文献类型：期刊文献

英文题名：Multi-scale prediction of water temperature using empirical mode decomposition with back-propagation neural networks

作者：Liu, Shuangyin[1,2,3,4];Xu, Longqin[1];Li, Daoliang[2,3,4]

机构：[1]Guangdong Ocean Univ, Coll Informat, Zhanjiang 524025, Guangdong, Peoples R China;[2]China Agr Univ, Coll Informat & Elect Engn, Beijing 100083, Peoples R China;[3]China Agr Univ, Beijing ERC Internet Things Agr, Beijing 100083, Peoples R China;[4]China Agr Univ, Beijing ERC Adv Sensor Technol Agr, Beijing 100083, Peoples R China

年份：2016

卷号：49

起止页码：1

外文期刊名：COMPUTERS & ELECTRICAL ENGINEERING

收录：SCI-EXPANDED(收录号：WOS:000368208100001)、、EI(收录号：20161502216876)、Scopus(收录号：2-s2.0-84962434632)、WOS

基金：The authors would like to thank native English speaking expert Laurie Schiller to polish our paper. This research was supported by the Special Fund for Agro-scientific Research in the Public Interest (no. 201203017), National Natural Science Foundation Framework Project (no. 61471133), National Science and Technology Supporting Plan Project (no. 2012BAD35B07), Guangdong Science and Technology Plan Project (nos. 2013B090500127, 2013B021600014, 2015A070709015 and 2015A020209171), and Guangdong Natural Science Foundation Project (no. S2013010014629).

语种：英文

外文关键词：Empirical mode decomposition; Back-propagation neural network; Water temperature; Multi-scale prediction

外文摘要：In order to reduce aquaculture risks and optimize the operation of water quality management in prawn engineering culture ponds, this paper proposes a novel water temperature forecasting model based on empirical mode decomposition (EMD) and back-propagation neural network (BPNN). First, the original water temperature datasets are decomposed into a collection of intrinsic mode functions (IMFs) and a residue by EMD yields relatively stationary sub-series that can be readily modeled by BPNN. Second, both IMF components and residue is applied to establish the corresponding BPNN models. Then, each sub-series is predicted using the corresponding BPNN. Finally, the prediction values of the original water temperature datasets are calculated by the sum of the forecasting values of every sub-series. The proposed hybrid model was applied to predict water temperature in prawn culture ponds. Compared with traditional models, the simulation results of the hybrid EMD-BPNN model demonstrate that de-noising and capturing non-stationary characteristics of water temperature signals after EMD comprise a very powerful and reliable method for predicting water temperature in intensive aquaculture accurately and quickly. (C) 2015 Elsevier Ltd. All rights reserved.