A Cognitively Inspired Hybridization of Artificial Bee Colony and Dragonfly Algorithms for Training Multi-layer Perceptrons

Ghanem, Waheed Ali H. M.; Jantan, Aman

doi:10.1007/s12559-018-9588-3

Cited by 49 publications

(40 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In reference [38], the strengths of DA combined with ABC. The aim of hybridizing these two metaheuristics was to eliminate slow convergence problem and falling into local optima by providing a better balance between local and global search components of the participated algorithms.…”

Section: G a Cognitively Inspired Hybridization Of Artificial Bee Comentioning

confidence: 99%

OUP accepted manuscript

2020

Journal of Computational Design and Engineering

View full text Add to dashboard Cite

Dragonfly algorithm (DA) is one of the most recently developed heuristic optimization algorithms by Mirjalili in 2016. It is now one of the most widely used algorithms. In some cases, it outperforms the most popular algorithms. However, this algorithm is not far from obstacles when it comes to complex optimization problems. In this work, along with the strengths of the algorithm in solving real-world optimization problems, the weakness of the algorithm to optimize complex optimization problems is addressed. This survey presents a comprehensive investigation of DA in the engineering area. First, an overview of the algorithm is discussed. Additionally, the different variants of the algorithm are addressed too. The combined versions of the DA with other techniques and the modifications that have been done to make the algorithm work better are shown. Besides, a survey on applications in engineering area that used DA is offered. The algorithm is compared with some other metaheuristic algorithms to demonstrate its ability to optimize problems comparing to the others. The results of the algorithm from the works that utilized the DA in the literature and the results of the benchmark functions showed that in comparison with some other algorithms DA has an excellent performance, especially for small to medium problems. Moreover, the bottlenecks of the algorithm and some future trends are discussed. Authors conduct this research with the hope of offering beneficial information about the DA to the researchers who want to study the algorithm and utilize it to optimize engineering problems.

show abstract

Section: G a Cognitively Inspired Hybridization Of Artificial Bee Comentioning

confidence: 99%

OUP accepted manuscript

2020

Journal of Computational Design and Engineering

View full text Add to dashboard Cite

show abstract

“…In reference [28], the DA's strength combined with ABC. The aim of hybridizing these two metaheuristics was to eliminate the convergence speed problem and falling into local optima by providing a better steadiness concerning local and global search constituents of the contributed techniques.…”

Section: Hybridized Versions Of Dragonfly Algorithmmentioning

confidence: 99%

A Survey on Dragonfly Algorithm and its Applications in Engineering

Rahman¹,

Rashid²,

Alsadoon³

et al. 2020

Preprint

View full text Add to dashboard Cite

Dragonfly algorithm developed in 2016. It is one of the algorithms used by the researchers to optimize an extensive series of uses and applications in various areas. At times, it offers superior performance compared to the most well-known optimization techniques. However, this algorithm faces several difficulties when it is utilized to enhance complex optimization problems. This work addressed the robustness of the method to solve real-world optimization issues, and its deficiency to improve complex optimization problems. This review paper shows a comprehensive investigation of the dragonfly algorithm in the engineering area. First, an overview of the algorithm is discussed. Besides, we also examine the modifications of the algorithm. The merged forms of this algorithm with different techniques and the modifications that have been done to make the algorithm perform better are addressed. Additionally, a survey on applications in the engineering area that used the dragonfly algorithm is offered. A comparison is made between the algorithm and other metaheuristic techniques to show its ability to enhance various problems. The outcomes of the algorithm from the works that utilized the dragonfly algorithm previously and the outcomes of the benchmark test functions proved that in comparison with some techniques, the dragonfly algorithm owns an excellent performance, especially for small to intermediate applications. Moreover, the congestion facts of the technique and some future works are presented. The authors conducted this research to help other researchers who want to study the algorithm and utilize it to optimize engineering problems.

show abstract

“…DA has advantages in exploring the global search space by using the food source and enemy source. However, the use of Lévy Flight results in a large movement that leads to local convergence and pushes the algorithm apart from the global optimum [56]. In addition, NSGA II, developed by Deb et al [63], is a well-known meta-heuristic approach for solving multi-objective optimization problems.…”

Section: The Hybrid Da-ga For the Proposed Modelmentioning

confidence: 99%

“…Khadanga et al [55] proposed a hybrid dragonfly and pattern search algorithm approach and used it in tilt integral derivative controller design. Ghanem and Jantan [56] combined ABC and DA to train a multi-layer perceptron. Sree and Murugan [57] developed a memory-based hybrid dragonfly algorithm with the concept of PSO gbest and pbest for solving three engineering design problems.…”

Section: Introductionmentioning

confidence: 99%

Credibilistic Mean-Semi-Entropy Model for Multi-Period Portfolio Selection with Background Risk

Zhang

2019

Entropy

View full text Add to dashboard Cite

In financial markets, investors will face not only portfolio risk but also background risk. This paper proposes a credibilistic multi-objective mean-semi-entropy model with background risk for multi-period portfolio selection. In addition, realistic constraints such as liquidity, cardinality constraints, transaction costs, and buy-in thresholds are considered. For solving the proposed multi-objective problem efficiently, a novel hybrid algorithm named Hybrid Dragonfly Algorithm-Genetic Algorithm (HDA-GA) is designed by combining the advantages of the dragonfly algorithm (DA) and non-dominated sorting genetic algorithm II (NSGA II). Moreover, in the hybrid algorithm, parameter optimization, constraints handling, and external archive approaches are used to improve the ability of finding accurate approximations of Pareto optimal solutions with high diversity and coverage. Finally, we provide several empirical studies to show the validity of the proposed approaches.

show abstract

A Cognitively Inspired Hybridization of Artificial Bee Colony and Dragonfly Algorithms for Training Multi-layer Perceptrons

Cited by 49 publications

References 52 publications

OUP accepted manuscript

OUP accepted manuscript

A Survey on Dragonfly Algorithm and its Applications in Engineering

Credibilistic Mean-Semi-Entropy Model for Multi-Period Portfolio Selection with Background Risk

Contact Info

Product

Resources

About