Detection of Six Kinds of Acid in Red Wine with Infrared Spectroscopy Based on FastICA and Neural Network

摘要：

For the rapid detection of the six kinds of acid inred wine,infrared(IR)spectra of 44 wine sampleswere analyzed A new method of model constructionbased on back-propagation artificial neural networks(BP-ANN)regression and fast independent componentanalysis(FastlCA)was proposed. This newchemometric method,named ICA-NNR,has beenapplied to detect the six kinds of acid in wine samples.Compared with the model built by the common usedmethods,such as PCR and PLS,ICA-NNR method hasadvantages in both the correlation coefficient andstandard error of calibration.The correlationcoefficients(R)between the referenced values and themodel predicted values are 0.9833,0.9759,0.9585,0.9989,0.9643 and 0.9884,respectively.The resultsshow the feasibility of establishing the models withICA-NNR method for red wine samplesquantitativeanalysis and provide a foundation for the applicationand further development of IR on-line red wineanalyzer.

作者: Limin Fang Min Lin

作者单位: College of Metrology and Measurement Engineering,China Jiliang University,Hangzhou,China

会议类型: 国际会议

会议名称: 2008 3rd International Conference on Intelligent System and Knowledge Engineering(第三届智能系统与知识工程国际会议)(ISKE 2008)

会议地点: 厦门

会议语种:英文

页码: 856-861

在线出版日期: 2008-11-17（万方平台首次上网日期，不代表论文的发表时间）