Screening Paper Runnability in a Web-Offset Pressroom by Data Mining

Authors:
A. Alzghoul;A. Verikas;M. Hållander;M. Bacauskiene;A. Gelzinis
Affiliations:
Intelligent Systems Laboratory, Halmstad University, Halmstad, Sweden S-30118;Intelligent Systems Laboratory, Halmstad University, Halmstad, Sweden S-30118 and Kaunas University of Technology, Kaunas, Lithuania LT-51368;Intelligent Systems Laboratory, Halmstad University, Halmstad, Sweden S-30118;Kaunas University of Technology, Kaunas, Lithuania LT-51368;Kaunas University of Technology, Kaunas, Lithuania LT-51368
Venue:
ICDM '09 Proceedings of the 9th Industrial Conference on Advances in Data Mining. Applications and Theoretical Aspects
Year:
2009

Citing 8
Cited 0

GTM: the generative topographic mapping

Neural Computation
Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control and Artificial Intelligence

Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control and Artificial Intelligence
Kernel Methods for Pattern Analysis

Kernel Methods for Pattern Analysis
Increasing the discrimination power of the co-occurrence matrix-based features

Pattern Recognition
Application of a modified neural fuzzy network and an improved genetic algorithm to speech recognition

Neural Computing and Applications
A Nonlinear Mapping for Data Structure Analysis

IEEE Transactions on Computers
A feature selection technique for generation of classification committees and its application to categorization of laryngeal images

Pattern Recognition
Curvilinear component analysis: a self-organizing neural network for nonlinear mapping of data sets

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper is concerned with data mining techniques for identifying the main parameters of the printing press, the printing process and paper affecting the occurrence of paper web breaks in a pressroom. Two approaches are explored. The first one treats the problem as a task of data classification into "break " and "non break " classes. The procedures of classifier design and selection of relevant input variables are integrated into one process based on genetic search. The search process results in a set of input variables providing the lowest average loss incurred in taking decisions. The second approach, also based on genetic search, combines procedures of input variable selection and data mapping into a low dimensional space. The tests have shown that the web tension parameters are amongst the most important ones. It was also found that, provided the basic off-line paper parameters are in an acceptable range, the paper related parameters recorded online contain more information for predicting the occurrence of web breaks than the off-line ones. Using the selected set of parameters, on average, 93.7% of the test set data were classified correctly. The average classification accuracy of the break cases was equal to 76.7%.