Evolutionary Computation

Dumitrescu, D.; Lazzerini, Beatrice; Jain, Lakhmi C.; Dumitrescu, A.

doi:10.1201/9781482273960

Cited by 146 publications

(73 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This allows to avoid the destruction of valuable genetic material, thus improving the performance of the algorithm (Dumitrescu D. et al, 2000). In the implemented GA a 10% of individuals go directly to the next generation, the selection of these individuals is carried out based on the fitness value, in order to retain only those most efficient.…”

Section: Ga Implementationmentioning

confidence: 99%

Implementation of a genetic algorithm for energy design optimization of livestock housing using a dynamic thermal simulator

Menconi¹,

Chiappini²,

Grohmann³

2013

J Agricult Engineer

View full text Add to dashboard Cite

A Genetic Algorithm (GA) is an optimization process inspired by natural systems ability of surviving in many different environments through the mechanisms of natural selection and genetics. The pairing of GA-based optimization techniques with dynamic energy models is a common and effective practice to find energy efficient design solutions. In this paper is implemented an optimization tool that use a GA and a dynamic energy model. Efficiency of GAs depends largely on the coding strategy and on the parameters selection. In order to test the code and to find the best combination of parameters, a parametric analysis of GA's performances is carried out. The algorithm, coded in Matlab, works with populations of strings. Each string, that represents a complete design solution, is initially randomly generated by the GA and evaluated in terms of energy performances by the dynamic thermal simulator. A new population is then generated using three different GA stochastic operators: reproduction, crossover and mutation, by selecting, mixing and randomly modifying the fittest solutions of the previous generation. Each generation is energetically evaluated and thus the fitness of the strings, that represent the energy efficiency of the design solutions, improves every cycle till eventually converge to the best solution. This whole methodology is well documented and applied in residential buildings design but can be easily extended to livestock housing. In this paper the algorithm is coded to be applied on a simple sheepfold model in order to optimize only passive design solutions.

show abstract

Section: Ga Implementationmentioning

confidence: 99%

Implementation of a genetic algorithm for energy design optimization of livestock housing using a dynamic thermal simulator

Menconi¹,

Chiappini²,

Grohmann³

2013

J Agricult Engineer

View full text Add to dashboard Cite

show abstract

“…General EA selections usually work well with GP without any modification. For a thorough treatment one should see [37].…”

Section: Fitness Assignmentmentioning

confidence: 99%

“…Mutations with different granularity levels usually coexist in a single implementation. For details see [10,37].…”

Section: Mutation Typesmentioning

confidence: 99%

See 1 more Smart Citation

Towards identifying salient patterns in genetic programming individuals

Joó

Neirotti

2009

Proceedings of the 11th Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

This thesis addresses the problem of offline identification of salient patterns in genetic programming individuals. It discusses the main issues related to automatic pattern identification systems, namely that these (a) should help in understanding the final solutions of the evolutionary run, (b) should give insight into the course of evolution and (c) should be helpful in optimizing future runs. Moreover, it proposes an algorithm, Extended Pattern Growing Algorithm ([E]PGA) to extract, filter and sort the identified patterns so that these fulfill as many as possible of the following criteria: (a) they are representative for the evolutionary run and/or search space, (b) they are human-friendly and (c) their numbers are within reasonable limits. The results are demonstrated on six problems from different domains.

show abstract

“…Using single-point and two-point crossover operator prevents schema to be disrupted, but when population becomes homogeneous, search space becomes smaller. [3][4]…”

Section: F Two-point Crossovermentioning

confidence: 99%

Improved Genetic Algorithm using New Crossover Operator

2017

IJCCIE

View full text Add to dashboard Cite

Abstract-The complexity of existing crossover operators used in Genetic Algorithm is a critical factor that affects performance due to its negative impact on processing time. In this paper, a new crossover operator called Push and Pop Genes Exchange Operator (PPX) is introduced and its performance evaluated in terms of processing time. Results of comparative performance with six crossover operators show that PPX performed better in terms of processing time across various population size, with improvements ranging from 0.6% when compared to shuffle crossover at n=100 to 24.8% when compared to the half-uniform crossover operator at n=30. Results also show that PPX performed better with increase in population with a maximum of 13.1% when population was increased from 30 to 100. The results confirm that PPX improved the performance of Genetic Algorithm by reducing the complexity of crossover operation when compared to the existing operators.

show abstract

Evolutionary Computation

Cited by 146 publications

References 0 publications

Implementation of a genetic algorithm for energy design optimization of livestock housing using a dynamic thermal simulator

Implementation of a genetic algorithm for energy design optimization of livestock housing using a dynamic thermal simulator

Towards identifying salient patterns in genetic programming individuals

Improved Genetic Algorithm using New Crossover Operator

Contact Info

Product

Resources

About