Identification of Wine According to Grape Variety Using Near-Infrared Spectroscopy Based on Radial Basis Function Neural Networks and Least-Squares Support Vector Machines
作者: Jing YuJicheng ZhanWeidong Huang
作者单位: 1China Agricultural University
刊名: Food Analytical Methods, 2017, Vol.10 (10), pp.3306-3311
来源数据库: Springer Journal
DOI: 10.1007/s12161-017-0887-1
关键词: Near-infrared spectroscopyWineDiscriminationRadial basis function neural networksLeast-squares support vector machines
英文摘要: This paper describes how near-infrared (NIR) spectroscopy combined with radial basis function neural networks (RBFNN) and least-squares support vector machines (LS-SVMs) based on principal component analysis (PCA) can be used to classify wines from grape varieties. The effects of different preprocessing methods (standard normal variate (SNV) and multiplicative scattering correction (MSC)) on classification results were also compared. The results show that the use of NIR preprocessing spectral data with optimum RBFNN parameters produced a very high level of correct classification rate, 90.16–98.36%. For RBF LS-SVM, identification rates were from 91.80 to 98.36%. The results demonstrate that, combined with chemometrics with appropriate spectral data pretreatment, NIR spectroscopy has...
原始语种摘要: This paper describes how near-infrared (NIR) spectroscopy combined with radial basis function neural networks (RBFNN) and least-squares support vector machines (LS-SVMs) based on principal component analysis (PCA) can be used to classify wines from grape varieties. The effects of different preprocessing methods (standard normal variate (SNV) and multiplicative scattering correction (MSC)) on classification results were also compared. The results show that the use of NIR preprocessing spectral data with optimum RBFNN parameters produced a very high level of correct classification rate, 90.16–98.36%. For RBF LS-SVM, identification rates were from 91.80 to 98.36%. The results demonstrate that, combined with chemometrics with appropriate spectral data pretreatment, NIR spectroscopy has...
全文获取路径: Springer  (合作)
分享到:
来源刊物:
影响因子:1.969 (2012)

×
关键词翻译
关键词翻译
  • preprocessing 预处理
  • Vector 矢量
  • machines 机械
  • demonstrate 说明
  • spectral 谱的
  • neural 神经系统的
  • infrared 红外线
  • vector 矢量
  • spectroscopy 分光学
  • correct 修正