Study on Scale Development of Boolean Medicine Data based on the GA and Improved k-NN Algorithm

The medicine data are Boolean ones in many situations, and the scale development based on them has not been solved soundly, especially the items weight problem. The methods combining GA and k-NN algorithm is often introduced to cope with the problem. But the present improved k-NN algorithm do not adapt to the weight determination of scale's items. A new improve methods named the LO-DFWS-based k-NN algorithm is put forward and presented to reduce the heavy time cost problem of the traditional k-NN, especially for the Boolean data in the paper. The availability of it is demonstrated by the theoretical analysis of the time complexity. And actual data test confirms that the speed is advanced by 2-4 times. The results also show that the new algorithm has a good anti-nose property.

[1]  Huan Liu,et al.  Feature Selection for Classification , 1997, Intell. Data Anal..

[2]  Belur V. Dasarathy,et al.  Nearest neighbor (NN) norms: NN pattern classification techniques , 1991 .

[3]  Rabab Kreidieh Ward,et al.  Genetic algorithms for feature selection and weighting, a review and study , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[4]  F. Gianfelici,et al.  Nearest-Neighbor Methods in Learning and Vision (Shakhnarovich, G. et al., Eds.; 2006) [Book review] , 2008 .

[5]  Wen-Jyi Hwang,et al.  Fast kNN classification algorithm based on partial distance search , 1998 .

[6]  Michael L. Raymer,et al.  GA-facilitated KNN classifier optimization with varying similarity measures , 2005, 2005 IEEE Congress on Evolutionary Computation.

[7]  Xiaopeng Yu,et al.  The Research on An Adaptive K-Nearest Neighbors Classifier , 2006 .

[8]  Qiang Shi,et al.  Optimization of K-NN by feature weight learning , 2005, 2005 International Conference on Machine Learning and Cybernetics.

[9]  Xizhao Wang,et al.  Enhancing Generalization Capability of SVM Classifiers with Feature Weight Adjustment , 2004, KES.

[10]  Jeng-Shyang Pan,et al.  Improved K nearest neighbor classification algorithm , 2004, The 2004 IEEE Asia-Pacific Conference on Circuits and Systems, 2004. Proceedings..