An Improving Mulit-category Classification Method Based on the Binary Tree Support Vector Machine
Journal Title: Scholars Journal of Engineering and Technology - Year 2017, Vol 5, Issue 3
Abstract
Aiming at the problems of the slow convergence speed of general partial binary tree support vector machine (SVM) classifier and the fault samples easy to accumulate caused by complete binary tree and partial binary tree SVM classifier. The thesis proposes a multi-category classification method based on the unbalanced binary tree support vector machine (SVM),which construct a unbalanced binary tree SVM, making the easy to distinguish category can split out step by step from the root node, and reducing the accumulated errors caused by previous classification by analyzing the distribution of sample space. The results show that, comparing this method with the method of complete- and partial-binary tree ,an unbalanced binary tree SVM built in this paper has a strong ability of autonomous learning, and can easily distinguish separate classes first, thus improving classification accuracy. Keywords: binary tree; support vector machine; lustering analysis; many kinds of points; pattern recognition.
Authors and Affiliations
BU Qing-chao
Keywords
Related Articles
- EP ID EP386266
- DOI -
- Views 75
- Downloads 0
Implementation of Data Warehousing in Telecommunication Companies in Rwanda: A Survey of MTN in Gasabo District and Tigo in Nyarugenge District
The study was to investigate the implementation of data warehouse at selected telecommunication companies in Rwanda (MTN and Tigo) and the objectives were to identify the key factors that lead to successful implementati...
The Influence of Angkak Treatment on Physical, Chemical and Organoleptical Characteristics of the Castoff Duck Meat Sausage
Abstract: This research is aimed to understand the influence of angkak as curing material and natural color maker on physical and chemical characteristics and also on organoleptical test of castoff duck meat sausage, in...
Estimation Model of Functional Stability of the Local Computer Network
Research existing scientifically grounded approaches to improving the efficiency of complex technical systems, which fully applies to local computer network, allowed to conclude about the formation in recent years a new...
Research on the Mechanism of Viscoelastic Emulsion Flooding
Chemical flooding adopts polymer to realize flow control generally. But section inversion is serious in the late injection and polymer is easily to block oil layers, compounding the difficulty of chemical flooding. In-ho...
Hand Written Circuit Schematic Recognition
Circuit drawing is an important task especially in undergraduate courses such as electronics and digital systems. To improve human computer interaction, we have developed recognition system for the hand written circuit a...