A hybrid approach to outlier detection in the offset lithographic printing process

Authors:
C. Englund;A. Verikas
Affiliations:
Intelligent Systems Laboratory, School of Information Science, Computer and Electrical Engineering, Halmstad University, Box 823, S 30118 Halmstad, Sweden;Intelligent Systems Laboratory, School of Information Science, Computer and Electrical Engineering, Halmstad University, Box 823, S 30118 Halmstad, Sweden and Department of Applied Electronics, Ka ...
Venue:
Engineering Applications of Artificial Intelligence
Year:
2005

Citing 11
Cited 2

Robust regression and outlier detection

Robust regression and outlier detection
On ordered weighted averaging aggregation operators in multicriteria decisionmaking

IEEE Transactions on Systems, Man and Cybernetics
Unsupervised Optimal Fuzzy Clustering

IEEE Transactions on Pattern Analysis and Machine Intelligence
Process drift control in lithographic printing: issues and a connectionist expert system approach

Computers in Industry
Process modelling and fault diagnosis using fuzzy neural networks

Fuzzy Sets and Systems - Special issue on neuro-fuzzy techniques and applications
About the use of fuzzy clustering techniques for fuzzy model identification

Fuzzy Sets and Systems
Outliers detection and confidence interval modification in fuzzy regression

Fuzzy Sets and Systems
Findout: finding outliers in very large datasets

Knowledge and Information Systems
Local overfitting control via leverages

Neural Computation
Generalized OWA Aggregation Operators

Fuzzy Optimization and Decision Making
Clustering algorithms based on volume criteria

IEEE Transactions on Fuzzy Systems

CPBUM neural networks for modeling with outliers and noise

Applied Soft Computing
Concept drift detection via competence models

Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Artificial neural networks are used to model the offset printing process aiming to develop tools for on-line ink feed control. Inherent in the modelling data are outliers owing to sensor faults, measurement errors and impurity of materials used. It is fundamental to identify outliers in process data in order to avoid using these data points for updating the model. We present a hybrid, the process-model-network-based technique for outlier detection. The outliers can then be removed to improve the process model. Several diagnostic measures are aggregated via a neural network to categorize data points into the outlier and inlier classes. We demonstrate experimentally that a soft fuzzy expert can be configured to label data for training the categorization of neural network.