Discovering regression data quality through clustering methods

Authors:
Dario Malchiodi;Simone Bassis;Lorenzo Valerio
Affiliations:
University of Milan, Department of Computer Science, Via Comelico 39/41, 20135 Milan, Italy, {malchiodi,bassis,valerio}@dsi.unimi.it;University of Milan, Department of Computer Science, Via Comelico 39/41, 20135 Milan, Italy, {malchiodi,bassis,valerio}@dsi.unimi.it;University of Milan, Department of Computer Science, Via Comelico 39/41, 20135 Milan, Italy, {malchiodi,bassis,valerio}@dsi.unimi.it
Venue:
Proceedings of the 2009 conference on New Directions in Neural Networks: 18th Italian Workshop on Neural Networks: WIRN 2008
Year:
2009

Citing 9
Cited 1

Practical methods of optimization; (2nd ed.)

Practical methods of optimization; (2nd ed.)
Support vector domain description

Pattern Recognition Letters - Special issue on pattern recognition in practice VI
Density-Based Clustering in Spatial Databases: The Algorithm GDBSCAN and Its Applications

Data Mining and Knowledge Discovery
Support vector clustering

The Journal of Machine Learning Research
Designing committees of models through deliberate weighting of data points

The Journal of Machine Learning Research
Estimating the Support of a High-Dimensional Distribution

Neural Computation
Clustering Using a Similarity Measure Based on Shared Near Neighbors

IEEE Transactions on Computers
Modern Regression Methods

Modern Regression Methods
A modified SVM classification algorithm for data of variable quality

KES'07/WIRN'07 Proceedings of the 11th international conference, KES 2007 and XVII Italian workshop on neural networks conference on Knowledge-based intelligent information and engineering systems: Part III

An experimental analysis of the impact of accuracy degradation in SVM classification

International Journal of Computational Intelligence Studies

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose the use of clustering methods in order to discover the quality of each element in a training set to be subsequently fed to a regression algorithm. The paper shows that these methods, used in combination with regression algorithms taking into account the additional information conveyed by this kind of quality, allow the attainment of higher performances than those obtained through standard techniques.