Catálogo de publicaciones - libros

The goal of maximum cut problem is to partition the vertex set of an undirected graph into two parts in order to maximize the cardinality of the set of edges cut by the partition. This paper proposes an Adaptive Hybrid Immune Genetic Algorithm, which includes key techniques such as vaccine abstraction, vaccination and affinity-based selection. A large number of instances have been simulated, and the results show that proposed algorithm is superior to existing algorithms.

According to the principles of non-self detection and negative selection in natural immune system, two generating algorithms of detector are proposed in this paper after reviewing current detector generating algorithms used in artificial immune systems. We call them as Bit Mutation Growth Detector Generating Algorithm (BMGDGA) and Arithmetical-compliment Growth Detector Generating Algorithm (AGDGA) based on their operational features. The principle and work procedure of the two detector generating algorithms are elaborated in details in the paper. For evaluation of the proposed algorithms, they are tested and verified by using different datasets, and compared to Exhaustive Detector Generating Algorithm (EDGA). It turns out that the proposed two algorithms are superior to EDGA in detection performance and computational complexities.

A new algorithm based on antibody immunodominance (AIDA) for TSP is explored. The main content of this paper is to explore how to produce the set of immunodominance and the superior antibodies. The experience proves that the algorithm has higher convergence speed and better solution compared with the corresponding genetic algorithm and is fit to solving complex problems.

Production scheduling is an important part in the factories, and there are various uncertainties in the production scheduling of industrial processes. A scheduling mathematical model for flow shop problems with uncertain processing time has been established based on fuzzy programming theory. And in this paper, the fuzzy model can be translated into two mathematical models about the characteristic of scheduling problems. Furthermore, a fuzzy immune scheduling algorithm combined with the feature of the Immune Algorithm is proposed, which prevents the possibility of stagnation in the iteration process and achieves fast convergence for global optimization. The effectiveness and efficiency of the fuzzy scheduling model and the proposed algorithm are demonstrated by simulation results.

Immune Evolutionary Algorithm (IEA) is proposed on the shortages of evolution algorithm and biological immune mechanism. According to the characteristics of chaos, a novel Chaotic Immune Evolutionary Algorithm (CIEA) is presented which introduces chaos to IEA. The algorithm has the merits of chaos, immunity and evolutionary algorithm. It can ensure the ability of global search and local search and enhance the performances of the algorithm. At last, we analyze the efficiency of the algorithm with two typical optimization problems. The analysis result shows that CIEA converges quickly and effectively avoids the inherent problem that the evolution algorithm traps in immature convergence, so CIEA is an effective way to solve complex optimization problem.

Based on clonal selection principle, an improved immune algorithm (IIA) is proposed in this paper. This algorithm generates the next population under the guidance of the previous superior antibodies (Ab’s) in a small and a large neighborhood respectively, in order to realize the parallel global and local search capabilities. The computational results show that higher quality solutions are obtained in a shorter time, and the degree of diversity in population are maintained by the proposed method. Meanwhile, “Average truncated generations” and “Distribution entropy of truncated generations” are used to evaluate the optimization efficiency of IIA. The comparison with clonal selection algorithm (CSA) demonstrates the superiority of the proposed algorithm IIA.

The problems of feature selection and automatically tuning parameters for SVM are considered at the same time. It is reasonable because the parameters of SVM are influenced by the given feature subset. Both of the problems can be considered as combination optimization problems. Immune clonal algorithm offers natural and potential way to solve the task because of its characteristic of rapid convergence to global optimal solution. In the evolution, the suitable feature subset and optimal parameters are got simultaneously by minimizing the existing bound on the generalization error for SVM. The results of experiments on sonar data set show the effectiveness of the method.

Designing optimal measurement infrastructure is a key step for network management. In this work the goal of the optimization is to identify a minimum aggregating nodes set subject to bandwidth and delay constraints on the aggregating procedure. The problem is NP-hard. In this paper, we describe the way of using Genetic Algorithm for finding aggregating nodes set. The simulation indicates that Genetic Algorithm can produce much better result than the current method of randomly picking aggregating nodes.

The accurate control of the work pieces temperature is a nonlinear, large time-delay, and cross-coupling complicated control problem in vacuum annealing furnace. In order to control the temperature of work pieces accurately. The optimization model for accurate work pieces temperature control has been proposed by the data gathered from the scene. The model was set up with Wavelet Neural Networks (WNN). Adaptive Immune Genetic Algorithm (AIGA) optimized the WNN structure and parameters (weights, dilation and translation). Simulation and experiment results show that the model in this paper is better than the model established with NN and optimizing the weights of NN by GA. And, it improves the training rate of Networks and obtains a system with good steady state precision, real timeliness and robustness.

In this paper, Immune Clonal Selection theory and Lamarckism are integrated to form a new algorithm, Lamarckian Polyclonal Programming Algorithm (LPPA), for solving the global numerical optimization problem. The idea that Lamarckian evolution described how organism can evolve through learning, namely the point of “Gain and Convey” is applied, then this kind of learning mechanism is introduced into Adaptive Polyclonal Programming Algorithm (APPA). In the experiments, ten benchmark functions are used to test the performance of LPPA, and the scalability of LPPA along the problem dimension is studied with great care. The results show that LPPA achieves a good performance when the dimensions are increased from 20-10,000. Moreover, even when the dimensions are increased to as high as 10,000, LPPA still can find high quality solutions at a low computation cost. Therefore, LPPA has good scalability and is a competent algorithm for solving high dimensional optimization problems.