Ruta, D. and Gabrys, B., 2003. Physical field models for pattern classification. Soft Computing, 8 (2), pp. 126-141.
Full text not available from this repository.
Official URL: http://www.springerlink.com/content/v7yv0kyej3rbh6...
Recent findings in pattern recognition show that dramatic improvement of the recognition rate can be obtained by application of fusion systems utilizing many different and diverse classifiers for the same task. Apart from a good individual performance of individual classifiers the most important factor is the useful diversity they exhibit. In this work we present an example of a novel, well performing non-parametric classifier design, which shows a substantial level of diversity with respect to other commonly used classifiers. Inspired by the mechanics of omnipresent physical fields like gravitational or electrostatic, we considered the data as particles carrying elementary units of charge. The charge has been presented as a source of the potential triggering attracting interaction among the data. This interaction has been reformulated as data matching procedure and developed into original classification technique where the unlabelled testing data are captured by the labelled training data and share their labels. In the extended model apart from the spatial data distribution we also exploit topology of class labels to devise repelling force as field action between differently labelled data samples. As we show introduction of the repelling force clearly smoothes the decision boundaries and improves performance while still preserving attractive diversity properties of the classification model. The paper covers extensive examples and visual interpretations of the presented techniques supported by the experimental work with established datasets and classifiers.
|Additional Information:||This paper forms a departure from the classical approaches to designing pattern classification systems and explores the metaphor between physical particles and data items. Designing the learning process on grounds of physical interactions among the particles is one of the most fruitful inspirations of physical phenomena for the machine learning domain. It is consciously or unconsciously being exploited in well known kernel machines methodology and very popular data density estimation methods. What is surprising however is the scarcity of physically inspired models in classification, clustering and regression methods which are becoming increasingly popular in the upcoming data mining age of business analytics. Authors' pioneering efforts into devising new classification, clustering and data condensation algorithms based on various potential fields found in nature confirm there is a huge potential for improving the performance of current predictive models as illustrated in this publication and others that followed in the last two years.|
|Uncontrolled Keywords:||Pattern recognition, fusion systems, pattern classification, classifier|
|Subjects:||Science > Physics|
Generalities > Computer Science and Informatics > Artificial Intelligence
Generalities > Computer Science and Informatics
|Group:||School of Design, Engineering & Computing > Smart Technology Research Centre|
|Deposited By:||INVALID USER|
|Deposited On:||17 Dec 2007|
|Last Modified:||07 Mar 2013 14:36|
|Repository Staff Only -|
|BU Staff Only -|
|Help Guide -||Editing Your Items in BURO|