Catálogo de publicaciones - libros

Inspired by the immunity theory, a new immune-based dynamic intrusion response model, referred to as IDIR, is presented. An intrusion detection mechanism based on self-tolerance, clone selection, and immune surveillance, is established. The method, which uses antibody concentration to quantitatively describe the degree of intrusion danger, is demonstrated. And quantitative calculations of response cost and benefit are achieved. Then, the response decision-making mechanism of maximum response benefit is developed, and a dynamic intrusion response system which is self-adaptation is set up. The experiment results show that the proposed model is a good solution to intrusion response in the network.

This paper proposes a novel immune mobile agent based grid intrusion detection () model, and gives the concepts and formal definitions of , , , , and in the grid security domain. Then, the mathematical models of (monitoring agent) and are improved. Besides, effects of the important parameter in the models of dynamic memory MoA survival on system performance are showed. Our theoretical analyses and the experiment results show the model that enhances detection efficiency and assures steady performance is a good solution to grid intrusion detection.

A hybrid Orthogonal Scheme Ant Colony Optimization (OSACO) algorithm for continuous function optimization (CFO) is presented in this paper. The methodology integrates the advantages of Ant Colony Optimization (ACO) and Orthogonal Design Scheme (ODS). OSACO is based on the following principles: a) each independent variable space (IVS) of CFO is dispersed into a number of random and movable nodes; b) the carriers of pheromone of ACO are shifted to the nodes; c) solution path can be obtained by choosing one appropriate node from each IVS by ant; d) with the ODS, the best solved path is further improved. The proposed algorithm has been successfully applied to 10 benchmark test functions. The performance and a comparison with CACO and FEP have been studied.

Adapting a niching algorithm for dynamic environments is described. The Vector-Based Particle Swarm Optimizer locates multiple optima by identifying niches and optimizing them in parallel. To track optima effectively, information from previous results should be utilized in order to find optima after an environment change, with less effort than complete re-optimization would entail. The Vector-Based PSO was adapted for this purpose. Several scenarios were set up using a test problem generator, in order to assess the behaviour of the algorithm in various environments. Results showed that the algorithm could track multiple optima with a varying success rate and that results were to a large extent problem-dependent.

This paper proposes a Binary Ant System (BAS), a new Ant Colony Optimization applied to multidimensional knapsack problem (MKP). In BAS, artificial ants construct the solutions by selecting either 0 or 1 at every bit stochastically biased by the pheromone level. For ease of implementation, the pheromone is designed specially to directly represent the probability of selection. Experimental results show the advantage of BAS over other ACO based algorithms. The ability of BAS in finding the optimal solutions of various benchmarks indicates its potential in dealing with large size MKP instances.

A hybrid discrete particle swarm algorithm is presented in this paper to solve open-shop problems. The operations are redefined in the discrete particle swarm algorithm. To improve the performance the simulated annealing algorithm is combined with discrete particle swarm. We use SA to enhance the results of local best positions instead of current positions. The experimental results show that our hybrid discrete particle swarm algorithm is effective and efficient to solve open-shop problems.

In this paper, a Particle Swarms Cooperative Optimization is proposed to solve Coalition Generation Problem in parallel manner with each Agent taking part in several different coalitions and each coalition turning its hand to several different tasks. With a novel two-dimensional binary encoding approach, the algorithm performs well on coalition parallel generation. An adaptive disturbance factor is adopted to force swarms getting out of local optimums quickly. Introduced an active-feedback based on island models, the algorithm has a good cooperative searching characteristic. The effectiveness of the proposed algorithm is proved by experiments.

A new approach is presented to handle constrained optimization by using PSO algorithm. It neither uses any penalty function in the proposed PSO algorithms. The new technique treats constrained optimization as a two-objective optimization, one objective is original objective function, and the other is the degree violation of constraints. As we prefer the second objective, a new crossover operator is designed based on the three-parent crossover operator, which will lead the degree violation of constraints to zero. Then, in order to keep the diversity of the swarm and escape from the local optimum easily, we design a dynamically changing inertia weight. The simulation results indicate the proposed algorithm is effective.

This paper presents a hybrid discrete particle swarm optimization (HDPSO) for solving the traveling salesman problem (TSP). The HDPSO combines a new discrete particle swarm optimization (DPSO) with a local search. DPSO is an approach designed for the TSP based on the binary version of particle swarm optimization. Unlike in general versions of particle swarm optimization, DPSO redefines the particle’s position and velocity, and then updates its state by using a tour construction. The embedded local search is implemented to improve the solutions generated by DPSO. The experimental results on some instances are reported and indicate HDPSO can be used to solve TSPs.

We propose methods for incrementally constructing a knowledge model for a dynamically changing database, using a swarm of special agents (ie an ant colony) and imitating their natural cluster-forming behavior. We use information-theoretic metrics to overcome some inherent problems of ant-based clustering, obtaining faster and more accurate results. Entropy governs the pick-up and drop behaviors, while movement is guided by pheromones. The primary benefits are fast clustering, and a reduced parameter set. We compared the method both with static clustering (repeatedly applied), and with the previous dynamic approaches of other authors. It generated clusters of similar quality to the static method, at significantly reduced computational cost, so that it can be used in dynamic situations where the static method is infeasible. It gave better results than previous dynamic approaches, with a much-reduced tuning parameter set. It is simple to use, and applicable to continuously- and batch-updated databases.