Particle swarm optimization training algorithm for ANNs in stage prediction of Shing Mun River

Chau, Kwok Wing

doi:10.1016/j.jhydrol.2006.02.025

Cited by 298 publications

(124 citation statements)

References 18 publications

Supporting

Mentioning

122

Contrasting

Unclassified

Order By: Relevance

“…It has roots in two main component methodologies: artificial life (such as bird flocking, fish schooling and swarming); and, evolutionary computation. Although the PSO algorithm is initially developed as a tool for modeling social behavior, it has been applied in different areas (Kennedy et al, 2001;Clerc and Kennedy, 2002;Chau, 2004a & b;Chau, 2005;Chau, 2006). Moreover, it has been recognized as a computational intelligence technique intimately related to evolutionary algorithms.…”

Section: Particle Swarm Optimization (Pso) Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Application of a PSO-based neural network in analysis of outcomes of construction claims

Chau

2007

Automation in Construction

Self Cite

242

View full text Add to dashboard Cite

It is generally acknowledged that construction claims are highly complicated and are interrelated with a multitude of factors. It will be advantageous if the parties to a dispute may have some insights to some degree of certainty how the case would be resolved prior to the litigation process. By its nature, the use of artificial neural networks (ANN) can be a cost-effective technique to help to predict the outcome of construction claims, provided with characteristics of cases and the corresponding past court decisions. This paper presents the adoption of a particle swarm optimization (PSO) model to train perceptrons in predicting the outcome of construction claims in Hong Kong. It is illustrated that the successful prediction rate of PSO-based network is up to 80%. Moreover, it is capable of producing faster and more accurate results than its counterparts of a benching back-propagation ANN. This will furnish an alternative in assessing whether or not to take the case to litigation.

show abstract

Section: Particle Swarm Optimization (Pso) Algorithmmentioning

confidence: 99%

“…Equation (6) then determines the new position according to the new velocity (Kennedy et al, 2001;Clerc and Kennedy, 2002;Chau, 2006).…”

Section: Adaptation Of Pso To Network Trainingmentioning

confidence: 99%

Application of a PSO-based neural network in analysis of outcomes of construction claims

Chau

2007

Automation in Construction

Self Cite

242

View full text Add to dashboard Cite

show abstract

“…Two recent applications in hydrology are the parameter estimation of the Sacramento soil moisture accounting model (Gill et al, 2006) and in the training algorithm for an artificial neural network (ANN) in stage prediction of a river in Hong Kong (Chau, 2006). …”

Section: Particle Swarm Optimization (Pso)mentioning

confidence: 99%

Comparative assessment of six automatic optimization techniques for calibration of a conceptual rainfall—runoff model

Goswami

O’Connor

2007

Hydrological Sciences Journal

View full text Add to dashboard Cite

In this application-based study, six automated strategies of parameter optimization are used for calibration of the conceptual soil moisture accounting and routing (SMAR) model for rainfall-runoff simulation in two catchments, one small and the other large. The methods used are: the genetic algorithm, particle swarm optimization, Rosenbrock's technique, shuffled complex evolution of the University of Arizona, simplex search, and simulated annealing. A comparative assessment is made using the Nash-Sutcliffe model efficiency index and the mean relative error (MRE) to evaluate the performance of each optimization method. It is found that the degree of variation of the values of the water balance parameters is generally less for the small catchment than for the large one. In the case of both catchments, the probabilistic global population-based optimization method of simulated annealing is considered best in terms of having the least variability of parameter values in successive tests, thereby alleviating the phenomenon of equifinality in parameter optimization, and also in producing the lowest MRE in verification.Key words optimization; SMAR; genetic algorithm; Rosenbrock; simplex; particle swarm optimization; simulated annealing; shuffled complex evolution Evaluation comparative de six techniques automatiques d'optimisation pour le calage d'un modèle conceptuel pluie-débitRésumé Dans cette étude de mise en application, six stratégies automatiques d'optimisation de paramètres sont utilisées pour le calage du modèle conceptuel "soil moisture accounting and routing" (SMAR) pour la simulation pluie-débit dans deux bassins versants, l'un petit et l'autre grand. Les méthodes utilisées sont: l'algorithme génétique, l'optimisation par essaim de particules, la technique de Rosenbrock, la technique "shuffled complex evolution" de l'Université d'Arizona, la méthode du simplex et celle du recuit simulé. Une estimation comparative est menée à l'aide de l'indice d'efficience de modélisation de Nash-Sutcliffe et de l'erreur relative moyenne pour évaluer la performance de chaque méthode d'optimisation. Il apparaît que le degré de variation des valeurs des paramètres du bilan hydrologique est généralement inférieur pour le petit bassin versant que pour le grand. Dans le cas de l'ensemble des deux bassins, la méthode d'optimisation du recuit simulé, probabiliste globale basée sur la population, apparaît être la meilleure en termes de moindre variabilité des valeurs des paramètres au cours de tests successifs, ce qui atténue le phénomène d'équifinalité vis-à-vis de l'optimisation des paramètres et également de la minimisation de l'erreur relative moyenne lors de la vérification.

show abstract

“…This technique has been applied in hydrological problems and accomplished satisfactory results [13][14]. Moreover, a combination of global and local search methods, such as [15][16] can be explored.…”

Section: Introduction 26 27mentioning

confidence: 99%

“…The split-step is the key improvement over [13]. It is believed that, by combining the two algorithms, the advantages of global search capability of PSO algorithm in the first step and local fast convergence of LM algorithm in the second step can be fully utilized to furnish promising results.…”

Section: Introduction 26 27mentioning

confidence: 99%

A split-step particle swarm optimization algorithm in river stage forecasting

Chau

2007

Journal of Hydrology

Self Cite

113

View full text Add to dashboard Cite

8An accurate forecast of river stage is very significant so that there is ample time for the 9 pertinent authority to issue a forewarning of the impending flood and to implement early 10 evacuation measures as required. Since a variety of existing process-based hydrological 11 models involve exogenous input and different assumptions, artificial neural networks have 12 the potential to be a cost-effective solution. In this paper, a split-step particle swarm 13 optimization (PSO) model is developed and applied to train multi-layer perceptrons for 14 forecasting real-time water levels at Fo Tan in Shing Mun River of Hong Kong with different 15 lead times on the basis of the upstream gauging station (Tin Sum) or at Fo Tan. This 16 paradigm is able to combine the advantages of global search capability of PSO algorithm in 17 the first step and local fast convergence of Levenberg-Marquardt algorithm in the second step. 18The results demonstrate that it is able to attain a higher accuracy in a much shorter time when 19 compared with the benchmarking backward propagation algorithm as well as the standard 20 PSO algorithm. 21 22

show abstract

Particle swarm optimization training algorithm for ANNs in stage prediction of Shing Mun River

Cited by 298 publications

References 18 publications

Application of a PSO-based neural network in analysis of outcomes of construction claims

Application of a PSO-based neural network in analysis of outcomes of construction claims

Comparative assessment of six automatic optimization techniques for calibration of a conceptual rainfall—runoff model

A split-step particle swarm optimization algorithm in river stage forecasting

Contact Info

Product

Resources

About