Rapid determination of oil content of single peanut seed by near-infrared hyperspectral imaging

Q3 Agricultural and Biological Sciences

Oil Crop Science Pub Date : 2024-09-06 DOI:10.1016/j.ocsci.2024.05.002

Shunting Zhang , Xue Li , Du Wang , Li Yu , Fei Ma , Xuefang Wang , Mengxue Fang , Huiying Lyu , Liangxiao Zhang , Zhiyong Gong , Peiwu Li

{"title":"Rapid determination of oil content of single peanut seed by near-infrared hyperspectral imaging","authors":"Shunting Zhang , Xue Li , Du Wang , Li Yu , Fei Ma , Xuefang Wang , Mengxue Fang , Huiying Lyu , Liangxiao Zhang , Zhiyong Gong , Peiwu Li","doi":"10.1016/j.ocsci.2024.05.002","DOIUrl":null,"url":null,"abstract":"<div><div>Oil content is a crucial indicator for evaluating the quality of peanuts. A rapid and non-destructive method to determine oil content of individual peanut seed can provide robust technical support for breeding high-oil-content peanut varieties. In this study, we established a rapid determination method using near-infrared hyperspectral imaging and chemometrics to assess the oil content of single peanut seed. After selecting key wavelengths through competitive adaptive reweighted sampling (CARS), uninformative variable elimination (UVE), and random frog (RF), we constructed an oil content calibration model based on partial least squares regression for single peanut seed. Validation results demonstrated that the correlation coefficient was 0.8393 with a root mean square error of 1.7771 in the calibration set, while it was 0.7915 with a root mean square error of 2.2943 in the independent prediction set. Most samples exhibited relative errors below 5%, confirming the reliability of this model in predicting oil content of single peanut seed.</div></div>","PeriodicalId":34095,"journal":{"name":"Oil Crop Science","volume":"9 4","pages":"Pages 220-224"},"PeriodicalIF":0.0000,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Oil Crop Science","FirstCategoryId":"1091","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2096242824000605","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Agricultural and Biological Sciences","Score":null,"Total":0}

引用次数: 0

Abstract

Oil content is a crucial indicator for evaluating the quality of peanuts. A rapid and non-destructive method to determine oil content of individual peanut seed can provide robust technical support for breeding high-oil-content peanut varieties. In this study, we established a rapid determination method using near-infrared hyperspectral imaging and chemometrics to assess the oil content of single peanut seed. After selecting key wavelengths through competitive adaptive reweighted sampling (CARS), uninformative variable elimination (UVE), and random frog (RF), we constructed an oil content calibration model based on partial least squares regression for single peanut seed. Validation results demonstrated that the correlation coefficient was 0.8393 with a root mean square error of 1.7771 in the calibration set, while it was 0.7915 with a root mean square error of 2.2943 in the independent prediction set. Most samples exhibited relative errors below 5%, confirming the reliability of this model in predicting oil content of single peanut seed.

查看原文本刊更多论文

利用近红外高光谱成像技术快速测定单粒花生种子的含油量

含油量是评价花生质量的一个重要指标。快速、无损地测定单粒花生种子含油量的方法可为培育高含油量花生品种提供有力的技术支持。在本研究中，我们建立了一种利用近红外高光谱成像和化学计量学评估单粒花生种子含油量的快速测定方法。通过竞争性自适应加权采样（CARS）、无信息变量剔除（UVE）和随机蛙法（RF）选择关键波长后，我们构建了基于偏最小二乘回归的单粒花生种子含油量校准模型。验证结果表明，校准集的相关系数为 0.8393，均方根误差为 1.7771；独立预测集的相关系数为 0.7915，均方根误差为 2.2943。大多数样本的相对误差低于 5%，这证实了该模型在预测单粒花生种子含油量方面的可靠性。

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