Voting-mechanism based ensemble constraint handling technique for real-world single-objective constrained optimization

Wen, Xupeng; Wu, Guohua; Fan, Mingfeng; Wang, Rui; Suganthan, Ponnuthurai Nagaratnam

doi:10.1109/cec48606.2020.9185632

Cited by 9 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To further verify the comprehensive performance of GPEde, this section focus on comparing GPEde with four state-of-the-art algorithms including VMCH [48], sCMAgES [49], EnMODE [50], FCHA [51]. The four algorithms are the more advanced algorithms in solving CEC 2020 real-world single-objective constrained optimization problems.…”

Section: Comparison Of Gpede With Other State-of-the-art Algorithmsmentioning

confidence: 99%

An Improved Grey Prediction Evolution Algorithm for Real-world Engineering Optimization Problems

Zhang,

Hu,

et al. 2024

Preprint

View full text Add to dashboard Cite

Grey predictive evolutionary algorithm (GPE), which is developed with the inspiration of the grey prediction theory, is a promising candidate for solving complex optimization problems. Due to the complexity and challenge of constraint search space of real-world engineering problems, an improved GPE algorithm (called GPEde) incorporated the constraint handling methods of an ε-constrained level and a gradient-based repair is proposed to effectively handle real-world engineering constrained problems in this paper. The core idea of GPEde is to guide inferior individuals through predicted information produced by GPE. The proposed algorithm is developed by the following two processes. Firstly, half of offspring individuals carrying the predicted information are generated by GPE using three consecutive generation subpopulation, where the subpopulation consists of the top 50% excellent individuals in each generation. Secondly, another half of offspring individuals are produced by adopting a prediction-based learning strategy that is constructed by using the new 50% of offspring individuals to guide inferior individuals of the last 50% of the current population. The effectiveness and superiority of GPEde are validated on 19 mechanical engineering problems extracted from the CEC 2020 real-world single-objective constrained optimization problems. The experimental results demonstrate that GPEde is a competitive optimizer for solving constrained optimization problems compared with differential evolution algorithm, GPE, three variants of GPE and four state-of-the-art algorithms. If this paper is accepted, MATLAB codes associated with this paper will be uploaded to https://github.com/Zhongbo-Hu/Prediction-Evolutionary-Algorithm-HOMEPAGE.

show abstract

Section: Comparison Of Gpede With Other State-of-the-art Algorithmsmentioning

confidence: 99%

An Improved Grey Prediction Evolution Algorithm for Real-world Engineering Optimization Problems

Zhang,

Hu,

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Researchers have proposed many types of penalty functions, such as static penalty [32], dynamic penalty [33], [34], the superiority of feasible solutions [35], ranking-based method [36], and ensemble constraint handling technique [37]. In the evolutionary algorithm community, the most commonly used approach to handle constraints is the penalty function [38].…”

Section: B Constraint Handling Techniquementioning

confidence: 99%

An Improved Genetic Algorithm for Constrained Optimization Problems

Wang

2023

IEEE Access

View full text Add to dashboard Cite

The mathematical form of many optimization problems in engineering is constrained optimization problems. In this paper, an improved genetic algorithm based on two-direction crossover and grouped mutation is proposed to solve constrained optimization problems. In addition to making full use of the direction information of the parent individual, the two-direction crossover adds an additional search direction and finally searches in the better direction of the two directions, which improves the search efficiency. The grouped mutation divides the population into two groups and uses mutation operators with different properties for each group to give full play to the characteristics of these mutation operators and improve the search efficiency. In experiments on the IEEE CEC 2017 competition on constrained real-parameter optimization and ten real-world constrained optimization problems, the proposed algorithm outperforms other state-of-the-art algorithms. Finally, the proposed algorithm is used to optimize a singlestage cylindrical gear reducer.

show abstract

“…Wang et al [21] proposed a multiobjective evolutionary ensemble model based on an extreme learning machine (ELM), which used an evolutionary algorithm to achieve feature selection and network structure search. Wen et al [22] proposed a constraint voting ensemble framework based on variants of the differential evolutionary algorithm. The designed differential evolutionary variants were used as a search engine.…”

Section: Precision-oriented Approachesmentioning

confidence: 99%

Using dual evolutionary search to construct decision tree based ensemble classifier

Chen

Zhang

Pan

et al. 2022

Complex Intell. Syst.

View full text Add to dashboard Cite

A typical ensemble learning process typically uses a forward integration mechanism to construct the ensemble classifier with a large number of base classifiers. Based on this mechanism, it is difficult to adjust the diversity among base classifiers and optimize the structure inside ensemble since the generation process has a certain amount of randomness, which makes the performance of ensemble classifiers heavily dependent on the human design decisions. To address this issue, we proposed an automatic ensemble classifier construction method based on a dual-layer evolutionary search mechanism, which includes a tree coding-based base classifier population and a binary coding-based ensemble classifier population. Through a collaborative searching process between the two populations, the proposed method can be driven by training data to update the base classifier population and optimize the ensemble classifiers globally. To verify the effectiveness of the dual evolutionary ensemble learning method (DEEL), we tested it on 22 classification tasks from 4 data repositories. The results show that the proposed method can generate a diverse decision tree population on the training data while searching and constructing ensemble classifiers from them. Compared with 9 competitor algorithms, the proposed method achieved the best performance on 17 of 22 test tasks and improved the average accuracies by 0.97–7.65% over the second place. In particular, the generated ensemble classifiers show excellent structure, which involve small number and diverse decision trees. That increases the transparency of ensembles and helps to perform interpretability analysis on them.

show abstract

Voting-mechanism based ensemble constraint handling technique for real-world single-objective constrained optimization

Cited by 9 publications

References 19 publications

An Improved Grey Prediction Evolution Algorithm for Real-world Engineering Optimization Problems

An Improved Grey Prediction Evolution Algorithm for Real-world Engineering Optimization Problems

An Improved Genetic Algorithm for Constrained Optimization Problems

Using dual evolutionary search to construct decision tree based ensemble classifier

Contact Info

Product

Resources

About