant production and postharvest processing, advances in sensors and communication devices to measure and collect information about physical conditions in agricultural and natural environments. Papers accepted in the International Agrophysics should reveal substantial novelty and include thoughtful physical, biological and chemical interpretation and accurate description of the methods used. All manuscripts are initially checked on topic suitability and linguistic quality.