Dissertation > Excellent graduate degree dissertation topics show

Multiclassification Method Research Based on Fuzzy Support Vector Machines

Author: YangJie
Tutor: HuBaoQing
School: Wuhan University
Course: Computational Mathematics
Keywords: Statistical Learning Theory Support Vector Machines Multiclassification Fuzzy Membership Fuzzy Support Vector Machines
CLC: O241
Type: Master's thesis
Year: 2005
Downloads: 647
Quote: 8
Read: Download Dissertation

Abstract


Statistical Learning Theory is for small samples machine learning, and SVMs (Support Vector Machines) proposed by Vapnik are based on this theory. SVMs have great generalizability and pursue the best result through limited information. Because of the replacement of ERM (Empirical risk minimization) by SRM (Structural Risk Minimization), SVMs have a firm theoretic base; because of the use of kernel functions, SVMs transform non-linear problem to linear problem, so reduce the complexity of algorithm. Now SVMs behave well in comparison with ANN, GA, and this method is studied in many fields such as handwritten numerals recognition, face recognition, texture classification.Multiclassification is a branch of machine learning. SVMs were originally proposed for 2-classification, so people extended this method to meet multiclassification. Furthermore in some practical issues, the margin between classes is not clear, so FSVMs (Fuzzy Suppport Vector Machines) are given. For different purposes, there is mainly two methods based on FSVMs. In this paper, the author analyses these two methods in detail, gives advanced algorithms based on FSVMs and does some experiments to approve them. The two methods are listed as follow:One was given to resolve unclassifiable regions in one-aganist-one and one-against-all SVMs by Takuga and Shigeo. In this paper, An advanced model is proposed to keep coherence of all multiclassification methods.The other is given to incarnate different influence of samples and reduce the influence of noisy data by Chun-Fu Liu, Sheng-De Wang, Han-Pang Huang. In this paper. The author proposes a combination of this method and one-against-all rule to get a more generalizable algorithm.Through expeiments, the algorithms proposed in this paper get more remarkable results.

Related Dissertations

  1. Research on the Classification Based on the Reconstruction of Solder Joint,TP391.41
  2. Research on Predicting Intrinsic Disorder Protein Structure Based on Supervision Manifold Learning Algorithm,Q51
  3. Design and Implementation on the Text Classifier Based on Support Vector Machine,TP391.1
  4. The Research of Support Vector Machine Incremental Learning Algorithms,TP18
  5. Research Remote Image Classification Based on Support Vector Machine,P237
  6. Study of the Density Function Corresponding with Support Vector Regression Machine,O174
  7. Improved SVM and Its Applications in Prediction of Silicon Content in Hot Metal,TF325.69
  8. The deformation forecasting method based on support vector machine studies,TU196.1
  9. Study of Support Vector Machine Algorithms on Unbalanced Dataset,TP18
  10. Research on Modeling Method of Support Vector Machine,TP18
  11. The Forecasting Based on Support Vector Machine and Its Application in the Empirical Analysis of China’s Urban Unemployment Rate,TP18
  12. Static Damage Identification of Long-Span Cable-Stayed Bridge Based on Support Vector Machines,U441.4
  13. Research on Face Recognition Based on DCT and SVM,TP391.41
  14. The Research and the Application of the Fuzzy Support Vector Machines,O159
  15. Pattern Recognition Based on Discriminative Common Vectors,TP391.41
  16. Rule-based and statistical study of Chinese Automatic Segmentation,TP391.1
  17. Research on Application of Least Square Support Vector Machines and Unscented Kalman Filter in State Estimation,TM73
  18. Abnormal Condition Detection and Intelligent Decision of Shield Machine Process,U455.43
  19. Virtual fitting skirt semicircle shape SVM Classification Based on fabric,TS941.4
  20. Emotion Research Based on Facial Expression Recognition,TP391.41
  21. Research on Identification Method Based on Palmprint and Hand Shape Biometric,TP391.41

CLC: > Mathematical sciences and chemical > Mathematics > Computational Mathematics > Numerical Analysis
© 2012 www.DissertationTopic.Net  Mobile