Optimizing connection weights in neural networks using the whale optimization algorithm

Aljarah, Ibrahim; Faris, Hossam; Mirjalili, Seyedali

doi:10.1007/s00500-016-2442-1

Cited by 625 publications

(264 citation statements)

References 42 publications

Supporting

Mentioning

257

Contrasting

Unclassified

Order By: Relevance

“…Then, we run the FA 30 times. In each time, we use T i as a test set and the union of the others T ij where i ≠ j as training set [28]. We use the number of partitions to be 10 to avoid costly computation for higher portioning values.…”

Section: Dataset Partitioning Criteriamentioning

confidence: 99%

See 1 more Smart Citation

A Binary Classifier Based On Firefly Algorithm

Al-Abdallah¹,

Jaradat²,

Doush³

et al. 2017

JJCIT

View full text Add to dashboard Cite

show abstract

Section: Dataset Partitioning Criteriamentioning

confidence: 99%

“…Aljarah et al [28] proposed a new training algorithm based on whale optimization algorithm (WOA). A set of 20 datasets with different levels of difficulty have been chosen to test the proposed WOAbased trainer.…”

Section: Literature Reviewmentioning

confidence: 99%

A Binary Classifier Based On Firefly Algorithm

Al-Abdallah¹,

Jaradat²,

Doush³

et al. 2017

JJCIT

View full text Add to dashboard Cite

show abstract

“…Humpback whales prefer to hunt school of krill or small fishes close to the surface, whose foraging is done by creating distinctive bubbles along a circle or '9'-shaped path as shown in Figure 2. The bubble-net hunting is a unique behaviour which can be only observed in humpback whales [51][52][53][54].…”

Section: Wot Overview and Methodsologymentioning

confidence: 99%

“…An adult whale can grow up to 30 m long and weigh 180 tons [51][52][53][54]. Whales are mostly considered as predators, which never sleep because they have to breathe from the surface of oceans, and only half of whose brain sleeps.…”

Section: Wot Overview and Methodsologymentioning

confidence: 99%

See 1 more Smart Citation

A Reconfigured Whale Optimization Technique (RWOT) for Renewable Electrical Energy Optimal Scheduling Impact on Sustainable Development Applied to Damietta Seaport, Egypt

et al. 2018

View full text Add to dashboard Cite

This paper studies the effect on the rate of growth of carbon dioxide emission in seaports' atmosphere of replacing a part of the fossil fuel electrical power generation by clean renewable electrical energies, through two different scheduling strategies. The increased rate of harmful greenhouse gas emissions due to conventional electrical power generation severely affects the whole global atmosphere. Carbon dioxide and other greenhouse gases emissions are responsible for a significant share of global warming. Developing countries participate in this environmental distortion to a great percentage. Two different suggested strategies for renewable electrical energy scheduling are discussed in this paper, to attain a sustainable green port by the utilization of two mutual sequential clean renewable energies, which are biomass and photovoltaic (PV) energy. The first strategy, which is called the eco-availability mode, is a simple method. It is based on operating the renewable electrical energy sources during the available time of operation, taking into consideration the simple and basic technical issues only, without considering the sophisticated technical and economical models. The available operation time is determined by the environmental condition. This strategy is addressed to result on the maximum available Biomass and PV energy generation based on the least environmental and technical conditions (panel efficiency, minimum average daily sunshine hours per month, minimum average solar insolation per month). The second strategy, which is called the Intelligent Scheduling (IS) mode, relies on an intelligent Reconfigured Whale Optimization Technique (RWOT) based-model. In this strategy, some additional technical and economical issues are considered. The studied renewable electrical energy generation system is considered in two scenarios, which are with and without storage units. The objective (cost) function of the scheduling optimization problem, for both scenarios, are developed. Also, the boundary conditions and problem constraints are concluded. The RWOT algorithm is an updated Whale Optimization Algorithm (WOA). It is developed to accelerate the rate of reaching the optimal solution for the IS problem. The two strategies simulation and implementation are illustrated and applied to the seaport of Damietta, which is an Egyptian port, located 10 km to the west of the Nile River (Damietta Branch). The scheduling of PV and biomass energy generation during the different year months is examined for both strategies. The impact of renewable electrical energies generation scheduling on carbon dioxide emission and consequently global warming is discussed. The saving in carbon dioxide emission is calculated and the efficient results of the suggested models are clarified. The carbon dioxide emission is reduced to around its fifth value, during renewable energy operation. This work focuses on decreasing the rate of growth of carbon dioxide emission coming from fossil fuel electrical power generation in Egypt, targ...

show abstract

Distributed Whale Optimization Algorithm based on MapReduce

Khalil

Alshayeji

Ahmad

2018

Concurrency and Computation

View full text Add to dashboard Cite

Whale Optimization Algorithm (WOA) is a recent swarm intelligence based meta-heuristic optimization algorithm, which simulates the natural behavior of bubble-net hunting strategy of humpback whales and has been successfully applied to solve complex optimization problems in a wide range of disciplines. However, when applied to large-size problems, its performance degrades due to the need of massive computational work load. Distributed computing is one of the effective ways to improve the scalability of WOA for solving large-scale problems. In this paper, we propose a simple and robust distributed implementation of WOA using Hadoop MapReduce named MR-WOA. MapReduce paradigm is adopted as the distribution model since it is one of the most mature technologies to develop parallel algorithms which automatically handles communication, load balancing, data locality, and fault tolerance. The design of MR-WOA is discussed in details using the MapReduce paradigm. Experiments are conducted for a set of well-known benchmarks for evaluating the quality, speedup, and scalability of MR-WOA. The conducted experiments reveal that our approach achieves a promising speedup. For some benchmarks, speedup scales linearly with increasing the number of computational nodes.

show abstract

Optimizing connection weights in neural networks using the whale optimization algorithm

Cited by 625 publications

References 42 publications

A Binary Classifier Based On Firefly Algorithm

A Binary Classifier Based On Firefly Algorithm

A Reconfigured Whale Optimization Technique (RWOT) for Renewable Electrical Energy Optimal Scheduling Impact on Sustainable Development Applied to Damietta Seaport, Egypt

Distributed Whale Optimization Algorithm based on MapReduce

Contact Info

Product

Resources

About