Map-reduce framework-based non-iterative granular echo state network for prediction intervals construction
作者： Chunyang Sheng , Jun Zhao , Wei Wang
DOI: 10.1016/J.NEUCOM.2016.10.019
关键词:
摘要: When using interval-weighted granular neural networks (NNs) for prediction intervals (PIs) construction, the iterative mode is always accompanied with error accumulation that detrimental to reliability of PIs. In this study, a echo state network (ESN) developed PIs in which connections are represented by interval-valued information granules. To cope caused mode, non-iterative proposed here ESN. The training process ESN can be viewed as optimization allocation granularity, particle swarm (PSO)-based approach employed solving problem, and evaluation criteria performance, including coverage probability (PICP) mean width (MPIW), chosen optimized objectives. improve computational accuracy efficiency, Map-Reduce (MR) framework designed programming implementation PSO-based process. Two kinds time series data, two benchmark problems industrial ones coming from gas system steel industry, verify effectiveness method. experimental results indicate provides good performance construction.
acm.org
sci-hub.se 参考文章(33)
Mario G. C. A. Cimino, Beatrice Lazzerini, Francesco Marcelloni, Witold Pedrycz, Granular data regression with neural networks international workshop on fuzzy logic and applications. pp. 172- 179 ,(2011) , 10.1007/978-3-642-23713-3_22
Christopher M. Bishop, Neural networks for pattern recognition ,(1995)
D.A. Nix, A.S. Weigend, Estimating the mean and variance of the target probability distribution world congress on computational intelligence. ,vol. 1, pp. 55- 60 ,(1994) , 10.1109/ICNN.1994.374138
Nasullah Khalid Alham, Maozhen Li, Yang Liu, Man Qi, A MapReduce-based distributed SVM ensemble for scalable image classification and annotation Computers & Mathematics with Applications. ,vol. 66, pp. 1920- 1934 ,(2013) , 10.1016/J.CAMWA.2013.07.015
Richard D. de Veaux, Jennifer Schumi, Jason Schweinsberg, Lyle H. Ungar, Prediction intervals for neural networks via nonlinear regression Technometrics. ,vol. 40, pp. 273- 282 ,(1998) , 10.2307/1270528
Chunyang Sheng, Jun Zhao, Wei Wang, H. Leung, Prediction Intervals for a Noisy Nonlinear Time Series Based on a Bootstrapping Reservoir Computing Network Ensemble IEEE Transactions on Neural Networks. ,vol. 24, pp. 1036- 1048 ,(2013) , 10.1109/TNNLS.2013.2250299
Ying Liu, Quanli Liu, Wei Wang, Jun Zhao, Henry Leung, Data-driven based model for flow prediction of steam system in steel industry Information Sciences. ,vol. 193, pp. 104- 114 ,(2012) , 10.1016/J.INS.2011.12.031
Mingli Song, W. Pedrycz, Granular Neural Networks: Concepts and Development Schemes IEEE Transactions on Neural Networks. ,vol. 24, pp. 542- 553 ,(2013) , 10.1109/TNNLS.2013.2237787
Yanbo Xue, Le Yang, Simon Haykin, 2007 Special Issue: Decoupled echo state networks with lateral inhibition Neural Networks. ,vol. 20, pp. 365- 376 ,(2007) , 10.1016/J.NEUNET.2007.04.014
Ruijun Dong, Witold Pedrycz, A granular time series approach to long-term forecasting and trend forecasting Physica A-statistical Mechanics and Its Applications. ,vol. 387, pp. 3253- 3270 ,(2008) , 10.1016/J.PHYSA.2008.01.095