Examination of benefits of personal fitness improvement dependent inertia for Particle Swarm Optimization

Družeta, Siniša; Ivić, Stefan

doi:10.1007/s00500-015-2016-7

Cited by 12 publications

(18 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the originally proposed inertia switching technique reduces the overall velocity of the swarm, it would be reasonable to expect that the method would benefit from compensation in the form of increased inertia weight. This was also indicated by the results of the benchmark testing given in previous research [3], thus the aforementioned amplification coefficient was introduced in order to address this issue.…”

Section: Languid Particle Dynamicsmentioning

confidence: 95%

“…One possible technique for this is using fitness improvement as a prerequisite for particle inertia. As probably the simplest method for this, a basic switch-like condition on inertia term 3 of each individual particle [3] is used:…”

Section: Languid Particle Dynamicsmentioning

confidence: 99%

“…Note that (4) employs a correction of +0.05 for inertia weight when inertia is not disabled. This represents a modification of the original inertia handling technique of Languid PSO [3], which used no such correction. Since the originally proposed inertia switching technique reduces the overall velocity of the swarm, it would be reasonable to expect that the method would benefit from compensation in the form of increased inertia weight.…”

Section: Languid Particle Dynamicsmentioning

confidence: 99%

“…Here f best stands for final best-of-swarm fitness value, averaged across 1000 computational runs, while f stands for known global minimum of goal function f . Furthermore, so as to provide a relative comparison of the selected methods' performance, a dimensionless rating α is used [3]: and may reasonably be averaged across test functions and then used as a bulk value representing overall method score, while its values stay confined to the interval [−2, 2] with ε X L = ε X yielding α = 0. Note that the definition of (15) is extended so that α = 0 for ε X L = ε X =0.…”

Section: Preliminary Testing Of Languid Particle Dynamics Effects On mentioning

confidence: 99%

See 3 more Smart Citations

Introducing languid particle dynamics to a selection of PSO variants

Družeta

Ivić

Grbčić

et al. 2020

Egyptian Informatics Journal

Self Cite

View full text Add to dashboard Cite

Previous research showed that conditioning a PSO agent's movement based on its personal fitness improvement enhances the standard PSO method. In this article, languid particle dynamics (LPD) technique is used on five adequate and widely used PSO variants.Five unmodified PSO variants were tested against their LPD-implemented counterparts on three search space dimensionalities (10, 20, and 50 dimensions) and 30 test functions of the CEC 2014 benchmark test. In the preliminary phase of the testing four of the five tested PSO variants showed improvement in accuracy. The worst and best-achieving variants from preliminary test went through detailed investigation on 220 and 770 combinations of method parameters, where both variants showed overall gains in accuracy when enhanced with LPD. Finally, the results obtained with best achieving PSO parameters were subject to statistical analysis which showed that the two variants give statistically significant improvements in accuracy for 13-50% of the test functions.

show abstract

Section: Languid Particle Dynamicsmentioning

confidence: 95%

Section: Languid Particle Dynamicsmentioning

confidence: 99%

Section: Languid Particle Dynamicsmentioning

confidence: 99%

Section: Preliminary Testing Of Languid Particle Dynamics Effects On mentioning

confidence: 99%

See 2 more Smart Citations

Introducing languid particle dynamics to a selection of PSO variants

Družeta

Ivić

Grbčić

et al. 2020

Egyptian Informatics Journal

Self Cite

View full text Add to dashboard Cite

show abstract

“…The parameters that influence the movement of each particle include the inertia factor w , cognitive and social factors

and

. The languid particle dynamics modification [ 66 ] was used which involves setting the inertia of a particle to zero if it is not moving in the direction of better fitness. This modification was used as it proved beneficial to the standard PSO algorithm on the problem of water distribution pipe network routing [ 67 ].…”

Section: Materials and Methodsmentioning

confidence: 99%

Machine Learning and Simulation-Optimization Coupling for Water Distribution Network Contamination Source Detection

Grbčić

Kranjčević

Družeta

2021

Sensors

Self Cite

View full text Add to dashboard Cite

This paper presents and explores a novel methodology for solving the problem of a water distribution network contamination event, which includes determining the exact source of contamination, the contamination start and end times and the injected contaminant concentration. The methodology is based on coupling a machine learning algorithm for predicting the most probable contamination sources in a water distribution network with an optimization algorithm for determining the values of contamination start time, end time and injected contaminant concentration for each predicted node separately. Two slightly different algorithmic frameworks were constructed which are based on the mentioned methodology. Both algorithmic frameworks utilize the Random Forest algorithm for classification of top source contamination node candidates, with one of the frameworks directly using the stochastic fireworks optimization algorithm to determine the contamination start time, end time and injected contaminant concentration for each predicted node separately. The second framework uses the Random Forest algorithm for an additional regression prediction of each top node’s start time, end time and contaminant concentration and is then coupled with the deterministic global search optimization algorithm MADS. Both a small sized (92 potential sources) network with perfect sensor measurements and a medium sized (865 potential sources) benchmark network with fuzzy sensor measurements were used to explore the proposed frameworks. Both algorithmic frameworks perform well and show robustness in determining the true source node, start and end times and contaminant concentration, with the second framework being extremely efficient on the fuzzy sensor measurement benchmark network.

show abstract

Parameter Search for a Small Swarm of AUVs Using Particle Swarm Optimisation

Tholen

Nolle

2017

Artificial Intelligence XXXIV

View full text Add to dashboard Cite

Examination of benefits of personal fitness improvement dependent inertia for Particle Swarm Optimization

Cited by 12 publications

References 18 publications

Introducing languid particle dynamics to a selection of PSO variants

Introducing languid particle dynamics to a selection of PSO variants

Machine Learning and Simulation-Optimization Coupling for Water Distribution Network Contamination Source Detection

Parameter Search for a Small Swarm of AUVs Using Particle Swarm Optimisation

Contact Info

Product

Resources

About