Showing papers on "Crossover published in 2015"
TL;DR: A new kind of bio-inspired metaheuristic algorithm, called earthworm optimisation algorithm (EWA), is proposed in this paper and the results show that EWA23 performs the best and it can find the better fitness on most benchmarks than others.
Abstract: Earthworms can aerate the soil with their burrowing action and enrich the soil with their waste nutrients. Inspired by the earthworm contribution in nature, a new kind of bio-inspired metaheuristic algorithm, called earthworm optimisation algorithm (EWA), is proposed in this paper. The EWA method is inspired by the two kinds of reproduction (Reproduction 1 and Reproduction 2) of the earthworms. Reproduction 1 generates only one offspring by itself. Reproduction 2 is to generate one or more than one offspring at one time, and this can successfully be done by nine improved crossover operators. In addition, Cauchy mutation (CM) is added to EWA method. Nine different EWA methods with one, two and three offsprings based on nine improved crossover operators are respectively proposed. The results show that EWA23 performs the best and it can find the better fitness on most benchmarks than others.
350 citations
TL;DR: This work designs a new crossover-based genetic algorithm that uses mutation with a higher-than-usual mutation probability to increase the exploration speed and crossover with the parent to repair losses incurred by the more aggressive mutation.
208 citations
TL;DR: The proposed eigenvector-based crossover operator utilizes eigenvectors of covariance matrix of individual solutions, which makes the crossover rotationally invariant, and can be applied to any crossover strategy with minimal changes.
Abstract: Differential evolution has been shown to be an effective methodology for solving optimization problems over continuous space. In this paper, we propose an eigenvector-based crossover operator. The proposed operator utilizes eigenvectors of covariance matrix of individual solutions, which makes the crossover rotationally invariant. More specifically, the donor vectors during crossover are modified, by projecting each donor vector onto the eigenvector basis that provides an alternative coordinate system. The proposed operator can be applied to any crossover strategy with minimal changes. The experimental results show that the proposed operator significantly improves DE performance on a set of 54 test functions in CEC 2011, BBOB 2012, and CEC 2013 benchmark sets.
194 citations
TL;DR: The researcher explored the problems embedded in this process, attempted to find solutions such as the way of choosing mutation probability and fitness function, and chose Cranfield English Corpus test collection on mathematics, and concluded that the authors might have several improvements when using adaptive genetic algorithms.
Abstract: Genetic algorithms are usually used in information retrieval systems (IRs) to enhance the information retrieval process, and to increase the efficiency of the optimal information retrieval in order to meet the users' needs and help them find what they want exactly among the growing numbers of available information. The improvement of adaptive genetic algorithms helps to retrieve the information needed by the user accurately, reduces the retrieved relevant files and excludes irrelevant files. In this study, the researcher explored the problems embedded in this process, attempted to find solutions such as the way of choosing mutation probability and fitness function, and chose Cranfield English Corpus test collection on mathematics. Such collection was conducted by Cyrial Cleverdon and used at the University of Cranfield in 1960 containing 1400 documents, and 225 queries for simulation purposes. The researcher also used cosine similarity and jaccards to compute similarity between the query and documents, and used two proposed adaptive fitness function, mutation operators as well as adaptive crossover. The process aimed at evaluating the effectiveness of results according to the measures of precision and recall. Finally, the study concluded that we might have several improvements when using adaptive genetic algorithms. �
191 citations
TL;DR: The findings reveal that the hybrid optimization strategy proposed here may be used as a promising alternative forecasting tool for higher forecasting accuracy and better generalization ability and to avoid premature convergence.
181 citations
01 Oct 2015
TL;DR: This paper will help researchers in selecting appropriate crossover operator for better results and contains description about classical standard crossover operators, binary crossover operator, and application dependant crossover operators.
Abstract: The performance of Genetic Algorithm (GA) depends on various operators. Crossover operator is one of them. Crossover operators are mainly classified as application dependent crossover operators and application independent crossover operators. Effect of crossover operators in GA is application as well as encoding dependent. This paper will help researchers in selecting appropriate crossover operator for better results. The paper contains description about classical standard crossover operators, binary crossover operators, and application dependant crossover operators. Each crossover operator has its own advantages and disadvantages under various circumstances. This paper reviews the crossover operators proposed and experimented by various researchers.
165 citations
TL;DR: In this article, a distribution network reconfiguration method is presented for both the indices of power loss reduction and reliability improvement, which is based on the information of a single loop caused by closing a normally open switch.
154 citations
TL;DR: An effective and efficient successful-parent-selecting framework is proposed to improve the performance of differential evolution by providing an alternative for the selection of parents during mutation and crossover.
Abstract: An effective and efficient successful-parent-selecting framework is proposed to improve the performance of differential evolution (DE) by providing an alternative for the selection of parents during mutation and crossover. The proposed method adapts the selection of parents by storing successful solutions into an archive, and the parents are selected from the archive when a solution is continuously not updated for an unacceptable amount of time. The proposed framework provides more promising solutions to guide the evolution and effectively helps DE escaping the situation of stagnation. The simulation results show that the proposed framework significantly improves the performance of two original DEs and six state-of-the-art algorithms in four real-world optimization problems and 30 benchmark functions.
146 citations
TL;DR: In this paper, an effective teaching–learning-based optimization algorithm (TLBO) is proposed to solve the flexible job-shop problem with fuzzy processing time (FJSPF).
140 citations
TL;DR: A novel binary version of the artificial bee colony algorithm based on genetic operators (GB-ABC) such as crossover and swap to solve binary optimization problems and is the most suitable algorithm in binary optimization when compared with the other well-known existing binary optimization algorithms.
138 citations
25 May 2015
TL;DR: A self-optimization approach and a new success-history based adaptive differential evolution with linear population size reduction (L-SHADE) which is incorporated with an eigenvector-based (EIG) crossover and a successful-parent-selecting (SPS) framework are proposed in this paper.
Abstract: A self-optimization approach and a new success-history based adaptive differential evolution with linear population size reduction (L-SHADE) which is incorporated with an eigenvector-based (EIG) crossover and a successful-parent-selecting (SPS) framework are proposed in this paper. The EIG crossover is a rotationally invariant operator which provides superior performance on numerical optimization problems with highly correlated variables. The SPS framework provides an alternative of the selection of parents to prevent the situation of stagnation. The proposed SPS-L-SHADE-EIG combines the L-SHADE with the EIG and SPS frameworks. To further improve the performance, the parameters of SPS-L-SHADE-EIG are self-optimized in terms of each function under IEEE Congress on Evolutionary Computation (CEC) benchmark set in 2015. The stochastic population search causes the performance of SPS-L-SHADE-EIG noisy, and therefore we deal with the noise by re-evaluating the parameters if the parameters are not updated for more than an unacceptable amount of times. The experiment evaluates the performance of the self-optimized SPS-L-SHADE-EIG in CEC 2015 real-parameter single objective optimization competition.
TL;DR: Experimental results show that the DE operators can improve diversity and avoid prematurity effectively, and the hybrid method outperforms both the FA and the DE on the selected benchmark functions.
TL;DR: An improved analysis of the Simple Genetic Algorithm for the OneMax problem overcomes some limitations and presents a technique to bound the diversity of the population that does not require a bound on its bandwidth.
TL;DR: Recent work from the laboratory supporting the idea that all 3 of these aspects are intrinsic consequences of a single basic process and suggesting that the underlying logic of this process corresponds to that embodied in a particular (beam-film) model.
Abstract: During meiosis, crossover recombination is tightly regulated. A spatial patterning phenomenon known as interference ensures that crossovers are well-spaced along the chromosomes. Additionally, every pair of homologs acquires at least one crossover. A third feature, crossover homeostasis, buffers the system such that the number of crossovers remains steady despite decreases or increases in the number of earlier recombinational interactions. Here we summarize recent work from our laboratory supporting the idea that all 3 of these aspects are intrinsic consequences of a single basic process and suggesting that the underlying logic of this process corresponds to that embodied in a particular (beam-film) model.
TL;DR: A novel adaptive scaling factor and a dynamic crossover probability are presented to improve the adaptive and dynamic performance of differential evolution algorithm, and two kinds of neighborhood search operations based on the bee colony foraging mechanism are introduced.
TL;DR: In this article, a discrete artificial bee colony (ABC) algorithm is presented to solve the above scheduling problem with a makespan criterion by incorporating the ABC with differential evolution (DE), which contains three key operators.
Abstract: A flow-shop scheduling problem with blocking has important applications in a variety of industrial systems but is underrepresented in the research literature. In this study, a novel discrete artificial bee colony (ABC) algorithm is presented to solve the above scheduling problem with a makespan criterion by incorporating the ABC with differential evolution (DE). The proposed algorithm (DE-ABC) contains three key operators. One is related to the employed bee operator (i.e. adopting mutation and crossover operators of discrete DE to generate solutions with good quality); the second is concerned with the onlooker bee operator, which modifies the selected solutions using insert or swap operators based on the self-adaptive strategy; and the last is for the local search, that is, the insert-neighbourhood-based local search with a small probability is adopted to improve the algorithm's capability in exploitation. The performance of the proposed DE-ABC algorithm is empirically evaluated by applying it to well-kno...
TL;DR: A novel LSSVM for effective prediction of daily building energy consumption is designed by utilizing a hybrid of the direct search optimization (DSO) algorithm and RCGA, called the DSORCGA, which differs from the conventional RCGA in terms of the reproduction operator and the crossover operator, and is used to optimize free parameters of L SSVM for faster computation speed and higher predictive accuracy.
TL;DR: It is indicated that semantic backpropagation helps evolution to identify the desired intermediate computation states and makes the search process more efficient.
Abstract: In genetic programming, a search algorithm is expected to produce a program that achieves the desired final computation state (desired output). To reach that state, an executing program needs to traverse certain intermediate computation states. An evolutionary search process is expected to autonomously discover such states. This can be difficult for nontrivial tasks that require long programs to be solved. The semantic backpropagation algorithm proposed in this paper heuristically inverts the execution of evolving programs to determine the desired intermediate computation states. Two search operators, random desired operator and approximately geometric semantic crossover, use the intermediate states determined by semantic backpropagation to define subtasks of the original programming task, which are then solved using an exhaustive search. The operators outperform the standard genetic search operators and other semantic-aware operators when compared on a suite of symbolic regression and Boolean benchmarks. This result and additional analysis conducted in this paper indicate that semantic backpropagation helps evolution to identify the desired intermediate computation states and makes the search process more efficient.
TL;DR: It is contended that the use of crossover (mixed research) graphical displays enhances researchers’ understanding of social and behavioral phenomena in general and the meaning that underlies these phenomena in particular.
Abstract: In this paper, we introduce various graphical methods that can be used to represent data in mixed research. First, we present a broad taxonomy of visual representation. Next, we use this taxonomy to provide an overview of visual techniques for quantitative data display and qualitative data display. Then, we propose what we call “crossover” visual extensions to summarize and integrate both qualitative and quantitative results within the same framework. We provide several examples of crossover (mixed research) graphical displays that illustrate this natural extension. In so doing, we contend that the use of crossover (mixed research) graphical displays enhances researchers’ understanding (i.e., increased Verstehen) of social and behavioral phenomena in general and the meaning that underlies these phenomena in particular. Key Words: Graphic Methods, Visual Techniques, Graphical Displays, Crossover Graphical Displays, and Mixed Research
TL;DR: A self-adaptive DE algorithm with discrete mutation control parameters (DMPSADE) is proposed that was compared with 8 state-of-the-art DE variants and 3 non-DE algorithms by using 25 benchmark functions and indicates that the average performance of DMPSADE is better than those of all other competitors.
Abstract: In DMPSADE, control parameters and mutation strategies could be automatically adjusted.We first proposed a new encoding for parameter control in DE algorithm.Roulette wheel is used to implement the selection of mutation strategies. Generally, the optimization problem has different relationships (i.e., linear, approximately linear, non-linear, or highly non-linear) with different optimized variables. The choices of control parameters and mutation strategies would directly affect the performance of differential evolution (DE) algorithm in satisfying the evolution requirement of each optimized variable and balancing its exploitation and exploration capabilities. Therefore, a self-adaptive DE algorithm with discrete mutation control parameters (DMPSADE) is proposed. In DMPSADE, each variable of each individual has its own mutation control parameter, and each individual has its own crossover control parameter and mutation strategy. DMPSADE was compared with 8 state-of-the-art DE variants and 3 non-DE algorithms by using 25 benchmark functions. The statistical results indicate that the average performance of DMPSADE is better than those of all other competitors.
TL;DR: This work proposes a powerful population-based memetic algorithm, called BMA, which is able to attain the best-known results for 133 out of 135 QAP benchmark instances and thus competes very favorably with the current most effective QAP approaches.
Abstract: We present a memetic algorithm (called BMA) for the well-known QAP.BMA integrates BLS within the population-based evolutionary computing framework.BMA is able to attain the best-known results for 133 out of 135 QAP benchmark instances.We provide insights on search landscapes and crossover operators for QAP. The quadratic assignment problem (QAP) is one of the most studied NP-hard problems with various practical applications. In this work, we propose a powerful population-based memetic algorithm (called BMA) for QAP. BMA integrates an effective local optimization algorithm called Breakout Local Search (BLS) within the evolutionary computing framework which itself is based on a uniform crossover, a fitness-based pool updating strategy and an adaptive mutation procedure. Extensive computational studies on the set of 135 well-known benchmark instances from the QAPLIB revealed that the proposed algorithm is able to attain the best-known results for 133 instances and thus competes very favorably with the current most effective QAP approaches. A study of the search landscape and crossover operators is also proposed to shed light on the behavior of the algorithm.
TL;DR: In this paper, a crisscross optimization (CSO) algorithm is implemented to solve the large scale CHPED problem, which is a challenging non-convex optimization problem with a large number of local minima.
TL;DR: The data are consistent with the view that diversification of worker behavior, but not immune function, is a driver of the high crossing-over rate in bees, and demonstrate that high non-crossover rates are not a necessary consequence of high recombination rates.
Abstract: Social hymenoptera, the honey bee (Apis mellifera) in particular, have ultra-high crossover rates and a large degree of intra-genomic variation in crossover rates. Aligned with haploid genomics of males, this makes them a potential model for examining the causes and consequences of crossing over. To address why social insects have such high crossing-over rates and the consequences of this, we constructed a high-resolution recombination atlas by sequencing 55 individuals from three colonies with an average marker density of 314 bp/marker. We find crossing over to be especially high in proximity to genes upregulated in worker brains, but see no evidence for a coupling with immune-related functioning. We detect only a low rate of non-crossover gene conversion, contrary to current evidence. This is in striking contrast to the ultrahigh crossing-over rate, almost double that previously estimated from lower resolution data. We robustly recover the predicted intragenomic correlations between crossing over and both population level diversity and GC content, which could be best explained as indirect and direct consequences of crossing over, respectively. Our data are consistent with the view that diversification of worker behavior, but not immune function, is a driver of the high crossing-over rate in bees. While we see both high diversity and high GC content associated with high crossing-over rates, our estimate of the low non-crossover rate demonstrates that high non-crossover rates are not a necessary consequence of high recombination rates.
TL;DR: A novel artificial fish swarm algorithm (NAFSA) is proposed for solving large-scale reliability-redundancy allocation problem (RAP) and shows good performance in terms of computational accuracy and computational efficiency for large scale RAP.
Abstract: A novel artificial fish swarm algorithm (NAFSA) is proposed for solving large-scale reliability-redundancy allocation problem (RAP). In NAFSA, the social behaviors of fish swarm are classified in three ways: foraging behavior, reproductive behavior, and random behavior. The foraging behavior designs two position-updating strategies. And, the selection and crossover operators are applied to define the reproductive ability of an artificial fish. For the random behavior, which is essentially a mutation strategy, the basic cloud generator is used as the mutation operator. Finally, numerical results of four benchmark problems and a large-scale RAP are reported and compared. NAFSA shows good performance in terms of computational accuracy and computational efficiency for large scale RAP.
TL;DR: The performance of the proposed RGA-RDD is superior to comparative methods in locating the global optimum for real-parameter optimization problems, especially for unsolved multimodal and high-dimensional hybrid functions.
11 Jul 2015
TL;DR: In this paper, Doerr et al. showed that the one-fifth success rule for step-size adaption in evolutionary strategies can be used to dynamically choose best-possible parameters during the optimization process.
Abstract: While evolutionary algorithms are known to be very successful for a broad range of applications, the algorithm designer is often left with many algorithmic choices, for example, the size of the population, the mutation rates, and the crossover rates of the algorithm. These parameters are known to have a crucial influence on the optimization time, and thus need to be chosen carefully, a task that often requires substantial efforts. Moreover, the optimal parameters can change during the optimization process. It is therefore of great interest to design mechanisms that dynamically choose best-possible parameters. An example for such an update mechanism is the one-fifth success rule for step-size adaption in evolutionary strategies. While in continuous domains this principle is well understood also from a mathematical point of view, no comparable theory is available for problems in discrete domains. In this work we show that the one-fifth success rule can be effective also in discrete settings. We regard the (1+(λ,λ)) GA proposed in [Doerr/Doerr/Ebel: From black-box complexity to designing new genetic algorithms, TCS 2015]. We prove that if its population size is chosen according to the one-fifth success rule then the expected optimization time on OneMax is linear. This is better than what any static population size λ can achieve and is asymptotically optimal also among all adaptive parameter choices.
TL;DR: In this article, a population-based metaheuristic is proposed to solve the pickup and delivery problem with time windows and last-in-first-out (LIFO) loading.
01 Nov 2015
TL;DR: A novel approach is proposed to improve the classification performance of a polynomial neural network (PNN) based on all possible combinations of two features of the training input patterns of a dataset.
Abstract: In this paper, a novel approach is proposed to improve the classification performance of a polynomial neural network (PNN). In this approach, the partial descriptions (PDs) are generated at the first layer based on all possible combinations of two features of the training input patterns of a dataset. The set of PDs from the first layer, the set of all input features, and a bias constitute the chromosome of the real-coded genetic algorithm (RCGA). A system of equations is solved to determine the values of the real coefficients of each chromosome of the RCGA for the training dataset with the mean classification accuracy (CA) as the fitness value of each chromosome. To adjust these values for unknown testing patterns, the RCGA is iterated in the usual manner using simple selection, crossover, mutation, and elitist selection. The method is tested extensively with the University of California, Irvine benchmark datasets by utilizing tenfold cross validation of each dataset, and the performance is compared with various well-known state-of-the-art techniques. The results obtained from the proposed method in terms of CA are superior and outperform other known methods on various datasets.
TL;DR: Results show that the proposed approach can outperform ABC-based approaches for constrained optimization problems in terms of the quality of the results, robustness and convergence speed, and provides better results in most cases compared with other state-of-the-art algorithms.
Abstract: Artificial bee colony (ABC) algorithm represents one of the most-studied swarm intelligence algorithms. Since the original ABC has been found to be very effective, today there are a lot of improved variants of ABC algorithm used to solve a wide range of hard optimization problems. This paper describes a novel artificial bee colony algorithm for constrained optimization problems. In the proposed algorithm, five modifications are introduced. Firstly, to improve the exploitation abilities of ABC, two different modified ABC search operators are used in employed and onlooker phases, and crossover operator is used in scout phase instead of random search. Secondly, modifications related to dynamic tolerance for handling equality constraints and improved boundary constraint-handling method are employed. The experimental results, obtained by testing on a set of 24 well-known benchmark functions and four widely used engineering design problems, show that the proposed approach can outperform ABC-based approaches for constrained optimization problems in terms of the quality of the results, robustness and convergence speed. Additionally, it provides better results in most cases compared with other state-of-the-art algorithms.
TL;DR: In this article, a crossover model is developed to account rigorously for the crossover of vanadium ions through the membrane and resultant side reactions occurring in both positive and negative electrodes, and numerically coupled with previously developed three-dimensional (3-D), transient, thermal VRFB model in which key physicochemical phenomena including the electrochemical reactions, waste heat generation, resultant species and heat transport are all included.