In the field of pattern recognition, more specifically in the area of supervised and feature-vector-based classifications, various classification methods exist but none of them can return always right results for any given kind of data. Each classifier behaves differently, having its own strengths and weaknesses. Some are more efficient then others in particular situations. The performance of these individual classifiers can be improved by combining them into one multiple classifier. In order to make more realistic decisions, the multiple classifier can analyze internal values generated by each classifier and can also rely on statistics learned from previous tests, such as reliability rates and confusion matrix. Individual classifiers studied in this project are Bayes, k-nearest neighbors, and neural network classifiers. They are combined using the Dempster-Shafer (1967, 1976) theory. The problem simplifies in finding weights that best represent individual classifier evidences. A particular approach has been developed for each of them, and for all of them it has been proven better to rely on classifiers internal information rather than statistics. When tested on a database comprised of 8 different kinds of military ships, represented by 11 features extracted from FLIR images, the resulting multiple classifier has given better results than others reported in the literature and tested in this work.


    Access

    Access via TIB

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    New initial basic probability assignments for multiple classifiers


    Contributors:
    Rheaume, F. (author) / Jousselme, A.L. (author) / Grenier, D. (author) / Bosse, E. (author) / Valin, P. (author)


    Publication date :

    2002


    Size :

    10 Seiten, 9 Quellen




    Type of media :

    Conference paper


    Type of material :

    Print


    Language :

    English




    Optimization of multiple objective gate assignments

    Yan, Shangyao | Online Contents | 2001


    Learning classifiers from imbalanced data based on biased minimax probability machine

    Kaizhu Huang, / Haiqin Yang, / King, I. et al. | IEEE | 2004


    Learning Classifiers from Imbalanced Data Based on Biased Minimax Probability Machine

    Huang, K. / Yang, H. / King, I. et al. | British Library Conference Proceedings | 2004


    UAV cooperative multiple task assignments using genetic algorithms

    Shima, T. / Rasmussen, S.J. / Sparks, A.G. | Tema Archive | 2005


    Combination of Multiple Classifiers for Handwritten Word Recognition

    Wang, W. / Brakensiek, A. / Rigoll, G. | British Library Conference Proceedings | 2002