Dissertation > Excellent graduate degree dissertation topics show

An Improved Classification Algorithm of SVM for Learning Unbalanced Datasets

Author: YaoBing
Tutor: ZhangZongSheng
School: Jilin University
Course: Network and Information Security
Keywords: SMOIS algorithm Support Vector Machine Shell vector Imbalanced data sets Text Classification
CLC: TP311.13
Type: Master's thesis
Year: 2010
Downloads: 140
Quote: 1
Read: Download Dissertation

Abstract


The classification problem is one of the important contents of the data mining field of heavy research , some of the existing classification methods have been relatively mature , and has achieved good results on the classification of the balance datasets . But real life data sets are often unbalanced , and that certain types of data set the sample size is much larger than the number of samples of the other classes . The traditional classification algorithms to solve the problem of unbalanced data sets classification ability is limited , the classification problems in imbalanced data sets need to seek new discrimination method and classification criteria . The papers for the deficiencies of the traditional classification algorithms , Algorithm and enhance the practicality of the algorithm in both directions to expand in-depth study of the system . Made two key improvements ; existing classification algorithm based on the reconstruction of unbalanced data sets at the data level , the algorithm level , the reconstructed data sets and support vector machine - based classification method combine based the shell vector and SMOIS of algorithm support vector classification algorithm SHS (SVM classification algorithm for imbalanced datasets based on SMOIS and convex hull). The main work and conclusions are as follows : (1 ) improved SMOIS algorithm by reference the shell vector mechanism and a small number of categories like space to copy to adjust the proportion of minority class samples and samples of most categories dataset , to reduce the imbalance of the data set . (2) SHS the algorithm instance verify the selection of the the Institute of lexical analysis systems ICTCLAS corpus , a total of 751 documents, involving the environment , computers, medical category . The experiments show that the traditional classification algorithms , SHS algorithm to reduce the size of the training samples to improve the classification rate of the large-scale text data sets , especially the imbalance text data set , the algorithm is more obvious advantages .

Related Dissertations

  1. Research on Automatic Detection Algorithm for Substructure Distress of Highway Pavement Based on SVM,U418.6
  2. Research on Autamatic Music Structrue Analysis,TN912.3
  3. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  4. Research on Text Classification Based on Biomimetic Pattern Recongnition,TP391.1
  5. Tourism Comments on the Internet’s Semantic Analysis and Usefulness Research,TP391.1
  6. Fault Diagnosis Method Based on Support Vector Machine,TP18
  7. Process Support Vector Machine and Its Application to Satellite Thermal Equilibrium Temperature Prediction,TP183
  8. Research for Infrared Image Target Identification and Tracking Technology,TP391.41
  9. Study on the Road Condition Monitoring Based on Vehicular 3D Acceleration Sensor,TP274
  10. Research of Diagnosing Cucumber Diseases Based on Hyperspectral Imaging,S436.421
  11. Based on Data Distribution Characteristics of Text Classification,TP391.1
  12. The Research on Intrusion Detection System Based on Machine Learning,TP393.08
  13. Research on Improved K Neighbor Support Vector Machine Algorithm Faced Text Classification,TP391.1
  14. Research on Face Recognition Based on AdaBoost Algorithm,TP391.41
  15. Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
  16. Research on Subimage Selection and Mathching Method for Synthetic Aperture Radar(SAR) Target Recognition,TN957.52
  17. Research of Facial Expression Recognition Algorithm,TP391.41
  18. Fundus Image Segmentation Based on SVM and Template Matching,TP391.41
  19. Research and Realization of License Plate Character Recognition Algorithm Based on SVM,TP391.41
  20. Cloud Classification Based on Geostationary Meteorological Satellite Imagery,TP391.41
  21. The Studies on Some Improvements of the GA and Their Applications in SVM,TP18

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer software > Program design,software engineering > Programming > Database theory and systems
© 2012 www.DissertationTopic.Net  Mobile