Zhang M.,Henan University of Economics and Law |
Li G.,North China University of Water Conservancy and Electric Power
Journal of Convergence Information Technology | Year: 2012
Classification of intrusion attacks is a challenging problem in network security. In order to improve the classification accuracy of traditional intrusion detection methods, a novel intrusion detection technology by combining least squares support vector machine and chaos particle swarm optimization (CPSO-LSSVM) is proposed in the paper. Least squares support vector machine (LSSVM) is a popular pattern classification method with many diverse applications. However, the choice of the training parameters of least squares support vector machine has a heavy impact on its classification accuracy. Chaos particle swarm optimization is an evolutionary computation technique,which is better than particle swarm optimization algorithm.Thus, this study introduces CPSO as an optimization technique to simultaneously optimize the training parameter of LSSVM. The experimental results demonstrate that the proposed CPSO-LSSVM model has detection accuracy than other classifiers.
XiaoXue L.,Henan University of Economics and Law
International Journal of Advancements in Computing Technology | Year: 2011
Peer-to-peer (P2P) networking is more and more widely used in many fields, such as exchange, contribute, or obtain files from any users of the internet. It's also a convenient environment for worms, viruses to find an easy way to attack other users from network. Therefore, a domain pool trust model for P2P networks is presented in this paper to represent the trust model among peers because they may from different domain pools. In this model, every peer belongs to a domain pool, which is marked by different hierarchy and category. The trust reputation value is based on which domain pool they belong to. What's more, a domain feedback algorithm is designed to filter selfish and fake peers. Finally, after simulation experiment in Query Cycle Simulator, it shows the domain pool trust model can get available peers effectively and against fake ones.
Zhao Y.,CAS Academy of Mathematics and Systems Science |
Li Z.,CAS Academy of Mathematics and Systems Science |
Li Z.,Henan University of Economics and Law |
Cheng D.,CAS Academy of Mathematics and Systems Science
IEEE Transactions on Automatic Control | Year: 2011
This paper considers the infinite horizon optimal control of logical control networks, including Boolean control networks as a special case. Using the framework of game theory, the optimal control problem is formulated. In the sight of the algebraic form of a logical control network, its cycles can be calculated algebraically. Then the optimal control is revealed over a certain cycle. When the games, using memory μ> 1 (which means the players only consider previous μ steps' action at each step), are considered, the higher order logical control network is introduced and its algebraic form is also presented, which corresponds to a conventional logical control network (i.e., μ = 1). Then it is proved that the optimization technique developed for conventional logical control networks is also applicable to this μ-memory case. © 2010 IEEE.
Wang J.,Henan University of Economics and Law
International Review on Computers and Software | Year: 2012
With the development of the cloud computing technology, more and more companies are willing to apply this technology. When our private data are out-sourced in cloud computing, we should guarantee the confidentiality and searchability of the sensitive data. However, nowadays privacy preserving issues in the cloud have not been carefully explored at current stage. To relieve individuals' concerns of their data privacy, this paper explores an effective algorithm based on privacy protocol and min-attribute generalization to avoid the disclosure of private information in the cloud environment. This paper also provides security analysis and experimental evaluation for the proposed algorithm. © 2012 Praise Worthy Prize S.r.l.
Wang C.,Henan University of Economics and Law
Computers in Human Behavior | Year: 2014
This paper examines the antecedents and consequences of perceived value in m-government continuance use. Drawing upon service science studies and Chinese m-government context, a research model is constructed by extending the technology acceptance model (TAM). Data collected from a field survey of 326 m-government users are analyzed to test the proposed hypotheses. The results indicate that perceived value is strongly influenced by mobility, perceived usefulness and security, which is, in turn, significant impact on satisfaction and trust in technology, trust in agent and trust in government. These results contribute to drawing attention to the important role of perceived value in m-government continuance use and providing a new view that supplements to the extant technology acceptance research. © 2014 Elsevier Ltd. All rights reserved.
Guo Q.,Henan University of Economics and Law
Advances in Information Sciences and Service Sciences | Year: 2012
This paper would study the DSR routing technology based on multiple description coding and communication distance between nodes in vehicle ad hoc network. This routing technology based on routing protocol DSR, aims to cope with the characteristics of dynamic network topology, high-speed motion of vehicle, unpredictable direction and speed of vehicle in vehicle ad hoc network. This technology improves the discovery and reply process of DSR route through multiple description coding technology and residual energy of nodes. The vehicle nodes measure the one-hop communication distance between nodes according to the attenuation degree of signals and the original node chooses the main path according to RREP messages. Sending and receiving routing message through multiple-description technology would reduce the overhead of routing request.Simulation experiment analysis indicates that the improved DSR routing technology has the better performance in terms of end-to-end delay, packet delivery ratio and routing request overhead.
Zhou X.,Henan University of Economics and Law
Advances in Information Sciences and Service Sciences | Year: 2012
Among the application of gradient algorithm, the selection of the step length is the key of the blind signal separation. Therefore, in order to solve the relationship between the convergence speed and the stability problem of the natural gradient blind source separation algorithm, a kind of adaptive variable step length natural gradient algorithm was researched in this paper. A suitable step length adaptive natural gradient separation algorithm for the ECG signal blind source separation was found, which makes the next iteration of the step length optimal, and the objective function is the smallest. Through the blind source separation result of the mixed maternal ECG signal shown that the adaptive variable step length natural gradient algorithm can achieve fetal ECG signal separation effectively, and the frequency spectrum testing error is less than 0.5%.
Cheng D.,CAS Academy of Mathematics and Systems Science |
Qi H.,CAS Academy of Mathematics and Systems Science |
Li Z.,Henan University of Economics and Law
IEEE Transactions on Neural Networks | Year: 2011
In this paper, a set of data is assumed to be obtained from an experiment that satisfies a Boolean dynamic process. For instance, the dataset can be obtained from the diagnosis of describing the diffusion process of cancer cells. With the observed datasets, several methods to construct the dynamic models for such Boolean networks are proposed. Instead of building the logical dynamics of a Boolean network directly, its algebraic form is constructed first and then is converted back to the logical form. Firstly, a general construction technique is proposed. To reduce the size of required data, the model with the known network graph is considered. Motivated by this, the least in-degree model is constructed that can reduce the size of required data set tremendously. Next, the uniform network is investigated. The number of required data points for identification of such networks is independent of the size of the network. Finally, some principles are proposed for dealing with data with errors. © 2011 IEEE.
Zhang H.,Henan University of Economics and Law
International Journal of Advancements in Computing Technology | Year: 2012
Privacy preserving data mining is an important research area right now, and the key issue is to develop data mining method under the premise of protecting privacy data. As an important method for classified data mining, decision tree is also one exceptional classified method that has been studied intensively in the area of privacy preserving data mining. This paper comprehensively summarized decision tree mining methods of privacy preserving, and suggested a highly efficient decision tree classified mining method for privacy preserving based on lazy decision tree. Experiment results proved this method considered the advantages of eager learning and lazy learning, and hence possessed higher flexibility and compatibility.
Cui C.-S.,Henan University of Economics and Law
Xitong Gongcheng Lilun yu Shijian/System Engineering Theory and Practice | Year: 2013
From the output functional of recommender systems, the issue of the top-N was researched in this paper. The value of N affects the recommended quality and personalization. The feasibility and general methods of personalization of the output were studied in this paper. A new method based on aggregative rank was proposed. In the method, the entire sub-group is used as output of recommendation and the number of products in the sub-group is used as candidate value of N, in order to avoid big differences between the recommended products in the recommendation results and small differences between recommended products and un-recommended products. The general aggregative rank model of product was built in this paper. Meanwhile, aggregative rank quality was assessment based on different N, only in order to get a reliable value of N. The research results not only enrich the recommended system theoretical results, but also get a new road for personalization study of recommender systems.