On Stopping Criteria for Genetic Algorithms

Safe, Martín D.; Carballido, Jessica Andrea; Ponzoni, Ignacio; Brignole, Nélida Beatríz

doi:10.1007/978-3-540-28645-5_41

Cited by 101 publications

(45 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different approaches have been used to stop the search process of EAs including those that consider the desired solution quality, the specific number of solution evaluations, the required computation time, and the prespecified convergence behavior (Safe et al 2004). Originally suggested for stopping the search in a single objective evolutionary algorithm, a new stopping criterion is introduced here that considers the convergence speed towards the true Pareto optimal front while dealing with expensive, real-world optimization problems.…”

Section: Proposed Moea Search Stopping Criterion-hypervolume Growth Ratementioning

confidence: 99%

Evolutionary multiobjective optimization in noisy problem environments

Eskandari

Geiger

2008

J Heuristics

View full text Add to dashboard Cite

This paper presents a multiobjective evolutionary algorithm (MOEA) capable of handling stochastic objective functions. We extend a previously developed approach to solve multiple objective optimization problems in deterministic environments by incorporating a stochastic nondomination-based solution ranking procedure. In this study, concepts of stochastic dominance and significant dominance are introduced in order to better discriminate among competing solutions. The MOEA is applied to a number of published test problems to assess its robustness and to evaluate its performance relative to NSGA-II. Moreover, a new stopping criterion is proposed, which is based on the convergence velocity of any MOEA to the true Pareto optimal front, even if the exact location of the true front is unknown. This stopping criterion is especially useful in real-world problems, where finding an appropriate point to terminate the search is crucial.

show abstract

Section: Proposed Moea Search Stopping Criterion-hypervolume Growth Ratementioning

confidence: 99%

Evolutionary multiobjective optimization in noisy problem environments

Eskandari

Geiger

2008

J Heuristics

View full text Add to dashboard Cite

show abstract

“…Each iteration of the sGA, also referred as generation, produces a new population of strings. Among the many possible termination criteria [81], here we considered the maximum number of generations (Algorithm 3, line 3).…”

Section: Genetic Algorithmsmentioning

confidence: 99%

Optimization Algorithms for Computational Systems Biology

Reali

Priami

Marchetti

2017

Front. Appl. Math. Stat.

View full text Add to dashboard Cite

Computational systems biology aims at integrating biology and computational methods to gain a better understating of biological phenomena. It often requires the assistance of global optimization to adequately tune its tools. This review presents three powerful methodologies for global optimization that fit the requirements of most of the computational systems biology applications, such as model tuning and biomarker identification. We include the multi-start approach for least squares methods, mostly applied for fitting experimental data. We illustrate Markov Chain Monte Carlo methods, which are stochastic techniques here applied for fitting experimental data when a model involves stochastic equations or simulations. Finally, we present Genetic Algorithms, heuristic nature-inspired methods that are applied in a broad range of optimization applications, including the ones in systems biology.

show abstract

“…The population size was fixed to 145 individuals, the crossover probability was set to 0.75 and the mutation probability was established as 2/n. As is recommended in the literature [55], a phenotypic criterion was selected for the stopping of the evolutionary algorithm: it stops when the improvement during 15 generations of the average fitness of the population is less than a given tolerance value (x ¼ 10…”

Section: Design Of the Experimentsmentioning

confidence: 99%

Multi‐Objective Feature Selection in QSAR Using a Machine Learning Approach

et al. 2009

Self Cite

View full text Add to dashboard Cite

The selection of descriptor subsets for QSAR/QSPR is a hard combinatorial problem that requires the evaluation of complex relationships in order to assess the relevance of the selected subsets. In this paper, we describe the main issues in applying descriptor selection for QSAR methods and propose a novel two-phase methodology for this task. The first phase makes use of a multi-objective evolutionary technique which yields interesting advantages compared to mono-objective methods. The second phase complements the first one and it enables to refine and improve the confidence in the chosen subsets of descriptors. This methodology allows the selection of subsets when a large number of descriptors are involved and it is also suitable for linear and nonlinear QSAR/QSPR models. The proposed method was tested using three data sets with experimental values for blood-brain barrier penetration, human intestinal absorption and hydrophobicity. Results reveal the capability of the method for achieving subsets of descriptors with a high predictive capacity and a low cardinality. Therefore, our proposal constitutes a new promising technique helpful for the development of QSAR/QSPR models.

show abstract

On Stopping Criteria for Genetic Algorithms

Cited by 101 publications

References 13 publications

Evolutionary multiobjective optimization in noisy problem environments

Evolutionary multiobjective optimization in noisy problem environments

Optimization Algorithms for Computational Systems Biology

Multi‐Objective Feature Selection in QSAR Using a Machine Learning Approach

Contact Info

Product

Resources

About