Classification of three wine varieties based on ELM and PCA

Authors:
Yuhui Zhao;Suxia Yu;Bingbing Chu;Nan Zhang;Xin Hu
Affiliations:
Northeastern University at QinHuangdao, Qinhuangdao City, China;Northeastern University at QinHuangdao, Qinhuangdao City, China;Northeastern University at QinHuangdao, Qinhuangdao City, China;Northeastern University at QinHuangdao, Qinhuangdao City, China;Northeastern University at QinHuangdao, Qinhuangdao City, China
Venue:
IScIDE'12 Proceedings of the third Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
Year:
2012

Citing 3
Cited 0

Approximate statistical tests for comparing supervised classification learning algorithms

Neural Computation
Modeling wine preferences by data mining from physicochemical properties

Decision Support Systems
Learning Associative Memories by Error Backpropagation

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Grape varieties have a decisive impact on the quality of the wine, but it still is a difficult problem to differentiate wine quality which is made from the variety of grapes, the paper suggests a grape varieties detection method using principal component analysis (PCA) and Extreme Learning Machine (ELM). Firstly, in order to get a more stable model, the k-fold cross-validation method is used to determine the training data sets and test data sets. Then, the PCA algorithm is adopted to process chemical components of publicly available data sets wine, and lastly classification predict train is performed using the ELM. The train and test experimental results show that the proposed model is better than the separately ELM in the three wine varieties classification ability.