Xiyu Liu

Shandong Normal University, Chi-nan-shih, Shandong Sheng, China

Are you Xiyu Liu?

Claim your profile

Publications (99)20.8 Total impact

  • Jie Xue · Xiyu Liu

    No preview · Article · Mar 2014
  • Xiyu Liu · Jie Xue · Laisheng Xiang
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a new technique for clustering, which is the combination of membrane computing and Bin-packing technique. A new kind of P system (graph P system) is constructed which is different with the traditional ones. New rules and membrane structure are described. Cluster analysis is transformed by Bin-packing technique. All processes of the algorithm are implemented on this P system, including rules for mutation, swap and the calculation of energy change. Finally we apply the technique in the heart disease data set and obtain some results.
    No preview · Article · Jan 2014 · Lecture Notes in Electrical Engineering
  • Qiang Du · Laisheng Xiang · Xiyu Liu
    [Show abstract] [Hide abstract]
    ABSTRACT: Particle Swarm Optimization algorithm is a kind of excellent optimization algorithm, and has been widely used in many fields. In order to overcome the premature convergence and improve the accuracy of the PSO, we combine some related theories of membrane computing with PSO. The new algorithm can effectively balance the global search and partial optimization. Simulation results based on three bench functions show that the new algorithm can effectively solve the problem of premature, and effectively improve the convergence precision. At the same time, the algorithm in solving TSP problem also shows good optimization ability.
    No preview · Article · Jan 2014 · Lecture Notes in Electrical Engineering
  • Xiuting Li · Laisheng Xiang · Xiyu Liu
    [Show abstract] [Hide abstract]
    ABSTRACT: Enterprises are both an emerging force in national reform and a major force in its future economic development. The professors in China and on abroad have do much research on enterprise development and put forward lots of valuable theories. P systems have been proposed for about 14 years, and its applications refer to numbers of areas. However, to investigate the survival and development of firms in the aspect of P systems is rarely. In this study, it makes analysis on the survival and development of small and medium-sized enterprises in an aspect of bionics, trying to find out the origin which makes the enterprise exuberant and everlasting. Have the enterprises compare to biological cells and construct a membrane framework in order to interpret an enterprise’s survival. At the same time it also highlights the irreplaceable role of enterprise DNA in the inheritance of the enterprise entity.
    No preview · Chapter · Jan 2014
  • Jie Sun · Xiyu Liu
    [Show abstract] [Hide abstract]
    ABSTRACT: Membrane computing has been applied in broad fields such as Biological modeling, NPC problems and combinatorial problems. It has great parallelism and non-determinacy. In this paper, a new variety of P system with chained rules is first applied to the problem of the hierarchical clustering. This new model of P system is designed to solve hierarchical clustering of individuals with nonnegative integer variables. Through performance analysis, this new model of P system can reduce the time complexity of clustering process comparing with the classical clustering algorithm. And it is proved to be more concise and explicit to realize agglomerative hierarchical clustering algorithm by example verification. This is a great improvement in applications of membrane computing.
    No preview · Article · Jan 2014
  • Xiuting Li · Laisheng Xiang · Xiyu Liu
    [Show abstract] [Hide abstract]
    ABSTRACT: Enterprise life cycle theory is the most direct business growth study of enterprise development. This theory divides SMEs' (small and medium-size enterprises) life into different stages, and do research respectively in each stage on the growth of them. It holds that companies are like biological organisms, they also have the growth from birth to death, from gloom to doom. It makes an analog of SMEs' stages development combined with the core concept of membrane computing and the knowledge of biology. It is on a living point of view to analyze the growth of an enterprise, but also a continuation of the theoretical research on bionic-evolution theory. The discussion on how to extend the life of the enterprise and how to make it grow as longevity enterprise is of profound practical effect to the cultivation of domestic life-oriented enterprises.
    No preview · Article · Jan 2014 · Lecture Notes in Electrical Engineering
  • Shuguo Zhao · Xiyu Liu
    [Show abstract] [Hide abstract]
    ABSTRACT: In recent years, DNA-GA algorithms, which attracts many scholars' attention, combine the DNA encoding method with Genetic algorithm. It effectively overcomes GA's limitation such as premature convergence, poor local search capability and binary Hamming cliffs problems. In this work, a new DNA-GA algorithm based on P system (PDNA-GA) is proposed to improve the performance of DNA-GA algorithms by combining the parallelism of P system in Membrane Computing. The performance of PDNA-GA in typical benchmark functions is studied. The experimental results demonstrate that the proposed algorithm can effectively yield the global optimum with high efficiency.
    No preview · Chapter · Jan 2014
  • Feng Qi · Xiyu Liu · Yinghong Ma
    [Show abstract] [Hide abstract]
    ABSTRACT: A neural tree network ensemble model is proposed for classification which is an important research field in data mining and machine learning. Firstly, establishes each single neural tree network by using an improved hybrid breeder genetic programming, and then more neural tree networks are combined to form the final classification model by the idea of ensemble learning. Simulation results on two disease classification problems show that this model is effective for the classification, and has better performance in classification precision, feature selection and structure simplification, especially for classification with multi-class attributes.
    No preview · Article · Jan 2014 · Lecture Notes in Electrical Engineering
  • Jie Xue · Xiyu Liu
    [Show abstract] [Hide abstract]
    ABSTRACT: The purpose of this paper is to propose a new clustering algorithm, which combines membrane computing with a modified chameleon algorithm. The new algorithm is called as P-chameleon algorithm, which can obtain the k-nearest graphs, complete the partition of graph, aggregate subgraphs through communication rules and rewriting rules with the help of active promoters and inhibitors. The whole process of P-chameleon algorithm is shown by a 10 points test data set, which indicates the feasibility of the algorithm. All the processes are conducted in membranes. Cluster results via the famous wine data set verify that the proposed P-chameleon algorithm can cluster data set more accurate and less time consuming. The influences of parameters to the algorithm are also illustrated. The P-chameleon algorithm provides an alternative for traditional computing.
    No preview · Article · Oct 2013 · Journal of Computers
  • Jie Xue · Xiyu Liu
    [Show abstract] [Hide abstract]
    ABSTRACT: Membrane computing is widely used in many areas, however, there are several limitations in its structures and rules. Although many researchers are engaged in the study of P systems, seldom focus on improving membrane structures. The purpose of this paper is to propose a new kind of communication P system on lattice (LTC-P systems). We describe membrane structures on lattice with communication rules. The computational completeness of the new P system is proved by simulation of register machine. The new P system is used in solving clustering problems. It is combined with the thought of density-based, partition-based and hierarchical clustering algorithm. Clustering is implemented by supremum and infimum rules. The result is obtained through output membrane. All the processes are conducted in membranes. Cluster result via a $20$ points data set verifies that the proposed new P systems cluster data set accurately and reduce time complexity. Wine data set are also used in testing the influence of parameters. More suitable $\varepsilon $ and ${ MinPts}$ are found to gain less missing data which are seen as noise. Comparative results in various aspects indicate LTC-P system based clustering algorithm consumes less time than traditional algorithms significantly. It also uses less rules and gives more simple membrane structures than conventional cell-like P system. The new P system provides an alternative for traditional membrane computing.
    No preview · Article · Jul 2013 · Soft Computing
  • Jie Xue · Xiyu Liu

    No preview · Article · Jun 2013
  • Feng Qi · Yinghong Ma · Xiyu Liu · Guangyong Ji
    [Show abstract] [Hide abstract]
    ABSTRACT: By changing the linear encoding and redefining the evolving rules, particle swarm algorithm is introduced into genetic programming and an hybrid genetic programming with particle swarm optimization (HGPPSO) is proposed. The performance of the proposed algorithm is tested on tow symbolic regression problem in genetic programming and the simulation results show that HGPPSO is better than genetic programming in both convergence times and average convergence generations and is a promising hybrid genetic programming algorithm.
    No preview · Chapter · Jun 2013
  • Xiyu Liu · Jie Xue
    [Show abstract] [Hide abstract]
    ABSTRACT: Spatial cluster analysis is an important data mining task. Typical techniques include CLARANS, density- and gravity-based clustering, and other algorithms based on traditional von Neumann's computing architecture. The purpose of this paper is to propose a technique for spatial cluster analysis based on sticker systems of DNA computing. We will adopt the Bin-Packing Problem idea and then design algorithms of sticker programming. The proposed technique has a better time complexity. In the case when only the intracluster dissimilarity is taken into account, this time complexity is polynomial in the amount of data points, which reduces the NP-completeness nature of spatial cluster analysis. The new technique provides an alternative method for traditional cluster analysis.
    No preview · Article · Apr 2013 · Discrete Dynamics in Nature and Society
  • Yuzhen Zhao · Xiyu Liu · Hua Zhang

    No preview · Article · Apr 2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: Trust is an important mechanism to promote cooperation among persons in social network. As a security mechanism, it is widely implemented computer networks. In P2P applications, trust among cooperating peers is an essential precondition. It is becoming increasing vital in open, distributed, dynamic and anonymous networks to protect against malicious peers. This paper proposed a trust-aware propagation model based on the social network and with the basis of analyzing aware-computing to attempt to discover the propagation characteristics and regularity of trust being as network stability factor, and to reveal the functional mechanism of trust in the network security, which can improve the stability and robustness of the network. Firstly, we proposed a trust-aware propagation framework that contains three layers: propagation layer, aware layer, and computation layer. And then, the trust-aware propagation algorithm is presented to implement the formation of trust networks as fast as in P2P. A fitness function for peers computes their fitness degree based on contextual information to provide an initial entity identification mechanism, and the process of trust-aware propagation based on Markov process is defined to apperceive of trust among peers to ulteriorly form trust alliance. Thirdly, we built the dynamics model of trust propagation in order to deeply analyze the stability of trust networks. Next, three propagation strategies is proposed for implementing trust propagation. Finally, simulation experiments are carried in the bio-network platform. The results show that the trust-aware propagation model can effectively enhance the security and stability of P2P network, and improve the availability of the peer's resources.
    No preview · Article · Mar 2013 · Knowledge-Based Systems
  • Yinghong Ma · Xiyu Liu · Xiao Li

    No preview · Article · Feb 2013
  • Laisheng Xiang · Feng Qi · Xiyu Liu
    [Show abstract] [Hide abstract]
    ABSTRACT: Neural tree network model has been successfully applied to solving a variety of complex nonlinear problems. The optimization of the neural tree model is divided into two steps in general: first structure optimization, and then parameter optimization. One major problem in the evolution of structure without parameter information is noisy fitness evaluation, so an improved breeder genetic programming algorithm is proposed to the synthesis of the optimization in neural tree network model. Simulation results on two time series prediction problems show that the proposed optimization strategy is a potential method with better performance and effectiveness.
    No preview · Article · Jan 2013 · Kongzhi yu Juece/Control and Decision
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: As a popular web innovation, Web service technology can provide a flexible solution to integrating diverse Web applications, taking advantage of existing Internet protocols and open standards. To provide on-request Web applications, Web services are evolving to be highly available, ubiquitous, self-managing, and adaptable to dynamic requests through distributed collaborations. However, the distributed collaborations unavoidably need security requirements, and traditional security mechanisms fail to address the challenge. On the other hand, trust is an important social concept and present in all human interactions. It has been proven as a promising way to resolving security problems raised by the distributed collaborations. This paper applies trust mechanisms into the development of a novel trust evaluation model of Web services. We first incorporate a trust management module into the standard Service Oriented Architecture (SOA). Then, regarding the trust relationships of service entities in Web service networks as a small-world network, we propose a trust evaluation model based on an amendatory subjective logic. The results of simulation experiments show the effectiveness of the proposed model, which outperforms other two models in terms of both detection capability and stability.
    Preview · Article · Jan 2013
  • Xiyu Liu · Jie Xue · Xiaolin Yu
    [Show abstract] [Hide abstract]
    ABSTRACT: A novel multi-agent membrane computing technique is proposed. We provide a new membrane structure on graph to construct a multi-agent membrane system, which offers a new framework for collaboration and resources sharing among designers. The new design environment provides a tool to extend designer's ideas with the help of communication rules of membrane. Shapes were generated and changed in membrane systems by rules base on the idea of genetic computing with operators crossover, mutation and selection. A multi-agent membrane system with rules is constructed in detail. Finally, a pipe design example is adopted to illustrate the entire design process, which also shows the great parallelism, less time-consuming and synchronization of MAMC.
    No preview · Conference Paper · Jan 2013
  • Yuzhen Zhao · Xiyu Liu · Jianhua Qu
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper a clustering algorithm based on a P System with active membranes is proposed which provides new ideas and methods for cluster analysis. The membrane system has great parallelism. It could reduce the computational time complexity. Firstly a clustering problem is transformed into a graph theory problem by transforming the objects into graph nodes and dissimilarities into edges with weights of complete undirected graph, and then a P system with all the rules to solve the problem is constructed. The specific P system with external output is designed for the dissimilarity matrix associated with n objects. First all combinations of all nodes are listed to show all possibilities of the paths (the solution space) by using division rules of P system. Then a shortest path with the minimum sum of weights is selected. At last the path is divided into k parts from the edges with the k-1 biggest weights according to the preset number of clusters k. That is to say, all nodes are divided into k clusters. The calculation of the P system can get all the clustering results. Through example test, the proposed algorithm is appropriate for cluster analysis. This is a new attempt in applications of membrane system.
    No preview · Conference Paper · Nov 2012