The effects of two new crossover operators on genetic algorithm performance

Two new crossover operators in genetic algorithms for solving some combinatorial problems with ordering are presented. One is enhanced order crossover (EOX). The other, GREE, is a heuristic crossover for a class of combinatorial optimization problems, such as traveling salesman problems (TSPs). Genetic algorithms using GREE as unique crossover run very fast and get good solutions. Combining GREE with EOX, genetic algorithms can find optimal or very near optimal solutions in a rather short time. >

Genetic Algorithm(GA) is a guided random search and the guiding direction always aims at the family whose ancestors have schemata with high fitness.Based on the results,the crossover operation in GA was redesigned by using the principle of random uniform design sampling and combining the locale search strategy.Then a new GA called Genetic Algorithm based on Uniform Design Sampling(UDS) was presented.The new GA was applied to solve the 2-way graph partitioning problem.Compared to simple GA and good point GA for solving this problem,the simulation results show that the new GA has superiority in terms of speed and accuracy and overcomes premature convergence.

Based on Latin Hypercube Sampling method, the crossover operation in GA is redesigned; combined with immune mechanism, chromosome concentration is defined and clonal selection strategy is designed, thus an Immune Genetic Algorithm is given based on Latin Hypercube Sampling for solving the Maximum Clique Problem in this paper. The examples shows the new algorithm in solution quality, convergence speed, and other indicators is better than the classical genetic algorithm and good point set genetic algorithm. On the other hand, the new algorithm is not inferior to such classical algorithms as dynamic local search, and it got better solutions to some examples.KeywordsMaximum Clique Problem(MCP)Genetic Algorithm (GA)Latin Hypercube Sampling(LHS)Artificial Immune Systems(AIS)Immune Genetic Algorithm based on Latin Hypercube Sampling(LIGA)

Improved random selection strategy, self-adaptive crossover and mutation operators, population co-evolution algorithm are adopted in this paper to set up a new genetic algorithm(GA), guaranteeing the universality of population, the thoroughness of solution and the execution efficiency of algorithm in solving multi-process, process crossover, work-piece flow and other condition based scheduling problem of flexible manufacturing system(FMS). The problem of GA in solving FMS scheduling is summarized in this paper, reasons and countermeasures for GA's pre-maturing are studied, longitudinal and transverse comprehensive state-based correlative self-adaptive crossover and mutation operators are raised according to the analysis on GA to avoid local optimization and pre-maturity, the co-evolutionary GA is designed to solve the scheduling model for FMS, and the algorithm is validated for the scheduling of box-type parts for precise machine tools.

Crossover is an important operation in the Genetic Algorithms (GA). Crossover operation is responsible for producing offspring for the next generation so as to explore a much wider area of the solution space. There are many crossover operators designed to cater to different needs of different optimization problems. Despite the many analyses, it is still difficult to decide which crossover to use when. In this article, we have considered the various existing crossover operators based on the application for which they were designed for and the purpose that they were designed for. We have classified the existing crossover operators into two broad categories, namely (1) Crossover operators for representation of applications -- where the crossover operators designed to suit the representation aspect of applications are discussed along with how the crossover operators work and (2) Crossover operators for improving GA performance of applications -- where crossover operators designed to influence the quality of the solution and speed of GA are discussed. We have also come up with some interesting future directions in the area of designing new crossover operators as a result of our survey.

Crisscross optimization algorithm and its application

Crossover is the main genetic operator which influences the power of evolutionary algorithms. Among a variety of crossover operators, there has been a growing interest in multi-parent crossover operators in evolutionary computation. The main motivation of those schemes is establishing comprehensive collective collaboration of more than two chromosomes in the population to generate a new offspring. In this paper, a novel all-parent crossover operator called collective crossover for genetic algorithm is proposed. In this method, all individuals in the current population are involved in recombination part and one offspring is generated. The contribution of each individuals is defined based on its quality in terms of fitness value. The performance of the collective crossover operator is tested on CEC2017 benchmark functions. The results revealed that the proposed crossover operator performs better when compared to well-known two-parent crossover operators including one-point and two-point crossovers. In addition, the differences between collective crossover and the other crossover operators are statistically significant for the most cases.

We review the recent work done by our group on theoretically analyzing the behavior of genetic algorithms(GAs) and searching for new ideas and strategies to design more efficient GAs. By introducing the concept of degree of population diversity and using the tools from finite Markov chain, we presented fairly clear characterizations of premature convergence in GAs and proved some results on the relationships between premature convergence and GA’s control parameters such as the population size, the mutation and crossover probabilities, and some population statistics. In the mean time, we have also obtained a result that depicts the search ability of the crossover operators in GAs. An upper bound on the convergence rate for the GAs has been established. Based on the theoretical analyses, we have proposed a novel GA called Genetic Algorithm with No Genetic Operators (GANGO), which needs neither to maintain a population nor to use the conventional genetic operators, and yet has the same search mechanisms as the classical GAs. As another development in improving the performance of GAs, a new concept called Dual Fitness Function was proposed which, when incorporated into the classical GAs will enable the algorithms to judge whether the current population is in the local or global attractive basins. And in this way, the control parameters of GAs can be adjusted adaptively. Some applications of our results to fields such as fuzzy systems, multi-destination routing problem (MDR) are briefly

Genetic algorithms (GA) are one of the most successful techniques in solving combinatorial optimization problems. Its general character has enabled its application to different types of problems: vehicle routing, planning, scheduling, etc. This article shows that there is controversy in the basic structure of the algorithm steps when it is applied at routing problems. Specifically in this paper we show that the crossover (CX) offers no advantage in the optimization process. To solve such problems, the most important steps are mutation and selection of individuals. These two steps are what help to analyze the solution space exhaustively and give GA optimization capability. To prove our hypothesis we will analyze the results obtained by applying different blind crossover operators to solve multiple instances of the TSP (Travelling Salesman Problem).

BackgroundMining epistatic loci which affects specific phenotypic traits is an important research issue in the field of biology. Bayesian network (BN) is a graphical model which can express the relationship between genetic loci and phenotype. Until now, it has been widely used into epistasis mining in many research work. However, this method has two disadvantages: low learning efficiency and easy to fall into local optimum. Genetic algorithm has the excellence of rapid global search and avoiding falling into local optimum. It is scalable and easy to integrate with other algorithms. This work proposes an epistasis mining approach based on genetic tabu algorithm and Bayesian network (Epi-GTBN). It uses genetic algorithm into the heuristic search strategy of Bayesian network. The individual structure can be evolved through the genetic operations of selection, crossover and mutation. It can help to find the optimal network structure, and then further to mine the epistasis loci effectively. In order to enhance the diversity of the population and obtain a more effective global optimal solution, we use the tabu search strategy into the operations of crossover and mutation in genetic algorithm. It can help to accelerate the convergence of the algorithm.ResultsWe compared Epi-GTBN with other recent algorithms using both simulated and real datasets. The experimental results demonstrate that our method has much better epistasis detection accuracy in the case of not affecting the efficiency for different datasets.ConclusionsThe presented methodology (Epi-GTBN) is an effective method for epistasis detection, and it can be seen as an interesting addition to the arsenal used in complex traits analyses.

An empirical study of impact of crossover operators on the performance of non-binary genetic algorithm based neural approaches for classification

The wide usage of tensor computation in deep neural networks (DNNs) has boosted the high demand for high-performance and flexible library implementation on different hardware platforms, which is time-cost and inefficient. Deep learning compilers (DLCs) are therefore proposed, such as Ansor, to search the optimization computation combinations automatically. Ansor can generate high-performance tensor programs by employing Genetic Algorithm (GA) in its auto-tuning process. However, the structure information of an individual is easily destroyed by the uniform crossover operator, which leads to low search efficiency. In this paper, we propose a two-point crossover operator applied in Ansor called Ansor-TPC, which can optimize tensor computation with higher efficiency. The tensor expression can be computed with random schedules regarded as individuals. When performing the crossover operator, Ansor-TPC exchanges parent genes at two points instead of every point, which can preserve the structure information of programs and find the optimal schedule combination in the large search space. A high-performance program is generated for targeted hardware based on the optimized schedule configuration. Ansor-TPC is compared with the benchmarks at different levels. In terms of average performance, Ansor-TPC achieves 1.07--23.2× performance speedup. In terms of the best performance, Ansor-TPC outperforms by up to 1.06--23.0×.

In many industries including metallurgy, petrochemicals, paper, aerospace, pharmaceutical, electronics, ceramic and automotive manufacturing, the production system can contain a machine bottleneck which processes, in some cases, all the jobs. The management of this machine is crucial for the enterprise because it is responsible for delays in customers' orders delivery. The jobs scheduling on this machine is a way of approaching the problem and treats the whole production system. The single machine model provides a basis for more complicated environment such those seen in many real cases. Also, several studies have shown that several jobs, if not all, have time-dependent setup times. So, decision makers must therefore organize the jobs scheduling on this single machine by trying to minimize downtime while respecting the different deadlines. On the other hand, several resolution methods have been developed in literature to solve this kind of problem using approaching methods like metaheuristics or hybrid methods integrating exact methods. This thesis is in this direction. In this research, we propose several effective approaches to solve the single machine scheduling problem with sequence-dependent setup times with the objective to minimize total tardiness of the jobs. First, a new crossover operator in a genetic algorithm is proposed. This algorithm shows its ability to be competitive with the best approaches found in the literature on benchmark problems. We thus highlight the importance of incorporating specific problem knowledge into genetic operators, even if classical genetic operators could be used. However, the results obtained show that the proposed genetic algorithm is less efficient in comparison to the best resolution method found in the literature. Indeed, we noticed that the proposed algorithm lacks an intensification process for enhancing its. To overcome this shortcoming, we explore resolution class methods that showed promising prospects in the last decade. Even, the hybrid algorithms have achieved very good results in a wide variety of problems. In recent years, several researchers have introduced the hybridization of metaheuristics with exact methods. In fact, this kind of hybridization can be an attractive alternative because both methods have very different characteristics that can be combined to produce better results. Thus we explore the design of hybrid genetic algorithms improving the intensification process of the proposed genetic algorithm by integrating an exact method and mechanisms from other resolution methods to improve the performance. However, we find few approaches hybridizing metaheuristics and constraint programming in the literature to solve scheduling problems. In a second step, we propose a modeling for the total tardiness single machine with setup-dependent times scheduling problem using the constraint-based scheduling and the ILOG C++ API. The related experiments show that algorithm efficiency improves with specific tree search strategies and heuristic scheduling variables. Under prohibitive time computing, the proposed approach results are generally far from the best known solutions. However, we got interesting performance on small instances to consider allowing its hybridization with other resolution methods. In a third step, we introduce a hybrid approach based on the integration between genetic algorithm and constraint based scheduling approaches. This latter approach is integrated in the reproduction and the intensification processes of a genetic algorithm autonomously. Finally, we propose a hybrid algorithm which integrates several concepts from constraint programming, multi-objective optimization and ant colonies optimization in a crossover operator into a genetic algorithm. The proposed hybrid algorithms show excellent performance on benchmark problems from the literature by improving many of the best known solutions for some of them.

That genetic algorithm is applied to the assembly sequence planning of marine diesel engine can improve assembly planning efficiency a lot. The genetic algorithm crossover operator of genetic algorithm is improved. By combining the clashes matrix and priority relationship matrix, the relational-clashes matrix is established. In order to get the assembly sequence which can assembly safely and effectively, but conform to the actual assembly habits as well, the fitness function combines the feasibility of assembly sequence, the rationality of assembly sequence and the number of redirection. The evaluation method based on the general principle of assembly sequence was proposed for the first time. Priority of parts is evaluated according to their barycentric coordinates and precision level. The evaluation method can enrich the evaluation method of assembly sequences and expand the application of intelligent algorithms in the field. After some tests and analysis of the experimental results, the algorithm proved to be convergent and the results are effective.

There are numerous algorithms available for training artificial neural networks. Besides classical algorithms for supervised learning such as backpropagation, associative memory and radial basis function, this training task can be employed by evolutionary computation since most of the gradient descent related algorithms can be view as an application of optimization theory and stochastic search. In this paper, the logistic model of population growth from ecology is integrated into initialization, selection and crossover operators of genetic algorithms for neural network training. These chaotic operators are very efficient in maintaining the population diversity during the evolution process of genetic algorithms. A comparison is done on the basis of a benchmark comprising several data classification problems for neural networks. Three variants of training – Backpropagation (BP), Genetic Algorithms (GA) and Genetic Algorithms with Chaotic Operators (GACO) – are described and compared. The experimental results confirm the dynamic mobility of chaotic algorithms in GACO network training, which can overcome saturation and improve the convergence rate.KeywordsChaos theoryChaotic operatorEvolutionary algorithmsNeural networks training