Improving the quality of prediction intervals through optimal aggregation Hosen, Mohammad Anwar, Khosravi, Abbas, Nahavandi, Saeid and Creighton, Douglas 2015, Improving the quality of prediction intervals through optimal aggregation, IEEE Transactions on industrial electronics, vol. 62, no. 7, pp. 4420-4429, doi: 10.1109/TIE.2014.2383994. Attached Files Name Description MIMEType Size Downloads Title Improving the quality of prediction intervals through optimal aggregation Author(s) Hosen, Mohammad Anwar orcid.org/0000-0001-8282-3198 Khosravi, Abbas orcid.org/0000-0001-6927-0744 Nahavandi, Saeid orcid.org/0000-0002-0360-5270 Creighton, Douglas orcid.org/0000-0002-9217-1231 Journal name IEEE Transactions on industrial electronics Volume number 62 Issue number 7 Start page 4420 End page 4429 Total pages 10 Publisher Institute of Electrical and Electronics Engineers Place of publication Piscataway, N.J Publication date 2015-07 ISSN 0278-0046 Keyword(s) Aggregation Neural Network Prediction interval Simulated annealing Uncertainty and disturbance Weighted average Science & Technology Technology Automation & Control Systems Engineering, Electrical & Electronic Instruments & Instrumentation Engineering neural network (NN) prediction interval (PI) simulated annealing (SA) NEURAL-NETWORK ENSEMBLES FORECAST COMBINATION BATCH REACTOR POLYMERIZATION MODEL OPTIMIZATION PERFORMANCE ALGORITHM CONTROLLERS Summary Neural networks (NNs) are an effective tool to model nonlinear systems. However, their forecasting performance significantly drops in the presence of process uncertainties and disturbances. NN-based prediction intervals (PIs) offer an alternative solution to appropriately quantify uncertainties and disturbances associated with point forecasts. In this paper, an NN ensemble procedure is proposed to construct quality PIs. A recently developed lower-upper bound estimation method is applied to develop NN-based PIs. Then, constructed PIs from the NN ensemble members are combined using a weighted averaging mechanism. Simulated annealing and a genetic algorithm are used to optimally adjust the weights for the aggregation mechanism. The proposed method is examined for three different case studies. Simulation results reveal that the proposed method improves the average PI quality of individual NNs by 22%, 18%, and 78% for the first, second, and third case studies, respectively. The simulation study also demonstrates that a 3%-4% improvement in the quality of PIs can be achieved using the proposed method compared to the simple averaging aggregation method. Language eng DOI 10.1109/TIE.2014.2383994 Field of Research 080108 Neural, Evolutionary and Fuzzy Computation Socio Economic Objective 970109 Expanding Knowledge in Engineering HERDC Research category C1 Refereed article in a scholarly journal ERA Research output type C Journal article Copyright notice ©2015, IEEE Persistent URL http://hdl.handle.net/10536/DRO/DU:30076649 Document type: Journal Article Collections: Institute for Intelligent Systems Research and Innovation (IISRI) GTP Research Related Links Link Description Connect to published version Go to link with your DU access privileges     Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved. Versions Version Filter Type Tue, 25 Aug 2015, 14:40:47 EST Wed, 26 Aug 2015, 05:05:20 EST Wed, 26 Aug 2015, 08:14:41 EST Wed, 26 Aug 2015, 08:20:59 EST Wed, 26 Aug 2015, 09:43:42 EST Thu, 27 Aug 2015, 06:09:33 EST Mon, 31 Aug 2015, 13:55:51 EST Mon, 31 Aug 2015, 13:58:29 EST Filtered Full Citation counts:   Cited 34 times in TR Web of Science Cited 36 times in Scopus Search Google Scholar Access Statistics: 558 Abstract Views, 3 File Downloads  -  Detailed Statistics Created: Wed, 26 Aug 2015, 09:43:42 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.