Heap-based optimizer inspired by corporate rank hierarchy for global optimization

Askari, Qamar; Saeed, Mehreen; Younas, Irfan

doi:10.1016/j.eswa.2020.113702

Cited by 285 publications

(159 citation statements)

References 66 publications

Supporting

Mentioning

157

Contrasting

Unclassified

Order By: Relevance

“…MFO and Comprehensive Learning PSO (CLPSO). Askari et al [57] proposed a Heap-based Optimizer (HBO) by simulating various interactions in a corporate rank hierarchy. A 3-ary heap structure according to the fitness values is established on the population.…”

Section: Metaheuristic Algorithmsmentioning

confidence: 99%

Evolving CNN-LSTM Models for Time Series Prediction Using Enhanced Grey Wolf Optimizer

2020

View full text Add to dashboard Cite

In this research, we propose an enhanced Grey Wolf Optimizer (GWO) for designing the evolving Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) networks for time series analysis. To overcome the probability of stagnation at local optima and a slow convergence rate of the classical GWO algorithm, the newly proposed variant incorporates four distinctive search mechanisms. They comprise a nonlinear exploration scheme for dynamic search territory adjustment, a chaotic leadership dispatching strategy among the dominant wolves, a rectified spiral local exploitation action, as well as probability distribution-based leader enhancement. The evolving CNN-LSTM models are subsequently devised using the proposed GWO variant, where the network topology and learning hyperparameters are optimized for time series prediction and classification tasks. Evaluated using a number of benchmark problems, the proposed GWO-optimized CNN-LSTM models produce statistically significant results over those from several classical search methods and advanced GWO and Particle Swarm Optimization variants. Comparing with the baseline methods, the CNN-LSTM networks devised by the proposed GWO variant offer better representational capacities to not only capture the vital feature interactions, but also encapsulate the sophisticated dependencies in complex temporal contexts for undertaking time-series tasks.

show abstract

Section: Metaheuristic Algorithmsmentioning

confidence: 99%

Evolving CNN-LSTM Models for Time Series Prediction Using Enhanced Grey Wolf Optimizer

2020

View full text Add to dashboard Cite

show abstract

“…The implementation of the algorithm as CRO-SL substrate is straightforward, as any solution within the substrate is just applied the set of operators described above, i.e. each coral in this substrate is modified by sequentially by applying Equations (10), (12) and finally (13), with the algorithm's parameters described in [66]. The resulting larvae pass through a settle down process to remain (or not) in the reef, as shown in the step 5 of the CRO pseudo-code.…”

Section: B Water Wave Optimization As Cro-sl Substratementioning

confidence: 99%

“…Many of these meta-heuristics have some class of bioinspiration [8], [9], and some others are based on physical processes [10] or different types of alternative inspirations. Some examples of the most recently proposed for metaheuristics for optimization, which are now gaining momentum are the slime mould algorithm [11], the Gradient-based optimizer [12], the Heap-based optimizer [13] or the Harris hawk optimization algorithm [14]. In addition to this upsurge of new meta-heuristics proposals, the last trend in optimization techniques is based on the development of multi-method ensembles.…”

Section: Introductionmentioning

confidence: 99%

Submerged Arches Optimal Design With a Multi-Method Ensemble Meta-Heuristic Approach

et al. 2020

View full text Add to dashboard Cite

This paper discusses the performance of a multi-method ensemble meta-heuristic for optimization in a problem of submerged arches design. Specifically, the Coral Reefs Optimization algorithm with Substrate Layers (CRO-SL) is proposed. It is a multi-method evolutionary ensemble which combines different searching structures in a single population. In this case, some novel searching strategies such as the Firefly algorithm and the Water Wave Optimization have been proposed to be included in the CRO-SL algorithm. In addition, some other traditional searching structures such as classical crossovers, Gaussian mutation operators, Harmony search and Differential Evolution search strategies have also been implemented in the algorithm. The proposed CRO-SL has been applied to the optimal design of submerged arches in deep waters, considering several design aspects such as the bending moment of the beam and the airspace of the arch. The evaluation of the submerged arches quality is obtained after the simulation of the arches by means of a finite elements computational software, which has been hybridized with the CRO-SL algorithm in the process of fitness calculation. It will be shown that the CRO-SL is able to obtain excellent solutions to submerged arches design problems. For this, the computational performance of each substrate (different searching strategies) in this optimization problem will be discussed and the results obtained will be compared with those in alternative works for similar experiments.

show abstract

“…▪ The simulation results are compared with many algorithms in the literature when using the same data set. ▪ To prove the proposed new algorithm ability, many recent algorithms for the first time as Jellyfish search (JFS) optimizer [38], Manta Ray Foraging optimizer (MRFO) [39][40], Marine Predator Algorithm (MPA) [41], Equilibrium Optimizer (EO) [42][43], and Heap Based Optimizer (HBO) [44] are implemented in this work for the two modules. ▪ The performance of the proposed FBIA algorithm is inspected in terms of fitness value and convergence speed in comparison to other metaheuristics.…”

Section: Introductionmentioning

confidence: 99%

A Forensic-Based Investigation Algorithm for Parameter Extraction of Solar Cell Models

et al. 2021

View full text Add to dashboard Cite

Heap-based optimizer inspired by corporate rank hierarchy for global optimization

Cited by 285 publications

References 66 publications

Evolving CNN-LSTM Models for Time Series Prediction Using Enhanced Grey Wolf Optimizer

Evolving CNN-LSTM Models for Time Series Prediction Using Enhanced Grey Wolf Optimizer

Submerged Arches Optimal Design With a Multi-Method Ensemble Meta-Heuristic Approach

A Forensic-Based Investigation Algorithm for Parameter Extraction of Solar Cell Models

Contact Info

Product

Resources

About