Gradient-based Mechanism For PSO Algorithm: A Comparative Study On Numerical Benchmarks

Cavalca, Diego L.; Fernandes, Ricardo Augusto Souza

doi:10.1109/cec.2018.8477798

Cited by 8 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The OMO algorithm has superior performance in most standard test functions. Table 6 shows the details of the six representative standard test functions [ 61 , 62 ]. The population number N and maximum iterations of the OMO optimizer are set to 30 and 300, respectively.…”

Section: Methodsmentioning

confidence: 99%

A Novel Method for Source Tracking of Chemical Gas Leakage: Outlier Mutation Optimization Algorithm

Xia

et al. 2021

Sensors

View full text Add to dashboard Cite

Chemical industrial parks, which act as critical infrastructures in many cities, need to be responsive to chemical gas leakage accidents. Once a chemical gas leakage accident occurs, risks of poisoning, fire, and explosion will follow. In order to meet the primary emergency response demands in chemical gas leakage accidents, source tracking technology of chemical gas leakage has been proposed and evolved. This paper proposes a novel method, Outlier Mutation Optimization (OMO) algorithm, aimed to quickly and accurately track the source of chemical gas leakage. The OMO algorithm introduces a random walk exploration mode and, based on Swarm Intelligence (SI), increases the probability of individual mutation. Compared with other optimization algorithms, the OMO algorithm has the advantages of a wider exploration range and more convergence modes. In the algorithm test session, a series of chemical gas leakage accident application examples with random parameters are first assumed based on the Gaussian plume model; next, the qualitative experiments and analysis of the OMO algorithm are conducted, based on the application example. The test results show that the OMO algorithm with default parameters has superior comprehensive performance, including the extremely high average calculation accuracy: the optimal value, which represents the error between the final objective function value obtained by the optimization algorithm and the ideal value, reaches 2.464e-15 when the number of sensors is 16; 2.356e-13 when the number of sensors is 9; and 5.694e-23 when the number of sensors is 4. There is a satisfactory calculation time: 12.743 s/50 times when the number of sensors is 16; 10.304 s/50 times when the number of sensors is 9; and 8.644 s/50 times when the number of sensors is 4. The analysis of the OMO algorithm’s characteristic parameters proves the flexibility and robustness of this method. In addition, compared with other algorithms, the OMO algorithm can obtain an excellent leakage source tracing result in the application examples of 16, 9 and 4 sensors, and the accuracy exceeds the direct search algorithm, evolutionary algorithm, and other swarm intelligence algorithms.

show abstract

Section: Methodsmentioning

confidence: 99%

A Novel Method for Source Tracking of Chemical Gas Leakage: Outlier Mutation Optimization Algorithm

Xia

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Despite the global optimization performance of stochastic optimization algorithms such as GAs (23) and PSO algorithms (6), the computational effort is expended because of these algorithms' random search performance. Nevertheless, while deterministic algorithms such as gradient descent have rapid convergence, they do tend to get stuck in multi-modal functions' local minima.…”

Section: Updatementioning

confidence: 99%

Hybrid Gradient Strategies in Event Focused Web Crawling

Rajiv¹

2022

ECS Trans.

View full text Add to dashboard Cite

Crawling is defined as the automated and systematic collection of useful web pages with an interconnecting link structure. Live web crawling that is dependent on human, expert-nominated seed URIs is employed for the general construction of event collections. In the focused web crawling technique, the crawler is guided by reference content that pertains to a particular event. With this technique, a focused crawler will attempt to predict if a target URL is directed towards a relevant web page prior to retrieving it. However, it can get trapped within a limited web community and overlook relevant web pages outside its track. For web crawling optimization as well as for the selection of more relevant web pages for retrieval by the crawler, a metaheuristic algorithm is employed. A global searching algorithm’s modification can address the problems. The utilization of basic heuristic algorithms and prohibition techniques forms the basis of the Tabu Search (TS). Swarm intelligence is used by the Particle Swarm Optimization (PSO) to identify an optimization problem’s solution. This is done by a generation of better candidate feature subsets as per a given ﬁtness criteria and rapid convergence towards a global optimum within a set number of iterations. Hence, the proposed gradient-based algorithm will present a more rapid convergence for the PSO than the other variants. A proposal for a hybrid Stochastic Gradient Descent-Particle Swarm Optimization has also been presented in this work.

show abstract

“…Önerilen algoritma yaygın olarak kullanılan dört işlev üzerinde daha iyi yakınsama özelliği gösterdi. Cavalca ve Fernandes [31] türev temelli bir sayısal yöntemi Parçacık Sürü Optimizasyonuna dâhil etmişlerdir. Önerilen yöntemin sonuçlarını üç farklı algoritmanın sonuçları ile sekiz yaygın işlev üzerinde karşılaştırdılar.…”

Section: Li̇teratür Taramasi (Literature Review)unclassified

Yaygın kullanılan bazı optimizasyon fonksiyonlarının melez bir algoritma ile çözümü

Cengiz

Çomak

2021

Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi

View full text Add to dashboard Cite

Designing a new hybrid optimization algorithm  Providing a new perspective to achieve optimized results  Designing an optimization algorithm for faster reach optimized solutionsIn this study, the development of a hybrid optimization method has been emphasized in order to eliminate the deficiencies in the structure of heuristic and numerical methods. In our applications, Particle Swarm Optimization (PSO) method and Broydon-Fletcher-Goldfarb-Shanno (BFGS) method are aimed to reach the optimum solution more accurately and faster. In the algorithm of the developed optimization method, the solution is firstly sought with BFGS. Optimum result points are screened using PSO. Until the final result is reached, the intermediate solution points are continuously transferred between the BFGS and the PSO. Using the original BFGS and the original PSO, two different methods are proposed: BFGS first, then PSO hybrid method, and vice versa hybrid method (first PSO then BFGS). Figure A. Recycled aggregate productionPurpose: Although numerical optimization algorithms guarantee the exact solution, they remain relatively slow. On the other hand, heuristic optimization algorithms are fast but they cannot guarantee the exact solution.From this point of view, it is aimed to design an algorithm that achieves both fast and exact solutions.Theory and Methods: In this study, it is proposed that numerical and heuristic methods can be hybridized and exact solutions can be reached faster. In the literature, hybrid optimization algorithms apply heuristic and then numerical approaches. In the developed method, the opposite way was followed. Results:The developed method was tested on the functions used in the literature for testing purposes. Accordingly, as the test function becomes more complex, the speed of the solution is slow in milliseconds according to the comparison algorithm. Conclusion:Consequently, the combination of numerical methods such as BFGS and heuristic methods such as PSO may be an appropriate approach for solution accuracy. As intended in this study, heuristics can be hybridized with other numerical methods. On the other hand, the literature research and the proposed algorithm proved that hybrid algorithms obtained better results than standard heuristics and numerical methods.

show abstract

Gradient-based Mechanism For PSO Algorithm: A Comparative Study On Numerical Benchmarks

Cited by 8 publications

References 12 publications

A Novel Method for Source Tracking of Chemical Gas Leakage: Outlier Mutation Optimization Algorithm

A Novel Method for Source Tracking of Chemical Gas Leakage: Outlier Mutation Optimization Algorithm

Hybrid Gradient Strategies in Event Focused Web Crawling

Yaygın kullanılan bazı optimizasyon fonksiyonlarının melez bir algoritma ile çözümü

Contact Info

Product

Resources

About