Comparison of a Neural Network and a Non-parametric Classifier for Grain Kernel Identification

Paliwal, Jitendra; Visen, N.S.; Jayas, Digvir S.; White, N. D. G.

doi:10.1016/s1537-5110(03)00083-7

Cited by 49 publications

(15 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Model 6 was found by inputting 69 variables into a backpropagation neural network for training with 40 nodes in the first hidden layer and 20 nodes in the second hidden layer, with 50,000 iterations, an RMS error of 0.19, and a correlation coefficient of 0.67. In the manner of Paliwal et al (2003), the two-dimensional correlation coefficient matrix of each variable (m × n matrix, where m and n are sample size and number of variables, respectively) was found. Taking the absolute of each element and calculating the average of each column, this reduced the two-dimensional correlation coefficient matrixes to a one-dimensional correlation coefficient vector and rearranged each variable by correlation coefficient from low to high.…”

Section: Methodsmentioning

confidence: 99%

Wavelength Selection for Classifying Paddy Rice by Near‐Infrared Spectroscopy

et al. 2006

View full text Add to dashboard Cite

Using five paddy rice cultivars grown in Central, Eastern, and Southern Taiwan and harvested in the summers of 1997, 1998, and 1999, eight calibrated models were established by discriminant analysis and back‐propagation neural network with four wavelength selection methods. Randomly adding 80 samples of the 2000 year crop in the three‐crop‐year calibrated models for annual recalibration, eight models were used to classify paddy rice harvested in the summer of 2000. With 351 wavelengths of models 1 and 2, the average classification rates by discriminant analysis and backpropagation neural network were 98.1 and 92.5%, respectively. With 69 wavelengths selected by stepwise discrimination of models 3 and 4, the average classification rates by discriminant analysis and backpropagation neural network were 98.5 and 85.5%, respectively. With 69 wavelengths selected by correlation matrix of models 5 and 6, the average classification rates by discriminant analysis and neural network were 72.0 and 72.2%, respectively. With 69 wavelengths from loading values in the first and second principal components of models 7 and 8, the average classification rates by discriminant analysis and neural network were 69.1 and 60.6%, respectively. Model 3 would be recommended for classifying paddy rice to set trading prices because of its highest classification rate (98.5%).

show abstract

Section: Methodsmentioning

confidence: 99%

Wavelength Selection for Classifying Paddy Rice by Near‐Infrared Spectroscopy

et al. 2006

View full text Add to dashboard Cite

show abstract

“…Network analyses (artificial neural network [ANN] and radial basis function [RBF]) have been utilized. Several authors have observed that ANNs can provide higher classification and prediction probability than conventional multivariate analysis for complex nonlinear data (Gardner and Bartlett 1993; Ping and Jun 1996; Brezmes and others 1997; Schaller and others 1998; Paliwal and others 2003; Ushada and Murase 2006). …”

Section: Introductionmentioning

confidence: 99%

Evaluation of Coffee Roasting Degree by Using Electronic Nose and Artificial Neural Network for Off‐line Quality Control

Romani¹,

Cevoli²,

Fabbri³

et al. 2012

Journal of Food Science

View full text Add to dashboard Cite

Actually the evaluation of coffee roasting degree is mainly a manned operation, substantially based on the empirical final color observation. For this reason it requires well-trained operators with a long professional skill. The coupling of e-nose and artificial neural networks (ANNs) may represent an effective possibility to roasting process automation and to set up a more reproducible procedure for final coffee bean quality characterization.

show abstract

“…They developed models with the use of neural networks, which resulted in a classification accuracy of 40-96%. Paliwal et al [9] used a combination of geometric features, grain surface texture and its color to develop a statistical model that used selected variables to identify varieties. They selected 20 features in each group.…”

Section: Introductionmentioning

confidence: 99%

Discrimination of wheat grain varieties using image analysis: morphological features

Zapotoczny

2011

Eur Food Res Technol

View full text Add to dashboard Cite

This paper presents the results of a study on the discrimination of 11 wheat grain varieties in three successive years of cultivation and at the grain humidity of 12, 14 and 16%. Each grain was described with the use of 54 geometric variables which, after reduction of variables, left 20 for use in the main analysis. Variables calculated from linear dimensions had the greatest share in the group of discriminating variables, with shape-related indexes being of lesser importance. Seven methods of variables selection based on genetic algorithms (the Class Ranker and Class RankersSearch methods) were used in the study. The final discriminant analysis was performed with the use of stepwise progressive analysis and Meta MultiClass Classifier. The proposed statistical model classified varieties with 90-100% accuracy, depending on the experimental group. Grain images were acquired with a flat scanner, and grains were arranged with a specially designed matrix which enabled arranging 552 grains in rows and columns within several minutes; this makes the method usable in the cereal industry.

show abstract

Comparison of a Neural Network and a Non-parametric Classifier for Grain Kernel Identification

Cited by 49 publications

References 12 publications

Wavelength Selection for Classifying Paddy Rice by Near‐Infrared Spectroscopy

Wavelength Selection for Classifying Paddy Rice by Near‐Infrared Spectroscopy

Evaluation of Coffee Roasting Degree by Using Electronic Nose and Artificial Neural Network for Off‐line Quality Control

Discrimination of wheat grain varieties using image analysis: morphological features

Contact Info

Product

Resources

About