Papers by Keyword: Crossover

Abstract: The notion of Genetic Algorithm was presented by [1] with the purpose of making computers execute what nature does. GA is one of the best methods for solving the optimization problems which involve a large search space [2].

Abstract: Genetic algorithm is the intelligent optimization design method, but its calculation workload is great and its convergence is slowly. This paper presents an improved micro-genetic algorithm (referred to as μGA-BLX) to overcome the shortcomings. The μGA-BLX algorithm uses the BLX-α operator to enhance the search ability of the algorithm in crossover; the mutation introduced on the Cauchy mutation operator to enhance the population's variety and the explore ability of algorithm. It shows the validity of the algorithm through the planet gear transmission optimization results.

Abstract: Based on the multimedia control theory, the mechanical bionic intelligent control is studied, and this theory is applied to the subjectivity analysis of college students employment to establish the mathematical model of mechanical bionic intelligent control, and to design automatic control algorithm. In order to validate the effect of mathematical model and algorithm, this paper compares the designed adaptive algorithm with 3 kinds of traditional genetic algorithm. From the calculation, we find that the adaptive algorithm in the fitness value of the solution and the mean is obviously better than that of the traditional genetic algorithm. While for the search of the optimal solution, the adaptive algorithm is fast and has high precision. The crossover and mutation rate of 20-100 generation calculation results show that the mutation rate is controlled within 0.1, which can meet the design requirement of accuracy, and can provide a theoretical reference for the study of mechanical automation control theory.

Abstract: This paper describes a genetic algorithm to solve the single machine scheduling problem with setup times, which uses the fixed two point crossover operator (F2PX) to produce new offspring chromosomes and uses the roulette wheel method in the selection of the chromosome population. In order to avoid the premature convergence we use a neighborhood based mutation operator to conduct disturbance in our genetic algorithm. Through the application of this genetic algorithm in practical scheduling problems, the effect of the genetic algorithm proposed in this paper is remarkable.

Abstract: This paper analyzed the basic object-oriented concepts from the perspective of testing. The effects of the characteristics of object-oriented software on the software testing were discussed. The class testing method of object-oriented software was put forward. This method includes tests based on the state transition diagram and data flow testing on class. A integration testing of object-oriented software was put forward based on the event-driven characteristics of object-oriented software, and a data-generating method of software test based on genetic algorithm was provided. The test case generating technology of object-oriented software was discussed, which utilized an intercalation method of branch function and regarded the genetic algorithm as the core search algorithm.

Abstract: The main goal of the paper is to provide a drawn up methodic for proposal of technical system optimization in terms of maximizing its reliability at given sum of financial costs or minimizing finance to achieve set reliability. The system reliability, respectively causal relationships between system failures and its elements faults are analyzed and illustrated by using special method called fault tree analysis (FTA) and technical system is represented by fault trees. Subsequently, the genetic algorithms are appropriately applied on the constructed diagram. The part of this paper is the proposal and description of individual steps of genetic algorithm in order to optimize fault tree analysis.

Abstract: This paper presents a genetic-based feature selection algorithm for object recognition. Firstly, the proposed algorithm encodes a solution with a binary chromosome. Secondly, the initial population was generated randomly. Thirdly, a crossover operator and a mutation operator are employed to operate on these chromosomes to generate more competency chromosomes. The probability of the crossover and mutation are adjusted dynamically according to the generation number and the fitness value. The proposed algorithm is tested using the features extracted from cotton foreign fiber objects. The results indicate that the proposed algorithm can obtain the optimal feature subset, and can reduce the classification time while keeping the classification accuracy constant.

Abstract: An swarm intelligence algorithm, particle swarm optimization (PSO) algorithm, is used in data association problem for multi-sensor multi-target data association. The association relation between measurements and targets is described by the likelihood function of filter innovation to establish the model of the optimal combination. Lagrange relaxation technology is used to reduce the combination to two dimensions firstly when solving the optimal combination problem, and then the improved PSO algorithm, which based on the cross and mutation rules, is used to obtain the optimal solution, and get the optimal association pairs for measurements and targets. The simulation shows the superiority of the method in accuracy and speed at last.

Abstract: For the issues of inferior local search ability and premature convergence in the later evolution stage of the traditional particle swarm optimization, an improved particle swarm optimization is proposed and applied to the parameter estimation. Firstly, in the evolutionary process of particle swarm optimization, the particles which have crossed the border are buffered according to the speed. Then, each particle is performed mutation in different probability according to the evolutionary generations, which can keep the diversity of the particle swarm and avoid the premature convergence effectively. Thirdly, a crossover operation is conducted between the current best particle and the particle which is selected from the particle swarm with a certain probability, which can lead particles gradually approaching to the extreme point and hence, the local search ability of the algorithm will be improved. The advanced particle swarm optimization is applied to the parameter estimation of the kinetic model in the Hg oxidation process and the application result show the effectiveness of the suggested algorithm.

Abstract: Considering that the particle swarm optimization (PSO) algorithm has a tendency to get stuck at the local solutions, an improved PSO algorithm is proposed in this paper to solve constrained optimization problems. In this algorithm, the initial particle population is generated using good point set method such that the initial particles are uniformly distributed in the optimization domain. Then, during the optimization process, the particle population is divided into two sub-populations including feasible sub-population and infeasible sub-population. Finally, different crossover operations and mutation operations are applied for updating the particles in each of the two sub-populations. The effectiveness of the improved PSO algorithm is demonstrated on three benchmark functions.