Catálogo de publicaciones - libros

In the paper, immune algorithm(IA) is proposed for optimizing membership function of fuzzy variables for mining associate rules. It is used in network detection to testify its efficiency in such mining task, including maximizing the similarity between normal association rule sets while minimizing the similarity between a normal and an abnormal association rule set. Experiment results show that IA-optimization based fuzzy logic system can improve the performance of mining associate rules in network intrusion.

In this paper, we introduce a new multiobjective optimization (MO) algorithm to solve ZDT test problems using the immune clonal principle. This algorithm is termed Immune Clonal MO Algorithm (ICMOA). In ICMOA, the antibody population is split into nondominated antibodies and dominated antibodies. Meanwhile, the nondominated antibodies are allowed to survive and to clone and the is adopted. Two metrics proposed by K. Deb et al. are adopted to measure the extent of convergence to a known set of Pareto-optimal solutions and the extent of spread achieved among the obtained solutions. Our algorithm is compared with another algorithm that is representative of the state-of-the-art in evolutionary multiobjective optimization–NSGA-II. Simulation results on ZDT test problems show that ICMOA, in most problems, is able to find much better spread of solutions and better convergence near the true Pareto-optimal front compared to NSGA-II.

This paper analyzes the deficiencies of current grid trust systems based on PKI (Public Key Infrastructure), ambiguity certificate principal information, and complicated identification process. Inspired by biologic gene technique, we propose a novel grid trust model based on Family Gene (FG) model. The model answers the existing questions in tradition trust model by adopting the technology of family gene. The concepts and formal definitions of Family Gene in the grid trust security domains are given. Then, the mathematical models of Family Gene are established. Our theoretical analysis and experimental results show that the model is a good solution to grid trust domain.

Based on the clonal selection theory, the main mechanisms of clone are analyzed in this paper, a new immune operator, Clonal Operator, inspired by the Immune System is discussed firstly. Based on the Clonal operator, we propose Immune Clonal Strategy Algorithm (ICSA); three different mutation mechanisms including Gaussian mutation, Cauthy mutation and Mean mutation are used in IMSA. IMSA based on these three methods are compared with Classical Evolutionary Strategy (CES) on a set of benchmark functions, the numerical results show that ICSA is capable of avoiding prematurity, increasing the converging speed and keeping the variety of solution. Additionally, we present a general evaluation of the complexity of ICSA.

Terrestrial social insects build architecturally complex nests despite their limited sensors, minimal individual intelligence and the lack of a central control system. [3] Many of the nest structures emerge as a response of the individual insects to pheremones, which the insects themselves can emit.[2] The work in [4] extrapolated from social insect building behavior to a system where the behavior of homogenous swarms of virtual agents could be designed to build simple structures. Like termites, these agents have no memory and limited sensors, and the macroscopic structure emerges from their interactions with their immediate environments. This paper presents Stigcode, a swarm programming language that permits more complex structures to be more conveniently specified. A StigCode program is a description of a target structure that is compiled into a set of reactions to pheremone concentrations for the swarm agents. Though not Turing-Universal, StigCode provides a syntax for defining re-usable, composable design elements. In keeping with the entomorphic theme, In the manner of ant and termite nests, StigCode architectures can do limited self-repair

The Ant Colony Optimization has gained great success in applications to combinatorial optimization problems, but few of them are proposed in the continuous domain. This paper proposes an ant algorithm, called Direct Ant Colony Optimization (DACO), for the function optimization problem in continuous domain. In DACO, artificial ants generate solutions according to a set of normal distribution, of which the characteristics are represented by pheromone modified by ants according to the previous search experience. Experimental results show the advantage of DACO over other ACO based algorithms for the function optimization problems of different characteristics.

By introducing the information entropy and mutual information of information theory into swarm intelligence, the Interaction Optimization Model (IOM) is proposed. In this model, the information interaction process of individuals is analyzed with and aiming at solving optimization problems. We call this optimization approach as interaction optimization. In order to validate this model, we proposed a new algorithm for Traveling Salesman Problem (TSP), namely Route-Exchange Algorithm (REA), which is inspired by the information interaction of individuals in swarm intelligence. Some benchmarks are tested in the experiments. The results indicate that the algorithm can quickly converge to the optimal solution with quite low cost.

Particle swarm optimization (PSO) has proven to be a promising heuristic algorithm for solving combinatorial optimization problems. However, N-P hard problems such as Job Shop Scheduling (JSSP) are difficult for most heuristic algorithms to solve. In this paper, two effective strategies are proposed to enhance the searching ability of the PSO. An alternate topology is introduced to gather better information from the neighborhood of an individual. Benchmarks of JSSP are used to test the approaches. The experiment results indicate that the improved Particle Swarm has a good performance with a faster searching speed in the search space of JSSP.

This paper presents an improved discrete particle swarm optimization algorithm based on virus theory of evolution. Virus-evolutionary discrete particle swarm optimization algorithm is proposed to simulate co-evolution of a particle swarm of candidate solutions and a virus swarm of substring representing schemata. In the co-evolutionary process, the virus propagates partial genetic information in the particle swarm by virus infection operators which enhances the horizontal search ability of particle swarm optimization algorithm. An example of partner selection in virtual enterprise is used to verify the proposed algorithm. Test results show that this algorithm outperforms the discrete PSO algorithm put forward by Kennedy and Eberhart.

This paper proposes kalman particle swarm optimization algorithm (KPSO), which combines kalman filter with PSO. Comparison of optimization performance between KPSO and PSO with three test functions shows that KPSO has better optimization performance than PSO. The combination of KPSO and ANN is also introduced (KPSONN). Then, KPSONN is applied to construct a soft-sensor of acrylonitrile yield. After comparing with practical industrial data, the result shows that KPSONN is feasible and effective in soft-sensor of acrylonitrile yield.