Multiple binary decision tree classifiers

https://doi.org/10.1016/0031-3203(90)90098-6Get rights and content

Abstract

Binary decision trees based on nonparametric statistical models of the data provide a solution to difficult decision problems where there are many classes and many available features related in a complex manner. Unfortunately, the technique requires a very large training set and is often limited by the size of the training set rather than by the discriminatory power of the features. This paper demonstrates that higher classification accuracies can be obtained from the same training set by using a combination of decision trees and by reaching a consensus using Dempster and Shafer's theory of evidence.

References (32)

  • Q.R. Wang et al.

    Analysis and design of a decision tree and its applications to large character set recognition

    IEEE Trans. Pattern Anal. Mach. Intell. PAMI-6

    (1984)
  • Q.R. Wang et al.

    Large tree classifier with heuristic search and global training

    IEEE Trans. Pattern Anal. Mach. Intell. PAMI-9

    (1987)
  • K.C. You et al.

    An approach to the design of a linear binary tree classifier

  • J.K. Mui et al.

    Automated classification of nucleated blood cells using a binary tree classifier

    IEEE Trans. Pattern Anal. Mach. Intell. PAMI-2

    (1980)
  • G.H. Landerweed et al.

    Binary tree versus single level tree classification of white blood cells

    Pattern Recognition

    (1983)
  • K.S. Fu

    Sequential Methods in Pattern Recognition and Machine Learning

    (1968)
  • Cited by (45)

    • AutoML-GWL: Automated machine learning model for the prediction of groundwater level

      2024, Engineering Applications of Artificial Intelligence
    • A survey of multiple classifier systems as hybrid systems

      2014, Information Fusion
      Citation Excerpt :

      Fuser weight selection can be treated as a specific learning process [31,136]. Shlien [150] used Dempster and Shafer’s theory to reach a consensus on the weights to combine decision trees. Wozniak [151] trained the fuser using perceptron-like learning, evolutionary algorithm [152,153].

    • Shape matching using a binary search tree structure of weak classifiers

      2012, Pattern Recognition
      Citation Excerpt :

      Many applications, such as visual surveillance or pedestrian detection systems have real-time constraints, thus the template search speed is vital to the viability of such a system. While binary decision trees have been employed for shape related tasks, these attempts mostly considered shape classification based on the presence or absence of features [25], or feature extraction for classification purposes [2]. A tree of weak classifiers has also been proposed in [8] for a sports pictures classification system.

    View all citing articles on Scopus
    View full text