• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Components, packaging and manufacturing technology >Nondestructive Determination of Citric Acid Using Successive Projections Algorithm and Spectroscopic Techniques
【24h】

Nondestructive Determination of Citric Acid Using Successive Projections Algorithm and Spectroscopic Techniques

机译：连续投影算法和光谱技术无损测定柠檬酸

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

Successive projections algorithm (SPA) combined with least square-support vector machine (LS-SVM) was investigated to determine the citric acid of lemon vinegar by 13 wavelengths within visibleear infrared (Vis/NIR) spectral region. Five concentration levels (100%, 80%, 60%, 40% and 20%) of lemon vinegar were prepared, and the calibration set consisted of 150 samples, validation set consisted of 75 samples and the remaining 75 samples for prediction set. After the comparison of different preprocessing such as smoothing, standard normal variate and derivative, SPA was applied to extract the effective wavelengths to reduce the redundancies and collinearity of variables, and the multiple linear regression (MLR) models were developed compared with partial least squares (PLS) models. Simultaneously, the selected wavelengths were used as the inputs of LS-SVM, and a new proposed combination of SPA-LS-SVM model was developed. The results indicated that SPA-LS-SVM achieved the optimal prediction performance, and the correlation coefficient (r) and root mean square error of prediction (RMSEP) were 0.9894 and 0.0623, respectively. An excellent prediction precision was obtained. The overall results demonstrated that it was feasible to utilize Vis/NIR spectroscopy to predict the citric acid of lemon vinegar, and SPA-LS-SVM model achieved the optimal prediction precision. This study supplied a feasible method for the process monitoring of fruit vinegar manufacture and fermentation.
机译：研究了连续投影算法（SPA）与最小二乘支持向量机（LS-SVM）的结合，通过可见/近红外（Vis / NIR）光谱区域内的13个波长确定柠檬醋中的柠檬酸。制备了五个浓度水平（100％，80％，60％，40％和20％）的柠檬醋，校准集包含150个样品，验证集包含75个样品，其余75​​个用于预测集。在比较了平滑，标准正态变量和导数等不同预处理之后，应用SPA提取有效波长以减少变量的冗余和共线性，并与偏最小二乘相比建立了多元线性回归（MLR）模型（ PLS）模型。同时，将选择的波长用作LS-SVM的输入，并开发了一种新的SPA-LS-SVM模型组合。结果表明，SPA-LS-SVM达到了最佳的预测性能，相关系数（r）和预测均方根误差（RMSEP）分别为0.9894和0.0623。获得了极好的预测精度。总体结果表明，利用Vis / NIR光谱法预测柠檬醋中的柠檬酸是可行的，SPA-LS-SVM模型达到了最佳的预测精度。该研究为果醋生产和发酵过程的监测提供了一种可行的方法。

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