Constructing Optimal Prediction Intervals by Using Neural Networks and Bootstrap Method

This brief proposes an efficient technique for the construction of optimized prediction intervals (PIs) by using the bootstrap technique. The method employs an innovative PI-based cost function in the training of neural networks (NNs) used for estimation of the target variance in the bootstrap method. An optimization algorithm is developed for minimization of the cost function and adjustment of NN parameters. The performance of the optimized bootstrap method is examined for seven synthetic and real-world case studies. It is shown that application of the proposed method improves the quality of constructed PIs by more than 28% over the existing technique, leading to narrower PIs with a coverage probability greater than the nominal confidence level.

[1]  J. T. Hwang,et al.  Prediction Intervals for Artificial Neural Networks , 1997 .

[2]  Abbas Khosravi,et al.  Particle swarm optimization for construction of neural network-based prediction intervals , 2014, Neurocomputing.

[3]  Debashis Kushary,et al.  Bootstrap Methods and Their Application , 2000, Technometrics.

[4]  Saeid Nahavandi,et al.  An optimized mean variance estimation method for uncertainty quantification of wind power forecasts , 2014 .

[5]  Tom Heskes,et al.  Practical Confidence and Prediction Intervals , 1996, NIPS.

[6]  Taher Niknam,et al.  Impact of thermal recovery and hydrogen production of fuel cell power plants on distribution feeder reconfiguration , 2012 .

[7]  Saeid Nahavandi,et al.  Load Forecasting Using Interval Type-2 Fuzzy Logic Systems: Optimal Type Reduction , 2014, IEEE Transactions on Industrial Informatics.

[8]  Amir F. Atiya,et al.  Lower Upper Bound Estimation Method for Construction of Neural Network-Based Prediction Intervals , 2011, IEEE Transactions on Neural Networks.

[9]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[10]  Xin-She Yang,et al.  Nature-Inspired Metaheuristic Algorithms , 2008 .

[11]  Bart De Schutter,et al.  DAISY : A database for identification of systems , 1997 .

[12]  Saeid Nahavandi,et al.  A prediction interval-based approach to determine optimal structures of neural network metamodels , 2010, Expert Syst. Appl..

[13]  David A. Nix,et al.  Learning Local Error Bars for Nonlinear Regression , 1994, NIPS.

[14]  Khashayar Khorasani,et al.  New training strategies for constructive neural networks with application to regression problems , 2004, Neural Networks.

[15]  Saeid Nahavandi,et al.  Construction of Optimal Prediction Intervals for Load Forecasting Problems , 2010, IEEE Transactions on Power Systems.

[16]  Abbas Khosravi,et al.  Short-Term Load and Wind Power Forecasting Using Neural Network-Based Prediction Intervals , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[17]  Saeid Nahavandi,et al.  Prediction Interval Construction and Optimization for Adaptive Neurofuzzy Inference Systems , 2011, IEEE Transactions on Fuzzy Systems.

[18]  M. Kenward,et al.  An Introduction to the Bootstrap , 2007 .

[19]  H. Künsch.  The Jackknife and the Bootstrap for General Stationary Observations , 1989 .

[20]  Aidong Adam Ding,et al.  Backpropagation of pseudo-errors: neural networks that are adaptive to heterogeneous noise , 2003, IEEE Trans. Neural Networks.

[21]  P. Bühlmann,et al.  Block length selection in the bootstrap for time series , 1999 .

[22]  Xin-She Yang,et al.  Firefly algorithm, stochastic test functions and design optimisation , 2010, Int. J. Bio Inspired Comput..