Bootstrapped artificial neural networks for synthetic flow generation with a small data sample

Jia, Yong; Culver, Teresa B.

doi:10.1016/j.jhydrol.2006.06.005

Cited by 61 publications

(27 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…While implicit methods rely on randomness to generate diversity, explicit methods deterministically generate diversity. For example, Bagging (short for Bootstrap Aggregation Learning) employs an implicit strategy to achieve diversity [8,24]. Bagging randomly samples the training data set by applying bootstrap to create a different training data set for each individual predictor [13]; at no point is a measurement taken to promote diversity.…”

Section: Key Factors In Ensemble Systemsmentioning

confidence: 99%

“…In machine learning, bootstrap is employed to expand upon a single realization of a distribution or generate different data sets that can provide a better understanding of the mean and variability of the original unknown distribution [24]. Bootstrap is performed by randomly sampling with replacement from the original training data set D train .…”

Section: Training Validation and Testing Data Setsmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of a genetic algorithm and simulated annealing for automatic neural network ensemble development

2013

View full text Add to dashboard Cite

In the last decades ensemble learning has established itself as a valuable strategy within the computational intelligence modeling and machine learning community. Ensemble learning is a paradigm where multiple models combine in some way their decisions, or their learning algorithms, or different data to improve the prediction performance. Ensemble learning aims at improving the generalization ability and the reliability of the system. Key factors of ensemble systems are diversity, training and combining ensemble members to improve the ensemble system performance. Since there is no unified procedure to address all these issues, this work proposes and compares Genetic Algorithm and Simulated Annealing based approaches for the automatic development of Neural Network Ensembles for regression problems. The main contribution of this work is the development of optimization techniques that select the best subset of models to be aggregated taking into account all the key factors of ensemble systems (e.g., diversity, training ensemble members and combination strategy). Experiments on two well-known data sets are reported to evaluate the effectiveness of the proposed methodologies. Results show that these outperform other approaches including Simple Bagging, Negative Correlation Learning (NCL), AdaBoost and GASEN in terms of generalization ability.

show abstract

Section: Key Factors In Ensemble Systemsmentioning

confidence: 99%

Section: Training Validation and Testing Data Setsmentioning

confidence: 99%

Comparison of a genetic algorithm and simulated annealing for automatic neural network ensemble development

2013

View full text Add to dashboard Cite

show abstract

“…Besides reducing uncertainty in the variance by mimicking randomness [EFRON, TIBSHIRANI 1993], ANN B models are simpler and easier to use in addressing uncertainty in an operational setting compared to Bayesian approaches [ISUKAPALLI, GEOR-GOPOULOS 2001]. Several studies have shown ANN B models to outperform standard ANN models [ABRA-HART 2003;HAN et al 2007;JEONG, KIM 2005;JIA, CULVER 2006;SHARMA, TIWARI 2009;SRIVASTAV et al 2007;TIWARI, CHATTERJEE, 2010a]. Both ANN W and ANN B hybrid approaches can be combined to form a wavelet-bootstrap-ANN (ANN WB ) model with the potential ability to achieve greater accuracy and reliability in real time water demand forecasting.…”

Section: Introductionmentioning

confidence: 99%

Water demand forecasting using extreme learning machines

Tiwari¹,

Adamowski²,

Adamowski³

2016

Journal of Water and Land Development

View full text Add to dashboard Cite

The capacity of recently-developed extreme learning machine (ELM) modelling approaches in forecasting daily urban water demand from limited data, alone or in concert with wavelet analysis (W) or bootstrap (B) methods (i.e., ELM, ELM W , ELM B ), was assessed, and compared to that of equivalent traditional artificial neural network-based models (i.e., ANN, ANN W , ANN B ). The urban water demand forecasting models were developed using 3-year water demand and climate datasets for the city of Calgary, Alberta, Canada. While the hybrid ELM B and ANN B models provided satisfactory 1-day lead-time forecasts of similar accuracy, the ANN W and ELM W models provided greater accuracy, with the ELM W model outperforming the ANN W model. Significant improvement in peak urban water demand prediction was only achieved with the ELM W model. The superiority of the ELM W model over both the ANN W or ANN B models demonstrated the significant role of wavelet transformation in improving the overall performance of the urban water demand model.

show abstract

“…However, it is not robust in the presence of outliers. Several studies applied the LOC for extending stream-flow records (e.g., Hirsch, 1982;Hirsch et al, 1991;Jia and Culver, 2006;Ryu et al, 2010), for estimation of missing precipitation values (e.g. Raziei et al, 2009Raziei et al, , 2011, and also for extension of water quality records (e.g.…”

Section: Introductionmentioning

confidence: 99%

Record extension for short-gauged water quality parameters using a newly proposed robust version of the Line of Organic Correlation technique

Khalil

Adamowski

2012

Hydrol. Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. In many situations the extension of hydrological or water quality time series at short-gauged stations is required. Ordinary least squares regression (OLS) of any hydrological or water quality variable is a traditional and commonly used record extension technique. However, OLS tends to underestimate the variance in the extended records, which leads to underestimation of high percentiles and overestimation of low percentiles, given that the data are normally distributed. The development of the line of organic correlation (LOC) technique is aimed at correcting this bias. On the other hand, the Kendall-Theil robust line (KTRL) method has been proposed as an analogue of OLS with the advantage of being robust in the presence of outliers. Given that water quality data are characterised by the presence of outliers, positive skewness and non-normal distribution of data, a robust record extension technique is more appropriate. In this paper, four record-extension techniques are described, and their properties are explored. These techniques are OLS, LOC, KTRL and a new technique proposed in this paper, the robust line of organic correlation technique (RLOC). RLOC includes the advantage of the LOC in reducing the bias in estimating the variance, but at the same time it is also robust in the presence of outliers. A Monte Carlo study and empirical experiment were conducted to examine the four techniques for the accuracy and precision of the estimate of statistical moments and over the full range of percentiles. Results of the Monte Carlo study showed that the OLS and KTRL techniques have serious deficiencies as record-extension techniques, while the LOC and RLOC techniques are nearly similar. However, RLOC outperforms OLS, KTRL and LOC when using real water quality records.

show abstract

Bootstrapped artificial neural networks for synthetic flow generation with a small data sample

Cited by 61 publications

References 22 publications

Comparison of a genetic algorithm and simulated annealing for automatic neural network ensemble development

Comparison of a genetic algorithm and simulated annealing for automatic neural network ensemble development

Water demand forecasting using extreme learning machines

Record extension for short-gauged water quality parameters using a newly proposed robust version of the Line of Organic Correlation technique

Contact Info

Product

Resources

About