China 
Africa 
Explore chapters and articles related to this topic
Introduction to Neural Networks, Fuzzy Systems, Genetic Algorithms, and their Fusion
Published in Lakhmi C. Jain, N.M. Martin, Fusion of Neural Networks, Fuzzy Systems, and Genetic Algorithms, 2020
Starting from an initial population of strings (representing possible solutions), the GA uses these operators to calculate successive generations. First, pairs of individuals of the current population are selected to mate with each other to form the offspring, which then form the next generation. Selection is based on the survival-of-the-fittest strategy, but the key idea is to select the better individuals of the population, as in tournament selection, where the participants compete with each other to remain in the population. The most commonly used strategy to select pairs of individuals is the method of roulette-wheel selection, in which every string is assigned a slot in a simulated wheel sized in proportion to the string’s relative fitness. This ensures that highly fit strings have a greater probability to be selected to form the next generation through crossover and mutation. After selection of the pairs of parent strings, the crossover operator is applied to each of these pairs.
Evolutionary Computation
Published in Anand Nayyar, Dac-Nhuong Le, Nhu Gia Nguyen, Advances in Swarm Intelligence for Optimizing Problems in Computer Science, 2018
Anand Nayyar, Surbhi Garg, Deepak Gupta, Ashish Khanna
Having said that, evolutionary computational techniques have a set of common features, but they also have distinctive features that can be seen by digging into the level of abstraction. They may differ in terms of data structure used and consequently the ‘genetic’ operators. Even a particular technique may exhibit various forms and twists. For example, selection of individuals can be done by applying numerous approaches such as: Proportional selection, in which the chances of selection increase with the fitness of an individual, implying the probability of selection is proportional to fitness. Detailing further, it may require use of scaling windows or truncation methods.The ranking method, in which individuals are ranked on a scale of best to worst with a fixed probability of selection for complete process of evolution. Moreover, probability may be a linear or non-linear representation.Tournament selection, where the next generation is selected on the basis of competition of a number of individuals (generally two), and the competition step is iterated a population size number of times. Tournament selection methods depend largely on the size of tournaments.
Genetic Algorithm for Input Assignment for Decoded-PLAs
Published in Hafiz Md. Hasan Babu, VLSI Circuits and Embedded Systems, 2023
The objective of the GA is to converge to an optimal individual, and selection pressure is the driving force which determines the rate of convergence. A high selection pressure will cause the population to converge quickly, possibly at the expense of a sub optimal result. Roulette wheel selection typically provides the highest selection pressure in the initial generations, especially when a few individuals have significantly higher fitness values than other individuals. Tournament selection provides more pressure in later generations when the fitness values of individuals are not significantly different. Thus, roulette wheel selection is more likely to converge to a suboptimal result if individuals have large variations in fitness values.
A novel heuristic method for the energy-efficient flexible job-shop scheduling problem with sequence-dependent set-up and transportation time
Published in Engineering Optimization, 2022
Hongliang Zhang, Gongjie Xu, Ruilin Pan, Haijiang Ge
To obtain the optimal solution set, the algorithm iterates until the termination criterion is satisfied. For each iteration i, genetic operators are used to obtain the updated Si′. Tournament selection is used to choose the individuals for reproduction, in which the non-dominated rank and crowding distance value determine whether an individual is selected or not (Deb et al. 2002). For the crossover operator, the multi-point preservative crossover (MPX) is adopted for MA (Zheng, Wang, and Wang 2014) and the improved precedence operation crossover (IPOX) is employed for OS (Wang et al. 2012). The two crossover operators can not only preserve the excellent information from parents to offspring, but also ensure that the updated Si is feasible (Türkyılmaz and Bulkan 2014). For the mutation operator, the assignment mutation and swap mutation are applied to MA and OS, respectively.
A new colour image copyright protection approach using evolution-based dual watermarking
Published in Journal of Experimental & Theoretical Artificial Intelligence, 2021
Saad M. Darwish, Osama F. Hassan
Q is the feasibility predicate (different operators-selection, crossover, and mutation). The crossover is the process of exchanging the parent’s genes to produce one or two offspring that carry inherent genes from both parents to increase the diversity of the mutated individuals (Soni & Kumar, 2014). Herein, a single point crossover is employed because of its simplicity. The purpose of mutation is to prevent falling into a locally optimal solution of the solved problem (Zhang et al., 2013); a uniform mutation is employed for its simple implementation. The selection operator retains the best fitting chromosome of one generation and selects the fixed numbers of parent chromosomes. Tournament selection is probably the most popular selection method in a genetic algorithm due to its efficiency and simple implementation (Razali & Geraghty, 2011).
Inspection procedures in manufacturing processes: recent studies and research perspectives
Published in International Journal of Production Research, 2020
Gianfranco Genta, Maurizio Galetto, Fiorenzo Franceschini
Vaghefi and Sarhangian (2009) developed a new mathematical model to optimise inspection plans for multi-stage manufacturing systems with possible misclassification errors. This model minimises total inspection costs while still assuring a required output quality. Given the model complexity, a simulation algorithm is presented to model the multi-stage manufacturing system subject to inspection and to estimate the resulting inspection costs. Korytkowski (2011) presented an approach for determining the optimal location of inspection stations in multiproduct multistage production system. A genetic algorithm with tournament selection has been adapted to solve the optimisation problem. The genetic approach resulted to be suitable for modelling the inspection allocation problem since the codes used in the chromosome reflect the inspection allocation policies.