China 
Africa 
Explore chapters and articles related to this topic
Signature Verification Based on a Fuzzy Genetic Algorithm
Published in Lakhmi C. Jain, Beatrice Lazzerini, KNOWLEDGE-BASED INTELLIGENT TECHNIQUES in CHARACTER RECOGNITION, 2020
Recently, the FGA [6], [7] was introduced for feature selection problems (FSP). The selection of features associated with each individual is based on the fitness-proportionate selection in which parents are chosen from the population. Results demonstrate that the operation using soft crossover will improve the searching power through the multidimensional feature space. It is noted that there are weaknesses or limitations with the GA approach to FSP, but these limitations can be resolved by the FGA. First, there are only 2 different selection degrees or categories for features in the GA: either being completely selected or completely rejected. It is obvious that it would be desirable to rank the degree of importance of the features. For the important features, the degree of importance should be close to 1; on the other hand, for the irrelevant features, the degree of importance should be close to 0; for the in-between cases, the degree of importance should be somewhere between 0 and 1 depending on their importance. This FGA approach can further improve the performance of the system because it is able to search through the continuous space by new chromosome type and operations. Second, over a range of genetic algorithm settings, i.e., the probability of crossover and that of mutation of the GA, the performance of the system varies significantly. This may be caused by the incomplete search of the feature space by the restricted information available. We believe that with the extra information of the degree of importance of the features in the FGA, the search space could be searched more efficiently and robustly.
Intelligent Optimization Techniques for Manufacturing Optimization Problems
Published in R. Saravanan, Manufacturing Optimization through Intelligent Techniques, 2017
Holland’s original GA used fitness-proportionate selection, in which the “expected value” of an individual (i.e., the expected number of times an individual will be selected to reproduce) is that individual’s fitness divided by the average fitness of the population. The most common method for implementing this is roulette wheel sampling, described earlier: each individual is assigned a slice of a circular “roulette wheel,” the size of the slice being proportional to the individual’s fitness. The wheel is spun N times, where N is the number of individuals in the population. On each spin, the individual under the wheel’s marker is selected to be in the pool of parents for the next generation. This method can be implemented as follows: Add the total expected value of individuals in the population. Call this sum T.Repeat N times.Choose a random integer r between 0 and T.Loop through the individuals in the population, summing the expected values, until the sum is greater than or equal to r. The individual whose expected value puts the sum over this limit is the one selected.
Fuzzy Modeling
Published in Shyam S. Sablani, M. Shafiur Rahman, Ashim K. Datta, Arun S. Mujumdar, Handbook of Food and Bioprocess Modeling Techniques, 2006
Haitham M. S. Lababidi, Christopher G. J. Baker
Many fitness selection procedures are currently in use, one of the simplest being fitness-proportionate selection,4 where individuals are selected within a probability proportional to their fitness. Crossover is performed using a “crossover rate” between two selected individuals, called parents, by exchanging parts of their genomes to form two new individuals, called offsping. The mutation operation is carried out by flipping randomly selected parts of the strings preserving the size of the population. There are several variations of GAs66 with different selection mechanisms (e.g., ranking, tournament, and elitism), crossover operators (e.g., multipoint crossover), and mutation operators (e.g., adaptive mutation). These and other advanced topics related to genetic algorithms are found in books such as Mitchell,64 Michalewicz,65 and Banzhaf et al.67
Artificial Intelligence-Based Image Classification Techniques for Hydrologic Applications
Published in Applied Artificial Intelligence, 2022
In GEP, the process commences random selection of an initial population having peculiar characteristics of the class. This initial population sample helps to generate many pairs of genotype and phenotype comprising an individual chromosome of fixed length for each pair. For potentially practical solutions from all chromosomes, the selection is made based on the fitness value using a fitness proportionate selection operation, generally known as the roulette wheel selection process. Genetic operators replicate the selected chromosome to apply modification, replication, recombination, and transposition to the genomes of the chromosome. This process helps to add the adaptive and evolution nature to the programming. New chromosomes are then brought down to the previous process of selection and modification. The process continues until the required accuracy, and a maximum number of iterations (generations) are achieved (Ferreira 2001, 2002, 2006). The GEP had performed well in predicting bridge pier scour depth compared to regression and ANN models (Mohammadpour 2017). The GEP has a unique approach for selecting and providing compact, explicit solutions by opting for the most optimized solution from all different types of suitable solutions. Hence, this feature supports its suitability, especially for using GEP in getting mathematical expression for computing bridge scours over other AI programming such as ANN (Khan, Azamathulla, and Tufail 2012).
Morphological evolution for pipe inspection using Robot Operating System (ROS)
Published in Materials and Manufacturing Processes, 2020
Ahmed Hallawa, Giovanni Iacca, Cagatay Sariman, Touhidur Rahman, Michael Cochez, Gerd Ascheid
Two possible reproduction operations are possible in the presented scheme: crossover and mutation. Crossover is conducted by randomly picking a single point among the rules in the genotype, and exchange the gene sequence around this random point between two parent solutions, thus producing two new offspring. Mutation is executed on offspring (after crossover) by flipping any symbol in their genotype, e.g. flipping an addF to addB, or a moveA to moveB. Both crossover and mutation are executed with probability and , which are two hyper-parameters to be selected adequately to allow a proper exploration–exploitation balance. As for selection, we adopted a roulette-wheel (fitness-proportionate) selection criterion, where the agents with better performance are more likely to reproduce. Furthermore, we kept the population size constant and did not use any elitism.
Feature Selection for Alzheimer’s Gene Expression Data Using Modified Binary Particle Swarm Optimization
Published in IETE Journal of Research, 2023
Ramya Ramaswamy, Premalatha Kandhasamy, Swathypriyadharsini Palaniswamy
Fitness proportionate selection or Roulette wheel selection is used in genetic algorithms to select most helpful solutions for recombination. If fi is the fitness of the particle , its selection probability is where is the number of particles in the population. It is utilized to identify the particles from the swarm and the new particles’ position and velocity are generated by crossover and mutation operation with the global best particle. Elitist selection mechanism is used to identify the particles for the next iteration. That is the best solution used to build the next generation.