This letter adopts a GA (Genetic Algorithm) approach to assist in learning scaling of features that are most favorable to SVM (Support Vector Machines) classifier, which is named as GA-SVM. The relevant coefficients o...This letter adopts a GA (Genetic Algorithm) approach to assist in learning scaling of features that are most favorable to SVM (Support Vector Machines) classifier, which is named as GA-SVM. The relevant coefficients of various features to the classification task, measured by real-valued scaling, are estimated efficiently by using GA. And GA exploits heavy-bias operator to promote sparsity in the scaling of features. There are many potential benefits of this method:Feature selection is performed by eliminating irrelevant features whose scaling is zero, an SVM classifier that has enhanced generalization ability can be learned simultaneously. Experimental comparisons using original SVM and GA-SVM demonstrate both economical feature selection and excellent classification accuracy on junk e-mail recognition problem and Internet ad recognition problem. The experimental results show that comparing with original SVM classifier, the number of support vector decreases significantly and better classification results are achieved based on GA-SVM. It also demonstrates that GA can provide a simple, general, and powerful framework for tuning parameters in optimal problem, which directly improves the recognition performance and recognition rate of SVM.展开更多
[Objective] The research aimed to clarify the genetic mechanism of special wide compatibility of GC13.[Method] The clustering analyses of GC13,five indica,five japonica and five wide compatibility varieties were carri...[Objective] The research aimed to clarify the genetic mechanism of special wide compatibility of GC13.[Method] The clustering analyses of GC13,five indica,five japonica and five wide compatibility varieties were carried out by using 70 SSR primers.[Result] GC13 was clustered into japonica group and had far genetic relationship with indica and wide compatibility variety.Two fertility loci were detected in GC13,in which one closely linked to RM225 on chromosome 6.According to the position on the chromosome,it speculated that this locus was allelic to S5.GC13 carried the allelic gene S5-n at this locus.The other locus closely linked to RM408 on chromosome 8 and was provisionally designated as Sg(t).At this locus,GC13 carried Sg(t)-i allelic gene,which was consistent with IR36.The effect of S5 locus was stronger than that of Sg(t).[Conclusion] The research laid the good foundation for using the wide compatibility line GC13 to breed the hybrid between subspecies.展开更多
基金Supported by the National Natural Science Foundation of China (No.60175020) the National High Tech Development '863' Program of China (No.2002AA117010-09).
文摘This letter adopts a GA (Genetic Algorithm) approach to assist in learning scaling of features that are most favorable to SVM (Support Vector Machines) classifier, which is named as GA-SVM. The relevant coefficients of various features to the classification task, measured by real-valued scaling, are estimated efficiently by using GA. And GA exploits heavy-bias operator to promote sparsity in the scaling of features. There are many potential benefits of this method:Feature selection is performed by eliminating irrelevant features whose scaling is zero, an SVM classifier that has enhanced generalization ability can be learned simultaneously. Experimental comparisons using original SVM and GA-SVM demonstrate both economical feature selection and excellent classification accuracy on junk e-mail recognition problem and Internet ad recognition problem. The experimental results show that comparing with original SVM classifier, the number of support vector decreases significantly and better classification results are achieved based on GA-SVM. It also demonstrates that GA can provide a simple, general, and powerful framework for tuning parameters in optimal problem, which directly improves the recognition performance and recognition rate of SVM.
基金Supported by Guangxi Natural Science Fund Item(2010GXNSFD013035)Guangxi Science Fund Item(Guikeqing0832063)+1 种基金Guangxi Science Research and Technology Development Planning Item(Guikegong1123001-3C)National Science and Technology Support Planning Item(2007BAD68B01)
文摘[Objective] The research aimed to clarify the genetic mechanism of special wide compatibility of GC13.[Method] The clustering analyses of GC13,five indica,five japonica and five wide compatibility varieties were carried out by using 70 SSR primers.[Result] GC13 was clustered into japonica group and had far genetic relationship with indica and wide compatibility variety.Two fertility loci were detected in GC13,in which one closely linked to RM225 on chromosome 6.According to the position on the chromosome,it speculated that this locus was allelic to S5.GC13 carried the allelic gene S5-n at this locus.The other locus closely linked to RM408 on chromosome 8 and was provisionally designated as Sg(t).At this locus,GC13 carried Sg(t)-i allelic gene,which was consistent with IR36.The effect of S5 locus was stronger than that of Sg(t).[Conclusion] The research laid the good foundation for using the wide compatibility line GC13 to breed the hybrid between subspecies.
