A Multi-Classified Method of Support Vector Machine (SVM) Based on Entropy

Yan Yue

doi:10.4028/www.scientific.net/AMM.241-244.1629

Paper Titles

Finite-Time H_∞ Consensus of Multi-Agent Systems with a Leader
p.1608

Human Ear Recognition Based on Phase Congruency and Kernel Discriminant Analysis
p.1614

Research on Parameters Optimization Algorithm in Support Vector Machine Based on Immune Memory Clone Strategy
p.1618

Study on Path Based Hierarchy Aggregation in DS-TE Environment
p.1622

A Multi-Classified Method of Support Vector Machine (SVM) Based on Entropy
p.1629

Research on Interactive Visualization Clustering Method Based on the Radar Chart
p.1633

Stressed Speech Recognition Method Based on Difference Subspace Combined with Dynamic Time Warping
p.1640

A Novel Technology in Surveillance Video for Detecting and Forecasting a Robbing Incident
p.1647

Illumination Invariant Face Recognition Using Nonlocal Total Variation in Logarithmic Domain
p.1652

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 241-244A Multi-Classified Method of Support Vector...

A Multi-Classified Method of Support Vector Machine (SVM) Based on Entropy

Abstract:

Studies propose to combine standard SVM classification with the information entropy to increase SVM classification rate as well as reduce computational load of SVM testing. The algorithm uses the information entropy theory to per-treat samples’ attributes, and can eliminate some attributes which put small impacts on the date classification by introducing the reduction coefficient, and then reduce the amount of support vectors. The results show that this algorithm can reduce the amount of support vectors in the process of the classification with support vector machine, and heighten the recognition rate when the amount of the samples is larger compared to standard SVM and DAGSVM.