期刊名称：International Journal of Signal Processing, Image Processing and Pattern Recognition
印刷版ISSN：2005-4254
出版年度：2016
卷号：9
期号：10
页码：377-386
出版社：SERSC
摘要：In order to increase the recognition rate of the CT image of benign ormalignant pulmonary nodules, Support vector machine(SVM)was adopted to classify them. Meanwhile,Particle swarm optimization(PSO) algorithmis used to optimize parameters of the kernel functionof SVM. Various optimizationresults wereacquired through multiple methods such as consistent inertiaweight, linear decreasing inertiaweight, first increasing and then decreasing inertiaweightand non-linear decreasing inertiaweight. As was provedby experiments, recognition rates of these methods in training set werethe same. The method with consistent inertiaweighthada short optimizing time, but recognition rate in test set was low. The remaining methods hada long optimizing time while recognition effects were better in test set.
