L&amp;#x00E9;vy flight PSO

Hariya, Yosuke; Kurihara, Takayuki; Shindo, Takahiko; Jin’no, Kenya

doi:10.1109/cec.2015.7257220

Cited by 19 publications

(14 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The Lé vy process is a stochastic process of continuous time, which was first proposed by the French scientist Paul Lé vy. Researchers have found that the behavior of many animals in nature is consistent with the characteristics of the Lé vy process and have proposed the Lé vy flight theory [41] based on the Lé vy process. Lé vy flight is an optimal exploration behavior to search for randomly distributed objects.…”

Section: ) Stagnation Disturbance Strategymentioning

confidence: 91%

A Novel Hybrid PSO-K-Means Clustering Algorithm Using Gaussian Estimation of Distribution Method and Lévy Flight

Gao

Kabalyants

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Clustering is an important data analysis technique, which has been applied to many practical scenarios. However, many partitioning based clustering algorithms are sensitive to the initial state of cluster centroids, may get trapped in a local optimum, and have poor robustness. In recent years, particle swarm optimization (PSO) has been regarded as an effective solution to the problem. However, it has the possibility of converging to a local optimum, especially when solving complex problems. In this paper, we propose a hybrid PSO-K-means algorithm, which uses the Gaussian estimation of distribution method (GEDM) to assist PSO in updating the population information and adopts Lé vy flight to escape from the local optimum. The proposed algorithm is named a GEDM and Lé vy flight based PSO-K-means (GLPSOK) clustering algorithm. Firstly, during initialization, a few particles are initialized using the cluster centroids generated by K-means, while other particles are randomly initialized in the search space. Secondly, GEDM and PSO are selected with different probability to update the population information at different optimization stages. Thirdly, Lé vy flight is adopted to help the search escape from the local optimum. Finally, the greedy strategy is carried out to select the promising particles from the parents and the newly generated candidates. Experimental results on both synthetic data sets and real-world data sets show that the proposed algorithm can produce better clustering results and is more robust than existing classic or state-ofthe-art clustering algorithms. INDEX TERMS Data clustering, K-means, particle swarm optimization, Gaussian estimation of distribution method, Lé vy flight.

show abstract

Section: ) Stagnation Disturbance Strategymentioning

confidence: 91%

A Novel Hybrid PSO-K-Means Clustering Algorithm Using Gaussian Estimation of Distribution Method and Lévy Flight

Gao

Kabalyants

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In Jensi and Jiji, 39 the velocity of the particles is updated using the Lévy flight. In Hariya et al, 40 the Lévy flight has been applied to the inertia coefficient of PSO. In Jana and Sil, 41 the Lévy flight has been applied to a percentage of particles except the global best particle, which uses a polynomial mutation.…”

Section: Adap-psomentioning

confidence: 99%

An adaptive particle swarm optimization method for multi-objective system reliability optimization

Mellal

Zio

2019

Proceedings of the IMechE

View full text Add to dashboard Cite

Multi-objective system reliability optimization has attracted the attention of several researchers, due to its importance in industry. In practice, the optimization regards multiple objectives, for example, maximize the reliability, minimize the cost, weight, and volume. In this article, an adaptive particle swarm optimization is presented for multi-objective system reliability optimization. The approach uses a Lévy flight for some particles of the swarm, for avoiding local optima and insuring diversity in the exploration of the search space. The multi-objective problem is converted to a single-objective problem by resorting to the weighted-sum method and a penalty function is implemented to handle the constraints. Nine numerical case studies are presented as benchmark problems for comparison; the results show that the proposed approach has superior performance than a standard particle swarm optimization.

show abstract

“…where α is the location parameter and β is the scale parameter. Thus, Lévy flight can be regarded as a fractional stochastic process, and has obtained some good computational results in the applications of optimization [61]. The connection of Lévy flight and extreme learning machine may gain better computational effects, and even bring an obvious improvement of machine learning.…”

Section: Challenges and Trends In Fnnmentioning

confidence: 99%

A Survey of Fractional-Order Neural Networks

Zhang

Chen

2017

Volume 9: 13th ASME/IEEE International Conference on Mechatronic and Embedded Systems and Applications

View full text Add to dashboard Cite

In this paper, the literature of fractional-order neural networks is categorized and discussed, which includes a general introduction and overview of fractional-order neural networks. Various application areas of fractional-order neural networks have been found or used, and will be surveyed and summarized such as neuroscience, computational science, control and optimization. Recent trends in dynamics of fractional-order neural networks are presented and discussed. The results, especially the stability analysis of fractional-order neural networks, are reviewed and different analysis methods are compared. Furthermore, the challenges and conclusions of fractional-order neural networks are given.

show abstract

Lévy flight PSO

Cited by 19 publications

References 8 publications

A Novel Hybrid PSO-K-Means Clustering Algorithm Using Gaussian Estimation of Distribution Method and Lévy Flight

A Novel Hybrid PSO-K-Means Clustering Algorithm Using Gaussian Estimation of Distribution Method and Lévy Flight

An adaptive particle swarm optimization method for multi-objective system reliability optimization

A Survey of Fractional-Order Neural Networks

Contact Info

Product

Resources

About