...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Spectrochimica acta, Part A. Molecular and biomolecular spectroscopy >Determination of origin and sugars of citrus fruits using genetic algorithm, correspondence analysis and partial least square combined with fiber optic NIR spectroscopy
【24h】

Determination of origin and sugars of citrus fruits using genetic algorithm, correspondence analysis and partial least square combined with fiber optic NIR spectroscopy

机译：遗传算法，对应分析和偏最小二乘结合光纤近红外光谱法测定柑橘类水果的原产地和糖分

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The capacity to confirm the variety or origin and the estimation of sucrose, glucose, fructose of the Citrus fruits are major interests of citrus juice industry. A rapid classification and quantification technique was developed and validated for simultaneous and nondestructive quantifying the sugar constituent's concentrations and the origin Of Citrus fruits using Fourier Transform Near-infrared (FT-NIR) spectroscopy in Conjunction with Artificial Neural Network (ANN) using genetic algorithm, Chemometrics and Correspondences Analysis (CA). To acquire good classification accuracy and to present a wide range of concentration Of Sucrose, glucose and fructose, we have collected 22 different Varieties of citrus fruits from the market during the entire season of citruses. FT-NIR spectra were recorded in the NIR region from 1100 to 2500 run using the fiber optic probe and three types of data analysis were performed. Chemometrics analysis using Partial Least Squares (PLS) was performed in order to determine the concentration of individual sugars. Artificial Neural Network analysis was performed for classification, origin or variety identification of citrus fruits using genetic algorithm. Correspondence analysis was performed in order to Visualize the relationship between the citrus fruits. To Compute a PLS model based upon the reference values and to validate the developed method, high performance liquid chromatography (HPLC) was performed. Spectral range and the number of PLS factors were optimized for the lowest standard error of calibration (SEC), prediction (SEP) and correlation coefficient (R-2). The calibration model developed was able to assess the Sucrose, glucose and fructose contents in unknown Citrus fruit Up to an R-2 value of 0.996-0.998. Numbers of factors from F1 to F10 were optimized for correspondence analysis for relationship visualization of citrus fruits based on the Output Values of genetic algorithm. ANN and CA analysis showed excellent classification of citrus according to the variety to which they belong and well-classified citrus according to their origin. The technique has potential in rapid determination of sugars content and to identify different varieties and origins of citrus in citrus in citrus industry. (C) 2008 Elsevier B.V. All rights reserved.
机译：确认柑橘类水果的品种或来源的能力以及估计蔗糖，葡萄糖，果糖的能力是柑橘汁工业的主要利益。开发了一种快速分类和定量技术，并通过遗传算法与人工神经网络（ANN）结合使用傅里叶变换近红外（FT-NIR）光谱技术，对糖成分的浓度和柑橘类水果的来源进行同时和无损定量验证，化学计量学和函授分析（CA）。为了获得良好的分类精度并呈现出广泛的蔗糖，葡萄糖和果糖浓度，我们在整个柑橘季节从市场上收集了22种不同的柑橘水果品种。使用光纤探针将FT-NIR光谱记录在1100至2500nm的NIR区域中，并进行了三种类型的数据分析。使用偏最小二乘（PLS）进行化学计量分析，以确定各个糖的浓度。使用遗传算法对柑橘类水果进行分类，起源或品种鉴定的人工神经网络分析。进行对应分析以可视化柑橘类水果之间的关系。为了基于参考值计算PLS模型并验证开发的方法，执行了高效液相色谱（HPLC）。优化了光谱范围和PLS因子的数量，以实现最低的标准校准误差（SEC），预测（SEP）和相关系数（R-2）。建立的校准模型能够评估未知柑橘类水果中的蔗糖，葡萄糖和果糖含量，R-2值为0.996-0.998。根据遗传算法的输出值，从F1到F10的因素数量进行了优化，以进行对应关系分析，从而可视化柑橘类水果的关系。 ANN和CA分析表明，根据柑橘所属的种类对柑橘进行出色的分类，并根据其来源对柑橘进行分类。该技术具有快速测定糖含量和鉴定柑橘工业中柑橘中柑橘的不同品种和来源的潜力。 （C）2008 Elsevier B.V.保留所有权利。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号