Dominance measures for multi-objective simulated annealing

Smith, Kevin; Everson, Richard; Fieldsend, Jonathan E.

doi:10.1109/cec.2004.1330833

Cited by 67 publications

(86 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This can result in a coarse acceptance probability distribution meaning that a slightly worse fit or complexity can result in a large reduction in acceptance probability. Smith et al (2004) present a number of methods to alleviate this problem. The solution we choose to prevent this is to create extra points evenly spread on the attainment surface of the APF as described in Smith et al (2004).…”

Section: Pareto Simulated Annealingmentioning

confidence: 99%

See 1 more Smart Citation

Metamodeling by symbolic regression and Pareto simulated annealing

Stinstra¹,

Rennen

Teeuwen³

2007

Struct Multidisc Optim

View full text Add to dashboard Cite

The subject of this paper is a new approach to symbolic regression. Other publications on symbolic regression use genetic programming. This paper describes an alternative method based on Pareto simulated annealing. Our method is based on linear regression for the estimation of constants. Interval arithmetic is applied to ensure the consistency of a model. To prevent overfitting, we merit a model not only on predictions in the data points, but also on the complexity of a model. For the complexity, we introduce a new measure. We compare our new method with the Kriging metamodel and against a symbolic regression metamodel based on genetic programming. We conclude that Pareto-simulated-annealing-based symbolic regression is very competitive compared to the other metamodel approaches.

show abstract

Section: Pareto Simulated Annealingmentioning

confidence: 99%

“…For this, we choose to use the dominance-based performance measure. This measure is introduced in Smith et al (2004) for general Pareto simulated annealing and solves some drawbacks of more traditional measures like the weighted sum. The dominance-based performance measure is defined by:…”

Section: Pareto Simulated Annealingmentioning

confidence: 99%

Metamodeling by symbolic regression and Pareto simulated annealing

Stinstra¹,

Rennen

Teeuwen³

2007

Struct Multidisc Optim

View full text Add to dashboard Cite

show abstract

“…The most recent approaches weight the different criteria into a scalar function [19,31,45]. Otherwise, in [8] it was proposed to use the dominance to decide the evolution of the simulated annealing.…”

Section: Evolutionary Transparent Modeling Of Chaotic Systemsmentioning

confidence: 99%

Multiobjective Evolutionary Search of Difference Equations-based Models for Understanding Chaotic Systems

Sánchez

Villar

2008

Foundations of Generic Optimization

View full text Add to dashboard Cite

In control engineering, it is well known that many physical processes exhibit a chaotic component. In point of fact, it is also assumed that conventional modeling procedures disregard it, as stochastic noise, beside nonlinear universal approximators (like neural networks, fuzzy rule-based or genetic programming-based models,) can capture the chaotic nature of the process.In this chapter we will show that this is not always true. Despite the nonlinear capabilities of the universal approximators, these methods optimize the one step prediction of the model. This is not the most adequate objective function for a chaotic model, because there may exist many different nonchaotic processes that have near zero prediction error for such an horizon. The learning process will surely converge to one of them. Unless we include in the objective function some terms that depend on the properties on the reconstructed attractor, we may end up with a non chaotic model. Therefore, we propose to follow a multiobjective approach to model chaotic processes, and we also detail how to apply either genetic algorithms or simulated annealing to obtain a difference equations-based model.

show abstract

“…The necessary extensions required for multi-objective maximisation are described by Smith et al [23]. We used the energy difference method of Smith et al [22] for archiving, generated a first current solution to (7)−(10) randomly to initiate the SA search, and selected an initial temperature according to the average increase method suggested by Busetti [2] and Triki et al [25]. We also implemented the search epoch protocol described by Busetti [2] with epoch lengths chosen according to the rule of thumb proposed by Dreo et al [6].…”

Section: Solving the Mathematical Model By Simulated Annealingmentioning

confidence: 99%

Optimisation of Radio Transmitter Locations in Mobile Telecommunication Networks

Schmidt-Dumont

Vuuren

2016

SAJIE

View full text Add to dashboard Cite

Multiple factors have to be taken into account when mobile telecommunication network providers make decisions about radio transmitter placement. Generally, area coverage and the average signal level provided are of prime importance in these decisions. These criteria give rise to a bi-objective problem of facility location, with the goal of achieving an acceptable trade-off between maximising the total area coverage and maximising the average signal level provided to the demand region by a network of radio transmitters. This paper establishes a mathematical modelling framework, based on these two placement criteria, for evaluating the effectiveness of a given set of radio transmitter locations. In the framework, coverage is measured according to the degree of obstruction of the so-called 'Fresnel zone' that is formed between handset and base station, while signal strength is modelled taking radio wave propagation loss into account. This framework is used to formulate a novel bi-objective facility location model that may form the basis for decision support aimed at identifying high-quality transmitter location trade-off solutions for mobile telecommunication network providers. But it may also find application in various other contexts (such as radar, watchtower, or surveillance camera placement optimisation). OPSOMMINGVerskeie faktore moet in ag geneem word wanneer radiosenderplasingsbesluite deur mobiele telekommunikasienetwerke gemaak word. In die algemeen word area-oordekking en gemiddelde seinsterkte in hierdie besluite as belangrike kriteria geag. Hierdie kriteria gee aanleiding tot 'n twee-doelige fasiliteitplasingsprobleem gemik op die soeke na aanvaarbare afruilings tussen die maksimering van totale area-oordekking en die maksimering van gemiddelde seinsterkte aan gebiede waarin aanvraag na oordekking bestaan. 'n Wiskundige modelleringsraamwerk, gebaseer op hierdie twee plasingskriteria, word in hierdie artikel vir die evaluering van 'n versameling radiosenderliggings daargestel. In die raamwerk word oordekking gemeet volgens die mate waartoe die Fresnel-sone tussen die handtoestel en die basisstasie belemmer is, terwyl seinsterkte aan die hand van radiogolf-voortsettingsverliese gemodelleer word. Hierdie raamwerk word gebruik om 'n nuwe, twee-doelige fasiliteitplasingsmodel te formuleer wat as basis kan dien vir besluitsteun in die soeke na hoë-kwaliteit senderliggingsafruilings deur mobiele telekommunikasie-netwerkverskaffers, maar vind ook toepassing in verskeie ander kontekste (soos die optimale plasing van radars, uitkyktorings, of waarnemingskameras).

show abstract

Dominance measures for multi-objective simulated annealing

Cited by 67 publications

References 17 publications

Metamodeling by symbolic regression and Pareto simulated annealing

Metamodeling by symbolic regression and Pareto simulated annealing

Multiobjective Evolutionary Search of Difference Equations-based Models for Understanding Chaotic Systems

Optimisation of Radio Transmitter Locations in Mobile Telecommunication Networks

Contact Info

Product

Resources

About