Introduction to evolutionary algorithms

Yu, Xinjie

doi:10.1109/iccie.2010.5668407

Cited by 52 publications

(52 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The algorithm is inspired by the behaviour of a flock of birds that can fly together, scatter suddenly and regroup again. Each bird or particle not only keeps track of its own behaviour, but of the behaviour of others as well [64]. Each particle knows four elements: its current location, its current velocity, its best location so far and the global best location so far, which takes the entire swarm into consideration.…”

Section: Particle Swarm Optimizationmentioning

confidence: 99%

“…Essentially, an original population of possible solutions is allowed to 'reproduce' and create new solutions. The survival of these solutions depends on a fitness criterion that is decided beforehand, so the best solution will ultimately be chosen by the algorithm after a number of iterations [8,64]. This general procedure of GA is formalized in Figure 1.…”

Section: Genetic Algorithmsmentioning

confidence: 99%

“…In order to find the optimal solution, PSO uses a similar procedure as GA [64]. The initial swarm is randomly selected, but the swarm size still needs to be determined beforehand.…”

Section: Particle Swarm Optimizationmentioning

confidence: 99%

“…This general procedure of GA is formalized in Figure 1. Before we can initialize the population, the solutions and their features need to be encoded in the chromosome, which is usually formalized in binary or decimal string values [64]. Once the possible solutions are encoded, we can choose an initial population of solutions, which often consists of a random selection process that can be guided by pre-set rules.…”

Section: Genetic Algorithmsmentioning

confidence: 99%

“…Concretely, we need to determine the chromosome encoding, the initial population size, the initial population selection, the fitness function, the distribution of the selection probabilities, the probabilities for crossover and mutation, the crossover method, the elitist strategy and the stopping criterion in order to execute the technique [64].…”

Section: Genetic Algorithmsmentioning

confidence: 99%

See 4 more Smart Citations

ProfARIMA: A profit-driven order identification algorithm for ARIMA models in sales forecasting

Calster

Baesens

Lemahieu

2017

Applied Soft Computing

View full text Add to dashboard Cite

In forecasting, evolutionary algorithms are often linked to existing forecasting methods to optimize their input parameters. Traditionally, the fitness function of these search heuristics is based on an accuracy measure. In this paper, however, we combine forecasting accuracy with business expertise by defining a flexible and easily interpretable profit function for sales forecasting, which is based on the profit margin of a given product, the volume of its sales and the accuracy of the forecast. ProfARIMA is a new procedure that selects the lags of a Seasonal ARIMA model according to the profit of a model's forecasts by taking advantage of search heuristics. This procedure is tested on both publicly available datasets and a real-life application with datasets of The Coca-Cola Company in order to assess its performance, both in profit and accuracy. Three different evolutionary algorithms were implemented during this testing process, i.e. Genetic Algorithms, Particle Swarm Optimization and Simulated Annealing. The results indicate that ProfARIMA always performs at least equally to the Box-Jenkins methodology and often outperforms this traditional procedure. For The Coca-Cola Company, our new algorithm in combination with Genetic Algorithms even leads to a significantly larger profit for out-of-sample forecasts.

show abstract

Section: Particle Swarm Optimizationmentioning

confidence: 99%

Section: Genetic Algorithmsmentioning

confidence: 99%

“…In order to find the optimal solution, PSO uses a similar procedure as GA [64]. The initial swarm is randomly selected, but the swarm size still needs to be determined beforehand.…”

Section: Particle Swarm Optimizationmentioning

confidence: 99%

Section: Genetic Algorithmsmentioning

confidence: 99%

Section: Genetic Algorithmsmentioning

confidence: 99%

See 3 more Smart Citations

ProfARIMA: A profit-driven order identification algorithm for ARIMA models in sales forecasting

Calster

Baesens

Lemahieu

2017

Applied Soft Computing

View full text Add to dashboard Cite

show abstract

Advances in Multiobjective Hybrid Genetic Algorithms for Intelligent Manufacturing and Logistics Systems

Gen

Ida

2013

Active Media Technology

View full text Add to dashboard Cite

Abstract. Recently, genetic algorithms (GA) have received considerable attention regarding their potential as a combinatorial optimization for complex problems and have been successfully applied in the area of various engineering. We will survey recent advances in hybrid genetic algorithms (HGA) with local search and tuning parameters and multiobjective HGA (MO-HGA) with fitness assignments. Applications of HGA and MO-HGA will introduced for flexible job-shop scheduling problem (FJSP), reentrant flow-shop scheduling (RFS) model, and reverse logistics design model in the manufacturing and logistics systems. IntroductionMany real world applications in engineering design problems and information systems impose on more complex issues, such as complex structure, complex constraints, and multiple objectives to be handled simultaneously and make the problem intractable to the traditional approaches. Network models provide a useful way for modeling various operation management problems and are extensively used in many different types of systems: manufacturing and logistics areas. Network models and optimization for various scheduling and/or routing problems in manufacturing and logistics systems also provide a useful way as one of case studies in real world problems and are extensively used in practice [1]. Genetic algorithm (GA) has recently received a considerable attention because of its potential of being a very effective design optimization technique for solving various NP hard combinatorial optimization problems and complex information processing, manufacturing and logistics systems. Evolutionary Algorithms (EA) are stochastic optimization techniques that utilize principles of natural evolution in finding new search directions. Although, each of the evolutionary techniques, e.g. Genetic Algorithms (GA), Genetic Programming (GP) etc., have their own strengths and weaknesses for the combinatorial optimization problems. The most common algorithms studied in the literature variants of EAs [2][3][4][5].

show abstract

Calibration of Dynamic Models of Railway Bridges Based on Genetic Algorithms

Ribeiro

Calçada

Delgado

2015

Computational Methods in Applied Sciences

View full text Add to dashboard Cite

This chapter presents the main experimental calibration methodologies of finite element numerical models, with particular focus on methodologies based on modal parameters. In this context, the computational implementation of an iterative method based on a genetic algorithm is described. The iterative method involves the resolution of an optimization problem, which involves the minimization of an objective function by varying a set of preselected model parameters. The objective function includes residuals associated to natural frequencies and mode shapes. The proposed methodology is applied to the calibration of the dynamic models of two railway bridges, São Lourenço bridge and Alverca viaduct, both located in the northern line of the Portuguese railways in recently upgraded track sections. The calibration results demonstrate a very good agreement between numerical and experimental modal responses and a significant improvement of the numerical models before calibration. Also the stability of a significant number of parameters, considering different initial populations, proved the robustness of the genetic algorithm in the scope of the optimization of the numerical models. The updated numerical models were validated based on dynamic tests under railway traffic. The results showed an excellent agreement between numerical and experimental responses in terms of displacements and accelerations of the bridges' decks.

show abstract

Introduction to evolutionary algorithms

Cited by 52 publications

References 0 publications

ProfARIMA: A profit-driven order identification algorithm for ARIMA models in sales forecasting

ProfARIMA: A profit-driven order identification algorithm for ARIMA models in sales forecasting

Advances in Multiobjective Hybrid Genetic Algorithms for Intelligent Manufacturing and Logistics Systems

Calibration of Dynamic Models of Railway Bridges Based on Genetic Algorithms

Contact Info

Product

Resources

About