Genetic Operators Crossover Research Articles

Black box optimization using evolutionary algorithm with novel selection and replacement strategies based on similarity between solutions

In the genetic algorithms, both crossover and mutation operators need one or more solutions from the population as inputs to be operated. Selection strategy decides which solutions should be selected as inputs of these operators. When a new solution is produced after applying one of these operators, the replacement strategy decides that is the new solution satiable to be inserted into the population, and if the answer is positive, then which of solutions in the population should be removed. The replacement plays a direct role in maintaining the diversity of the population, which is critical to avoid premature convergence problem. The selection effects on exploitation ability, which is vital to obtain high quality solutions. Where many of recent methods for the replacement and selection are time consuming or need complicated structures for the population, this paper proposes simple algorithms for the selection and the replacement, which are based on similarity between a pair of solutions.Result of experiments show how using the proposed strategies increases performance of genetic algorithm in terms of accuracy, on function optimization datasets. In addition, the proposed algorithms in this paper can be easily applied to different types of the population-based evolutionary algorithms. Results of experiments show how the proposed algorithms improve the performance of differential evolutionary algorithm in terms of accuracy, on variety of datasets including CEC-2015 Black Box Optimization.

Gravitational search algorithm and K-means for simultaneous feature selection and data clustering: a multi-objective approach

Clustering is an unsupervised classification method used to group the objects of an unlabeled data set. The high dimensional data sets generally comprise of irrelevant and redundant features also along with the relevant features which deteriorate the clustering result. Therefore, feature selection is necessary to select a subset of relevant features as it improves discrimination ability of the original set of features which helps in improving the clustering result. Though many metaheuristics have been suggested to select subset of the relevant features in wrapper framework based on some criteria, most of them are marred by the three key issues. First, they require objects class information a priori which is unknown in unsupervised feature selection. Second, feature subset selection is devised on a single validity measure; hence, it produces a single best solution biased toward the cardinality of the feature subset. Third, they find difficulty in avoiding local optima owing to lack of balancing in exploration and exploitation in the feature search space. To deal with the first issue, we use unsupervised feature selection method where no class information is required. To address the second issue, we follow pareto-based approach to obtain diverse trade-off solutions by optimizing conceptually contradicting validity measures silhouette index (Sil) and feature cardinality (d). For the third issue, we introduce genetic crossover operator to improve diversity in a recent Newtonian law of gravity-based metaheuristic binary gravitational search algorithm (BGSA) in multi-objective optimization scenario; it is named as improved multi-objective BGSA for feature selection (IMBGSAFS). We use ten real-world data sets for comparison of the IMBGSAFS results with three multi-objective methods MBGSA, MOPSO, and NSGA-II in wrapper framework and the Pearson’s linear correlation coefficient (FM-CC) as a multi-objective filter method. We employ four multi-objective quality measures convergence, diversity, coverage and ONVG. The obtained results show superiority of the IMBGSAFS over its competitors. An external clustering validity index F-measure also establish the above finding. As the decision maker picks only a single solution from the set of trade-off solutions, we employee the F-measure to select a final single solution from the external archive. The quality of final solution achieved by IMBGSAFS is superior over competitors in terms of clustering accuracy and/or smaller subset size.

A cloud model based DNA genetic algorithm for numerical optimization problems

Bio-inspired algorithms for optimization are significant topics in the areas of computational intelligence. Traditional genetic algorithm easily gets stuck at a local optimum, and often has slow convergent speed. To overcome these drawbacks, the Cloud model based genetic algorithm with DNA encoding (CM-DNAGA) is originally proposed in this study. The CM-DNAGA algorithm is based on not only the properties of randomness and stable tendency of the normal cloud model, but also the idea of GA with the bio-inspired coding method, i.e., DNA. In CM-DNAGA, a Y conditional normal cloud generator is used as the genetic crossover operator, and a basic normal cloud generator is used as the mutation operator. The simulation experiments are conducted on 12 numerical optimization functions, which evaluate the performance of the proposed algorithm. The experimental results indicate that the proposed method is a competitive optimizer in comparison with the three state-of-the-art heuristic algorithms, i.e. standard GA, PSO and RNA-GA.

An Improved Genetic Algorithm Approach on Mechanism Kinematic Structure Enumeration with Intelligent Manufacturing

During the process of mechanism kinematic structure enumeration, isomorphism identification of graphs is an important and complicated problem. The problem is known to be a NP-complete problem. In this paper, according to the mechanism kinematic chain isomorphism identification criteria, a highly efficient hybrid genetic algorithm model is proposed for isomorphism identification. The model method is coupled with genetic algorithm, optimal choice, and optimal crossover operation. It shows a quick convergence rate of the late operation and can avoid convergence to local optimum. Simulation results show that the hybrid algorithm is more rapid and effective compared with simple genetic algorithm and the improved neural network algorithm.

Comparative analysis of genetic crossover operators in knapsack problem

The Genetic Algorithm (GA) is an evolutionary algorithms and technique based on natural selections of individuals called chromosomes. In this paper, a method for solving Knapsack problem via GA (Genetic Algorithm) is presented. We compared six different crossovers: Crossover single point, Crossover Two point, Crossover Scattered, Crossover Heuristic, Crossover Arithmetic and Crossover Intermediate. Three different dimensions of knapsack problems are used to test the convergence of knapsack problem. Based on our experimental results, two point crossovers (TP) emerged the best result to solve knapsack problem.Keywords: Genetic Algorithm, Crossover, Heuristic, Arithmetic, Intermediate, Evolutionary Algorithm

A human–machine interaction approach of block erection schedule with three-dimensional spatial constraints

When the spatial constraints are taken into account, the problem about dispatch and optimization of block erection in shipbuilding becomes more complicated. A human–machine interaction approach is proposed and extended to quickly find an approximate optimal solution. First, a steer genetic algorithm enables users to guide the computing to an effective iterative direction and leverages the computing. The model of block erection dispatch to the crane is a parallel machine scheduling problem with spatial constraints. The genetic crossover operators can be guided according to the activities of block erection in shipbuilding. Two criteria are presented to justify the effectiveness of the proposed algorithm and a fitness function is given to represent the makespan. Moreover, three-dimensional spatial constraints, which affect the parallel machine scheduling problem heavily, are visualized. A better erection path can be obtained dynamically, when the users are in an immersive environment. Finally, a three-dimensional layout prototype system of block erection is developed with real size, embedded with an interactive genetic algorithm optimization to solve this problem with the objective of minimizing makespan.

Research on Improved Fuzzy Optimization Routing Problem in WSNs Based on Genetic Ant Colony Algorithm

The combination of traditional ant colony algorithm in solving the optimization process to consume a large amount of time, easily falling into local optimal solution and convergence is slow and other disadvantages, while also generating a lot of useless redundant iterative code, operation efficiency is low. Therefore, ant colony optimization algorithm is proposed. The algorithm based on genetic algorithm has the ability to search the global ant colony algorithm also has a parallel and positive feedback mechanisms. Changes in the use of genetic algorithm selection operator, crossover operator and mutation operator action to determine the distribution of pheromone on the path, the ant colony algorithm for feature selection using support vector machine classifiers for evaluating the performance characteristics of the feedback sub-Variorum And by changing the pheromone iteration, parameter selection and increase the local pheromone update feature nodes guided the re-combination. The algorithm uses probability expectation values are obtained to meet under the conditions with minimal sensor nodes, and gives the optimal coverage and connectivity probability models and reasoning. The experimental results show that, the algorithm can not only use the least nodes complete the effective target area to be covered, and in reducing the network energy consumption is also greatly improved, simultaneously reduces the cyber source configuration, improve the network life cycle.

Solving channel allocation problem using new genetic operators – An experimental approach

Summary Channel allocation schemes are required in mobile networks to allocate bandwidth and channels to mobile stations. The main objective of channel allocation is to achieve maximum efficiency by means of channel reuse by avoiding adjacent and co-channel interferences among nearby cells or networks that share the bandwidth. Channel allocation problem, an NP-hard problem, which means an exact solution cannot be found in polynomial time. Evolutionary and heuristic algorithms can be applied to find near optimal solutions to channel allocation. The main objective of this research is to design a new constraint based genetic crossover and mutation operators with the effective heuristic initialization to solve channel allocation with minimal computational complexity. The performances of the proposed genetic operators are compared with existing methods. It has been found that the proposed method significantly reduces the computational complexity.

Simplex particle swarm optimization with arithmetical crossover for solving global optimization problems

In this paper, we propose a new hybrid algorithm by combining the particle swarm optimization with a genetic arithmetical crossover operator after applying a modification on it in order to avoid the problem of stagnation and premature convergence of the population. In the final stage of the algorithm, we applied the Nelder-Mead method as a local search method in order to accelerate the convergence and avoid running the algorithm without any improvements in the results. We call the new proposed algorithm by simplex particle swarm optimization with a modified arithmetical crossover (SPSOAC). We test SPSOAC on 7 integer programming optimization benchmark functions, 10 minimax problems and 10 CEC05 functions. We present the general performance of the proposed algorithm by comparing SPSOAC against 13 benchmark algorithms. The Experiments results show the proposed algorithm is a promising algorithm and has a powerful performance.

Efficient Mutation Strategies Embedded in Laplacian-Biogeography-Based Optimization Algorithm for Unconstrained Function Minimization

Biogeography-Based optimization (BBO) is a nature inspired optimization technique that has excellent exploitation ability but the exploration ability needs to be improved to make it more robust. With this objective in mind, Garg and Deep proposed Laplacian BBO (LX-BBO) based on the Laplace Crossover which is a Real Coded Genetic Crossover Operator. It was concluded that LX- BBO outperforms its competitors. A natural question is to incorporate real coded mutation strategies into LX-BBO in order to improve its diversity. Therefore, in this paper, the exploring ability of LX-BBO is further investigated by using six different types of mutation operators present in literature. Gaussian, Cauchy, Levy, Power, Polynomial and Random mutation are used to test which mutation works best for LX-BBO. The performance of all these versions of BBO are measured on the benchmark problem set proposed in CEC 2014. On the basis of the criteria lay down by CEC, analysis of numerical and graphical results and statistical tests it is concluded that LX-BBO works best with Random and Cauchy Mutation.

An optimization method for composite structures with ply-drops

A genetic algorithm-based method is proposed to optimize the global stacking sequence of composite structures with ply-drops. To avoid the design space exploration problems in existing optimization methods, the prerequisites for the continuity between laminated composites are firstly studied and the continuity rules are summarized. To implement these rules in the evolutionary optimization, two newly constructed chromosomes are developed to encode the global stacking sequence with no additional chromosomal repair. Genetic operators, including mutation, swapping and crossover operators, are also developed to explore the design space sufficiently and meanwhile follow the continuity rules. A typical multi-laminate-panel structure is optimized to verify the proposed method. It is found that compared with existing methods, solutions with lower weights have been obtained with an acceptable efficiency in both symmetry and symmetry-balance constraint cases. The results reveal that with the proposed optimization method, the weight of composite structures could be further reduced.

HYBRID SHUFFLE FROG LEAPING ALGORITHM AND GENETIC ALGORITHM FOR ECONOMIC LOAD DISPATCH WITH WIND POWER UNITS

Economic load dispatch (ELD) problem considering valve point effect and wind power is a large scale mixed-integer nonlinear problem. Solving this problem is one of the critical tasks in electric power system operation. So, proposing an accurate method to solve this problem is of great interest. Shuffle frog leaping algorithm (SFLA) is recently proposed to solve many optimization problems but it has some problems. It is often being trapped in local optima. In this paper, a hybrid shuffle frog leaping algorithm and genetic algorithm (HSFLAGA) is proposed to solve this problem. The proposed algorithm can be derived by combining the SFLA and genetic crossover and mutation operators so that the drawbacks of original SFLA algorithm can be treated before employing it to solve the ELD problem with valve point effect and wind power. To show the effectiveness of the HSFLAGA algorithm, several test systems with different numbers of generating units are used. The results of the proposed HSFLAGA algorithm are compared with those obtained by other published methods employing same test systems. The obtained results prove the efficiency and the superiority of HSFLAGA algorithm over other published methods.

A study ofpolygradient media structure regularities

We have proved that the choice of the structure of poligradient media is one of the most important stages in new designs of magnetic separators. Ferromagnetic solids are considered as generating elements of the internal structure of poligradient media, which are elementary monostructuresof various geometric forms that, in terms of genetic concepts, are the parental chromosomes. We have specified that the genetic synthesis algorithms are based on genetic synthesis operators—in particular, on the genetic operators of crossover, replication, mutation,and spatial inversion. We have proved that the problem of selecting a poligradient medium in the working bodies of the separator must be solved through structural synthesis and, in the future, taking into account the properties of the medium, also parametric synthesis. Using genetic operators, we have synthesized an inner structure of a poligradient medium, in which an elementary monostructure generating unit is an isosceles triangle-shaped plate. The reliability of the research findings has been confirmed.

A Novel Hybrid Multi–objective BB–BC based Channel Allocation Algorithm to Reduce FWM Crosstalk and its Comparative Study

is a good source of inspirations for us. The algorithms developed from the nature are most powerful algorithms for optimizing many complex engineering design problems having multiple objectives (multi-objective). This paper presents an hybrid algorithm based on Multi-objective Big bang-Big Crunch (MOBB-BC) nature-inspired optimization algorithm with Genetic crossover and Differential evolution (DE) mutation operators for solving the minimum length ruler called Optimal Golomb ruler (OGR) as channel-allocation problem to reduce four-wave mixing crosstalk (FWM) effects in optical wavelength division multiplexing (WDM) systems. The comparative study of simulation results obtained by proposed hybrid Multi-objective BB-BC (HMOBB-BC) algorithm demonstrates better and efficient generation of OGRs in a reasonable computational time compared to simple BB-BC algorithm and one of the existing nature-inspired algorithms i.e. Genetic algorithm (GA). Also, the proposed hybrid algorithm outperforms the two existing conventional algorithms i.e. Extended quadratic congruence (EQC) and Search algorithm (SA), in terms of ruler length and total channel bandwidth.

Hybrid Particle Swarm Optimization with a Modified Arithmetical Crossover for Solving Unconstrained Optimization Problems

In this article, we propose a new hybrid algorithm by combining the particle swarm optimization and genetic arithmetical crossover operator. We adjust the proposed algorithm in order to avoid the problem of stagnation and premature convergence of the population. Invoking the modified arithmetical crossover operator improves the exploration process of the proposed algorithm. We call the new proposed algorithm hybrid particle swarm optimization with a modified arithmetical crossover (HPSOAC). Also, we test HPSOAC on 26 functions (16 unconstrained optimization benchmark functions and 10 CEC05 special session functions). Furthermore, we compare the general performance of the proposed algorithm against 6 various particle swarm optimization algorithms. Moreover, we show the efficiency of the proposed algorithm and its ability to solve unconstrained optimization problems by giving several computational results.

Voltage stability enhancement using VSC-OPF including wind farms based on Genetic algorithm

Abstract This paper describes the impact of wind generation to enhance the voltage stability of power system in optimal power flow problem. In this work, the Voltage Stability Constrained Optimal Power Flow (VSCOPF) algorithm is used, which combines the economical aspects and the voltage stability control of power system networks. A voltage stability index called L -index has been utilized to identify the most sensitive node prone to voltage collapse. Here Improved Genetic Algorithm (IGA) with mixed form of representation has been used for multi-objective formulation. Real power setting and voltage magnitudes are represented as floating point numbers and transformer tap settings and capacitors as integers. For effecting genetic processing, crossover and mutation operator, which can be directly deal with floating point number and integers, are used. The IGA has been implemented on IEEE 30 bus system to study the impact of wind farm on voltage stability. The obtained simulation shows the effectiveness of Improved Genetic algorithm on voltage stability of the power systems.

Genetic mechanism-based coupling algorithm for solving coordinated scheduling problems of yard systems in container terminals

This study develops models and methods utilized for solving the coordination scheduling problem in the yard of a container terminal. Based on the information shared by the yard storage subsystem and the YC scheduling subsystem, and the interaction between these subsystems, a coordination scheduling model, which is composed of a storage subsystem model, a YC scheduling subsystem and a coordinate controller model, is developed. A coupling algorithm, which is based on a genetic mechanism, is developed to solve the coordination scheduling problem. The algorithm adopts the genetic selection, crossover and mutation operations to adjust the yard storage plan and the YC scheduling plan. The performance of the coordination scheduling model and that of the proposed coupling algorithm are confirmed with reference to a numerical example.

The regulatory algorithm (RGA): a two-dimensional extension of evolutionary algorithms

In orientation to new developments in evolutionary biology we propose an extension of evolutionary algorithms in two dimensions, the regulatory algorithm (RGA). It consists of two levels of vectors, the regulatory vector and the structural vector. Each element of the regulatory vector is connected with one or several elements of the structural vector, but not vice versa. The connections can be interpreted as steering connections, the switching on or off of the structural elements and/or as switching orders for the structural elements. An RGA that operates with the usual genetic operators of mutation and crossover can be used for avoiding rules like penalty or default operators, it is in certain problems significantly faster than a standard genetic algorithm, and it is very suited when modeling and optimizing systems that consist themselves of different levels. Examples of RGA usage are shown, namely, the optimal dividing of socially deviant youths in a hostel, the optimal introduction of communication standards in information systems, and the allocation of employees to superiors by taking into regard the different personality types.

Designing optical coatings by means of genetic algorithms

This paper presents a new method of designing optical coatings, using evolutionary strategies based on genetic algorithms. It discusses methods of encoding alternative solutions and genetic operators of crossover, selection, genetic pressure, and mutation as applied to problems of synthesizing multilayer thin-film systems. It shows that these operators affect the rate at which the algorithm converges. The possibilities of the method are illustrated, using the design of broad-band antireflection coatings for items made from germanium as an example.

Computer aided product design tool for sustainable product development

A computer aided product design (CAPD) tool is proposed that finds mixtures matching target properties. Genetic algorithm crossover and mutation operators are completed with insertion or deletion operators adapted for side branches. A new substitution operator is devised for cyclic molecules. The mixture fitness is evaluated by a weighted sum of property performances. Molecules are represented by molecular graphs. They are split into molecular fragments which are built from polyatomic groups. Molecules or molecular fragments can be fixed, constrained or left free for building a new molecule. Building blocks are chemical functional groups or bio-sourced synthons. A specific coding of hydrogen-suppressed atoms is devised that can be used with various property estimation models where atom connectivity information is required. Illustration is provided through three case studies to find levulinic, glycerol and bio-based derivatives as substitute for chlorinated paraffin, methyl p-coumarate ester solvent and blanket wash solvent, respectively.