Discriminate of Moldy Chestnut Based on Near Infrared Spectroscopy and Feature Extraction by Fourier Transform

As near infrared spectra has the characters of multi-variables and strong correlations, to solve the problem, Fourier transform (FT) was used to extract feature variables of shelled chestnuts spectra. FT coefficients and the status of 178 chestnuts were selected as inputs and outputs of the back-propagation neural network (BPNN) classifier to build a recognition model. For comparison, principal component analysis (PCA) was utilized to compress the variables, which then was introduced as input of the neural network model. The results demonstrate that FT is a powerful feature extraction method and is better than PCA as a feature extraction method when employed together with BPNN. When the preprocessing method of standard normal variate transformation(SNV) was carried out and the first 15-point FT coefficients were used as the input, an optimal network structure of 15-6-1 was obtained, where discriminating rates of qualified chestnut, surface moldy chestnut and internal moldy chestnut in prediction set are 100%, 100% and 92.31%, respectively.

[1]  Guleda Onkal Engin,et al.  Modeling leaching behavior of solidified wastes using back-propagation neural networks. , 2009, Ecotoxicology and environmental safety.

[2]  Xiaoli Li,et al.  Non-destructive discrimination of Chinese bayberry varieties using Vis/NIR spectroscopy , 2007 .

[3]  Z-Y Yao,et al.  Equilibrium, kinetic and thermodynamic studies on the biosorption of Cu(II) onto chestnut shell. , 2010, Journal of hazardous materials.

[4]  Shouhong Wang,et al.  Application of the Back Propagation Neural Network Algorithm with Monotonicity Constraints for Two‐Group Classification Problems* , 1993 .

[5]  Jordi Coello,et al.  NIR calibration in non-linear systems: different PLS approaches and artificial neural networks , 2000 .

[6]  F. J. Acevedo,et al.  Classification of wines produced in specific regions by UV-visible spectroscopy combined with support vector machines. , 2007, Journal of agricultural and food chemistry.

[7]  Shuo-Yan Chou,et al.  A simulated-annealing-based approach for simultaneous parameter optimization and feature selection of back-propagation networks , 2008, Expert Syst. Appl..

[8]  M Gishen,et al.  Effect of temperature variation on the visible and near infrared spectra of wine and the consequences on the partial least square calibrations developed to measure chemical composition. , 2007, Analytica chimica acta.

[9]  Desire L. Massart,et al.  Feature reduction by Fourier transform in pattern recognition of NIR data , 1996 .

[10]  R. Yu,et al.  An ensemble of Monte Carlo uninformative variable elimination for wavelength selection. , 2008, Analytica chimica acta.

[11]  Daniel Cozzolino,et al.  Classification of Tempranillo wines according to geographic origin: combination of mass spectrometry based electronic nose and chemometrics. , 2010, Analytica chimica acta.

[12]  Fei Liu,et al.  Classification of brands of instant noodles using Vis/NIR spectroscopy and chemometrics , 2008 .

[13]  Emil W. Ciurczak,et al.  Handbook of Near-Infrared Analysis , 1992 .

[14]  B.H.M. Sadeghi,et al.  A BP-neural network predictor model for plastic injection molding process , 2000 .

[15]  Tom Fearn,et al.  Development and validation of near infrared microscopy spectral libraries of ingredients in animal feed as a first step to adopting traceability and authenticity as guarantors of food safety , 2010 .

[16]  Surjya K. Pal,et al.  Flank wear prediction in drilling using back propagation neural network and radial basis function network , 2008, Appl. Soft Comput..

[17]  Lijuan Xie,et al.  Classification of tomatoes with different genotypes by visible and short-wave near-infrared spectroscopy with least-squares support vector machines and other chemometrics. , 2009 .

[18]  Onno E. de Noord,et al.  Application of Fourier transform to multivariate calibration of near-infrared data , 1998 .

[19]  G. W. Small,et al.  Comparison of combination and first overtone spectral regions for near-infrared calibration models for glucose and other biomolecules in aqueous solutions. , 2004, Analytical chemistry.

[20]  Li Peiwu,et al.  Near-infrared spectral detection of soil moisture based on feature extraction of FFT. , 2009 .

[21]  H. Troy Nagle,et al.  Performance of the Levenberg–Marquardt neural network training method in electronic nose applications , 2005 .