Zhang S.,Nanyang Institute of Technology
RISTI - Revista Iberica de Sistemas e Tecnologias de Informacao | Year: 2016
In fact, there are a large number of incomplete data, and these data are mostly contained in a serious impact on the classification efficiency and efficiency of the redundant and irrelevant attributes. However, due to the complexity of processing incomplete data, the selective classification algorithm for incomplete data is very rare at present. In addition, with the continuous development of modern information technology, a large number of high dimensional data are emerging. Naive Bayesian is simple and efficient, suitable for processing high dimensional data, but also very sensitive to the choice of attributes. Therefore, it is significant to study the selective Bias classification algorithm for high dimensional data. The redundant or irrelevant attributes of incomplete data can not only reduce the classification efficiency but also can seriously damage the classification effect. Based on the packing method, two selective incomplete data classifiers are proposed. First, the classification effect is more prominent than the incomplete data classifier RBC and search results are good and the relative low complexity of the best pre search method, and a selective incomplete data classifier SRBC was constructed. Through experiments, compared with the efficient RBC and DBCI, SRBC can not only obtain significantly higher classification accuracy, but also significantly reduce the number of redundant and irrelevant attributes.
Xing J.,Nanyang Institute of Technology
Xitong Gongcheng Lilun yu Shijian/System Engineering Theory and Practice | Year: 2010
Based on the quantitative description of group split, first of all, this article defined the concept and the judging method for the splitting effectiveness of sample units, analyzed their economic connotative meaning, and discussed the relationship between the splitting effective unit and Pareto effective solution; And then, provided the measurement solution to the overall efficiency of splitting units and the methods to optimize the splitting efficiency; Finally, applied the method to the simulation of enterprise strategic split.
Ding W.,Nanyang Institute of Technology
Procedia Engineering | Year: 2011
The blind source separation (BSS) algorithms, especially the independent component analysis (ICA) algorithms, have been proven to be effective for the image data processing. The noise signal introduced into the image data can be perfectly eliminated using ICA only under the linear mixture condition. However, the images are always mixed nonlinearly with noise perturbations. The traditional linear ICA algorithm is not capable enough to suppress the noise in this situation. Hence, the nonlinear ICA is proposed to deal with the nonlinear mixtures in this paper. The radial basis function (RBF) neural network based post-nonlinear ICA algorithm has been adopted to remove noise from the original image data. To enhance the RBF-ICA operation, the Chaos-Particle Swarm Optimization (PSO) algorithm has been employed to optimize the RBF neural network to obtain satisfactory nonlinear solution of the nonlinear BBS procedure. A series of experiments have been implemented in this work to validate the efficiency of the proposed method. The Chaos-PSO optimized RBF-ICA model has been compared with other ICA models in the image de-noising processing. The comparative results show that the proposed approach is superior to the nonoptimized ICA methods with respect to the image de-noising performance. © 2011 Published by Elsevier Ltd.
Liu P.,Nanyang Institute of Technology
Sensors and Transducers | Year: 2014
The article introduces against technical defects of traditional network access control system, detail NAC, NAP, UAC and TNC four kinds of new network security access technology, and this article analyzes and compares them. Security framework for wireless sensor networks SPINS defines the mechanism and algorithm of complete and effective in confidentiality, point-to-point message authentication, integrity, authentication, broadcast authentication. © 2014 IFSA Publishing, S. L.
Xing J.,Nanyang Institute of Technology
Xitong Gongcheng Lilun yu Shijian/System Engineering Theory and Practice | Year: 2011
Based on resource sharing, to solve the problem that sample data envelopment analysis methods can not provide evaluating information by a determinate frontier and can not breakthrough the comparability restriction of decision-making units, a broad sample DEA method with restrain cone (PU-C 2WH) for evaluating alliance efficiency is provided by using some sample units. At the same time, the definitions of alliance efficiency and weak alliance efficiency are developed. The relationship between alliance efficiency and the relevant multiple objective programming non-dominated solution is studied. The properties on projection and efficiency improvement of decision making units are studied, In addition, it provides the measurement solution to the overall efficiency of alliance units and evaluation steps. Lastly, it applies the method to the simulation application.