A robust dynamic niching genetic algorithm with niche migration for automatic clustering problem

In this paper, a genetic clustering algorithm based on dynamic niching with niche migration (DNNM-clustering) is proposed. It is an effective and robust approach to clustering on the basis of a similarity function relating to the approximate density shape estimation. In the new algorithm, a dynamic identification of the niches with niche migration is performed at each generation to automatically evolve the optimal number of clusters as well as the cluster centers of the data set without invoking cluster validity functions. The niches can move slowly under the migration operator which makes the dynamic niching method independent of the radius of the niches. Compared to other existing methods, the proposed clustering method exhibits the following robust characteristics: (1) robust to the initialization, (2) robust to clusters volumes (ability to detect different volumes of clusters), and (3) robust to noise. Moreover, it is free of the radius of the niches and does not need to pre-specify the number of clusters. Several data sets with widely varying characteristics are used to demonstrate its superiority. An application of the DNNM-clustering algorithm in unsupervised classification of the multispectral remote sensing image is also provided.     

引入高斯变异和最速下降算子的人口迁移算法

人口迁移算法模拟了人口随经济中心而转移和随人口压力增加而扩散的机制。主要针对该算法提出了一种改进的人口迁移算法。该改进算法通过引入高斯变异算子和最速下降算子来改善人口迁移算法的收敛速度和全局收敛性,并对其收敛性进行了证明。通过对函数的数值实验测试结果表明,改进的人口迁移算法的全局寻优能力和收敛速度较人口迁移算法均有所提高。     

A grouping genetic algorithm with controlled gene transmission for the bin packing problem

In this study, the one-dimensional Bin Packing Problem (BPP) is approached. The BPP is a classical optimization problem that is known for its applicability and complexity. We propose a method that is referred to as the Grouping Genetic Algorithm with Controlled Gene Transmission (GGA-CGT) for Bin Packing. The proposed algorithm promotes the transmission of the best genes in the chromosomes without losing the balance between the selective pressure and population diversity. The transmission of the best genes is accomplished by means of a new set of grouping genetic operators, while the evolution is balanced with a new reproduction technique that controls the exploration of the search space and prevents premature convergence of the algorithm. The results obtained from an extensive computational study confirm that (1) promoting the transmission of the best genes improves the performance of each grouping genetic operator; (2) adding intelligence to the packing and rearrangement heuristics enhances the performance of a GGA; (3) controlling selective pressure and population diversity tends to lead to higher effectiveness; and (4) GGA-CGT is comparable to the best state-of-the-art algorithms, outperforming the published results for the class of instances Hard28, which appears to have the greatest degree of difficulty for BPP algorithms.     

A modified genetic algorithm for distributed scheduling problems

Genetic algorithms (GAs) have been widely applied to the scheduling and sequencing problems due to its applicability to different domains and the capability in obtaining near-optimal results. Many investigated GAs are mainly concentrated on the traditional single factory or single job-shop scheduling problems. However, with the increasing popularity of distributed, or globalized production, the previously used GAs are required to be further explored in order to deal with the newly emerged distributed scheduling problems. In this paper, a modified GA is presented, which is capable of solving traditional scheduling problems as well as distributed scheduling problems. Various scheduling objectives can be achieved including minimizing makespan, cost and weighted multiple criteria. The proposed algorithm has been evaluated with satisfactory results through several classical scheduling benchmarks. Furthermore, the capability of the modified GA was also tested for handling the distributed scheduling problems.     

A genetic algorithm for railway scheduling with environmental considerations

A genetic algorithm is a randomized optimization technique that draws its inspiration from the biological sciences. Specifically, it uses the idea that genetics determines the evolution of any species in the natural world. Integer strings are used to encode an optimization problem and these strings are subject to combinatorial operations called reproduction, crossover and mutation, which improve these strings and cause them to ‘evolve’ to an optimal or nearly optimal solution. In this paper, the general machinations of genetic algorithms are described and a performance-enhanced algorithm is proposed for solving the important practical problem of railway scheduling. The problem under consideration involves moving a number of trains carrying mineral deposits across a long haul railway line with both single and double tracks in either direction. Collisions can only be avoided in sections of the line with double tracks. Constraints reflecting practical requirements to reduce environmental impacts from mineral transport, such as avoidance of loaded trains traversing populated areas during certain time slots, have to be satisfied. This is an NP-hard problem, which usually requires enumerative, as opposed to constructive, algorithms. For this reason, an ‘educated’ random search procedure like the genetic algorithm is an alternative and effective technique. The genetic algorithm is given difficult test problems to solve and the algorithm was able to generate feasible solutions in all cases.     

A genetic algorithm for combined topology and shape optimisations

A method to find optimal topology and shape of structures is presented. With the first the optimal distribution of an assigned mass is found using an approach based on homogenisation theory, that seeks in which elements of a meshed domain it is present mass; with the second the discontinuous boundaries are smoothed. The problem of the optimal topology search has an ON/OFF nature and has suggested the employment of genetic algorithms. Thus in this paper a genetic algorithm has been developed, which uses as design variables, in the topology optimisation, the relative densities (with respect to effective material density) 0 or 1 of each element of the structure and, in the shape one, the coordinates of the keypoints of changeable boundaries constituted by curves. In both the steps the aim is that to find the variable sets producing the maximum stiffness of the structure, respecting an upper limit on the employed mass. The structural evaluations are carried out with a FEM commercial code, linked to the algorithm. Some applications have been performed and results compared with solutions reported in literature.     

A spatially structured genetic algorithm for multi-robot localization

In this paper the multi-robot localization problem is addressed. A new framework based on a spatially structured genetic algorithm is proposed. Collaboration among robots is considered and is limited to the exchange of sensor data. Additionally, the relative distance and orientation among robots are assumed to be available. The proposed framework (MR-SSGA) takes advantage of the cooperation so that the perceptual capability of each robot is extended. Cooperation can be set-up at any time when robots meet, it is fully decoupled and does not require robots to stop. Several simulations have been performed, either considering cooperation activated or not, in order to emphasize the effectiveness of the collaboration strategy.     

A genetic algorithm for the Flexible Job-shop Scheduling Problem

In this paper, we present a genetic algorithm for the Flexible Job-shop Scheduling Problem (FJSP). The algorithm integrates different strategies for generating the initial population, selecting the individuals for reproduction and reproducing new individuals. Computational result shows that the integration of more strategies in a genetic framework leads to better results, with respect to other genetic algorithms. Moreover, results are quite comparable to those obtained by the best-known algorithm, based on tabu search. These two results, together with the flexibility of genetic paradigm, prove that genetic algorithms are effective for solving FJSP.     

A multi-objective genetic algorithm for mixed-model assembly line rebalancing

When demand structure or production technology changes, a mixed-model assembly line (MAL) may have to be reconfigured to improve its efficiency in the new production environment. In this paper, we address the rebalancing problem for a MAL with seasonal demands. The rebalancing problem concerns how to reassign assembly tasks and operators to candidate stations under the constraint of a given cycle time. The objectives are to minimize the number of stations, workload variation at each station for different models, and rebalancing cost. A multi-objective genetic algorithm (moGA) is proposed to solve this problem. The genetic algorithm (GA) uses a partial representation technique, where only a part of the decision information about a candidate solution is expressed in the chromosome and the rest is computed optimally. A non-dominated ranking method is used to evaluate the fitness of each chromosome. A local search procedure is developed to enhance the search ability of moGA. The performance of moGA is tested on 23 reprehensive problems and the obtained results are compared with those by other authors.     

A genetic algorithm calibration method based on convergence due to genetic drift

The selection of Genetic Algorithm (GA) parameters is a difficult problem, and if not addressed adequately, solutions of good quality are unlikely to be found. A number of approaches have been developed to assist in the calibration of GAs, however there does not exist an accepted method to determine the parameter values. In this paper, a GA calibration methodology is proposed based on the convergence of the population due to genetic drift, to allow suitable GA parameter values to be determined without requiring a trial-and-error approach. The proposed GA calibration method is compared to another GA calibration method, as well as typical parameter values, and is found to regularly lead the GA to better solutions, on a wide range of test functions. The simplicity and general applicability of the proposed approach allows suitable GA parameter values to be estimated for a wide range of situations.     

A genetic algorithm with memory for mixed discrete-continuous design optimization

This paper describes a new approach for reducing the number of the fitness function evaluations required by a genetic algorithm (GA) for optimization problems with mixed continuous and discrete design variables. The proposed additions to the GA make the search more effective and rapidly improve the fitness value from generation to generation. The additions involve memory as a function of both discrete and continuous design variables, multivariate approximation of the fitness function in terms of several continuous design variables, and localized search based on the multivariate approximation. The approximation is demonstrated for the minimum weight design of a composite cylindrical shell with grid stiffeners.     

遗传算法采用进化方向算子的几种策略

提出了采用实数编码情况下应用进化方向算子的几种策略，包括单亲进化方向算子、双亲进化方向算子以及无轮盘赌选择的双亲进化方向算子策略，并进行了数值仿真。仿真结果表明，灵活使用方向进化算子以及遗传操作可大大提高遗传算法的全局搜索能力。     

A variable-grouping based genetic algorithm for large-scale integer programming

To effectively reduce the dimensionality of search space, this paper proposes a variable-grouping based genetic algorithm (VGGA) for large-scale integer programming problems (IPs). The VGGA first groups IP’s decision variables based on the optimal solution to the IP’s continuous relaxation problem, and then applies a standard genetic algorithm (GA) to the subproblem for each group of variables. We compare the VGGA with the standard GA and GAs based on even variable-grouping by applying them to solve randomly generated convex quadratic knapsack problems and integer knapsack problems. Numerical results suggest that the VGGA is superior to the standard GA and GAs based on even variable-grouping both on computation time and solution quality.     

A self-adaptive migration model genetic algorithm for data mining applications

Data mining involves nontrivial process of extracting knowledge or patterns from large databases. Genetic Algorithms are efficient and robust searching and optimization methods that are used in data mining. In this paper we propose a Self-Adaptive Migration Model GA (SAMGA), where parameters of population size, the number of points of crossover and mutation rate for each population are adaptively fixed. Further, the migration of individuals between populations is decided dynamically. This paper gives a mathematical schema analysis of the method stating and showing that the algorithm exploits previously discovered knowledge for a more focused and concentrated search of heuristically high yielding regions while simultaneously performing a highly explorative search on the other regions of the search space. The effective performance of the algorithm is then shown using standard testbed functions and a set of actual classification datamining problems. Michigan style of classifier was used to build the classifier and the system was tested with machine learning databases of Pima Indian Diabetes database, Wisconsin Breast Cancer database and few others. The performance of our algorithm is better than others.     

A Tabu-enhanced genetic algorithm approach for assembly process planning

Over the past decade, much work has been done to optimize assembly process plans to improve productivity. Among them, genetic algorithms (GAs) are one of the most widely used techniques. Basically, GAs are optimization methodologies based on a direct analogy to Darwinian natural selection and genetics in biological systems. They can deal with complex product assembly planning. However, during the process, the neighborhood may converge too fast and limit the search to a local optimum prematurely. In a similar domain, Tabu search (TS) constitutes a meta-procedure that organizes and directs the operation of a search process. It is able to systematically impose and release constraints so as to permit the exploration of otherwise forbidden regions in a search space. This study attempts to combine the strengths of GAs and TS to realize a hybrid approach for optimal assembly process planning. More robust search behavior can possibly be obtained by incorporating the Tabus intensification and diversification strategies into GAs. The hybrid approach also takes into account assembly guidelines and assembly constraints in the derivation of near optimal assembly process plans. A case study on a cordless telephone assembly is used to demonstrate the approach. Results show that the assembly process plans obtained are superior to those derived by GA alone. The details of the hybrid approach and the case study are presented.     

A genetic algorithm for the optimisation of assembly sequences

This paper describes a Genetic Algorithm (GA) designed to optimise the Assembly Sequence Planning Problem (ASPP), an extremely diverse, large scale and highly constrained combinatorial problem. The modelling of the ASPP problem, which has to be able to encode any industrial-size product with realistic constraints, and the GA have been designed to accommodate any type of assembly plan and component. A number of specific modelling issues necessary for understanding the manner in which the algorithm works and how it relates to real-life problems, are succinctly presented, as they have to be taken into account/adapted/solved prior to Solving and Optimising (S/O) the problem. The GA has a classical structure but modified genetic operators, to avoid the combinatorial explosion. It works only with feasible assembly sequences and has the ability to search the entire solution space of full-scale, unabridged problems of industrial size. A case study illustrates the application of the proposed GA for a 25-components product.     

A genetic algorithm for interval nonlinear integer programming problem

In this paper, we formulate an optimal design of system reliability problem as a nonlinear integer programming problem with interval coefficients, transform it into a single objective nonlinear integer programming problem without interval coefficients, and solve it directly with keeping nonlinearity of the objective function by using Genetic Algorithms (GA). Also, we demonstrate the efficiency of this method with incomplete Fault Detecting and Switching (FDS) for allocating redundant units.     

A multiple minima genetic algorithm for protein structure prediction

Protein structure prediction (PSP) has a large potential for valuable biotechnological applications. However the prediction itself encompasses a difficult optimization problem with thousands of degrees of freedom and is associated with extremely complex energy landscapes. In this work a simplified three-dimensional protein model (hydrophobic-polar model, HP in a cubic lattice) was used in order to allow for the fast development of a robust and efficient genetic algorithm based methodology. The new methodology employs a phenotype based crowding mechanism for the maintenance of useful diversity within the populations, which resulted in increased performance and granted the algorithm multiple solutions capabilities. Tests against several benchmark HP sequences and comparative results showed that the proposed genetic algorithm is superior to other evolutionary algorithms. The proposed algorithm was then successfully adapted to an all-atom protein model and tested on poly-alanines. The native structure, an alpha helix, was found in all test cases as a local or a global minimum, in addition to other conformations with similar energies. The results showed that optimization strategies with multiple solutions capability present two advantages for PSP applications. The first one is a more efficient investigation of complex energy landscapes; the second one is an increase in the probability of finding native structures, even when they are not at the global optimum.     

A FORTRAN 90 genetic algorithm module for composite laminate structure design

The design of the stacking sequence for a composite laminate involves a set of discrete variables (plymaterial and ply orientation), and is thus well-suited to genetic algorithms for design optimization. Such algorithms have typically been custom-designed in FORTRAN 77 to suit specific optimization problems. Fortran 90 is a modern, powerful language with features that support important programming concepts, including those used in object-oriented programming. The Fortran 90 genetic algorithm module is used to define genetic data types, the functions which use these data types, and to provide a general framework for solving composite laminate structure design problems. The language's support of abstract data types is used to build genetic structures such as populations, subpopulations, individuals, chromosomes, and genes, and these data types are combined and manipulated by module subroutines. The use of abstract data types and long variable names makes the code useful and easily understood, while dynamic memory allocation makes the module flexible enough to be used in design problems of varying size and specification.     

A hybrid genetic algorithm for the single machine maximum lateness problem with release times and family setups

We consider the problem of scheduling a number of jobs, each job having a release time, a processing time, a due date and a family setup time, on a single machine with the objective of minimizing the maximum lateness. We develop a hybrid genetic algorithm and validate its performance on a newly developed diverse data set. We perform an extensive study of local search algorithms, based on the trade-off between intensification and diversification strategies, taking the characteristics of the problem into account. We combine different local search neighborhood structures in an intelligent manner to further improve the solution quality. We use the hybrid genetic algorithm to perform a comprehensive analysis of the influence of the different problem parameters on the average maximum lateness value and the performance of the algorithm(s).