Morlet-RBF SVM model for medical images classification

Authors:
Huiyan Jiang;Xiangying Liu;Lingbo Zhou;Hiroshi Fujita;Xiangrong Zhou
Affiliations:
Software College, Northeastern University, Shenyang, China;Software College, Northeastern University, Shenyang, China;Software College, Northeastern University, Shenyang, China;2Graduate School of Medicine, Gifu University,Yanagido, Gifu, Japan;2Graduate School of Medicine, Gifu University,Yanagido, Gifu, Japan
Venue:
ISNN'11 Proceedings of the 8th international conference on Advances in neural networks - Volume Part II
Year:
2011

Citing 5
Cited 0

Recognition Algorithm Based on Wavelet Transform for Handprinted Chinese Characters

ICPR '98 Proceedings of the 14th International Conference on Pattern Recognition-Volume 1 - Volume 1
An improved SVM method P-SVM for classification of remotely sensed data

International Journal of Remote Sensing
Optimization of SVM Parameters Based on PSO Algorithm

ICNC '09 Proceedings of the 2009 Fifth International Conference on Natural Computation - Volume 01
An identification method of malignant and benign liver tumors from ultrasonography based on GLCM texture features and fuzzy SVM

Expert Systems with Applications: An International Journal
A computer-aided diagnostic system to characterize CT focal liver lesions: design and optimization of a neural network classifier

IEEE Transactions on Information Technology in Biomedicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

Mapping way plays a significant role in Support Vector Machine (SVM). An appropriate mapping can make data distribution in higher dimensional space easily separable. In this paper Morlet-RBF kernel model is proposed. That is, Morlet wavelet kernel is firstly used to transform data, then Radial Basis Function (RBF)is used to map the already transformed data into another higher space. And particle swarm optimization (PSO) is applied to find best parameters in the new kernel. Morlet-RBF kernel is compared with Mexican-Hat wavelet kernel and RBF kernel. Experimental results show the feasibility and validity of this new mapping way in classification of medical images.