首页 | 本学科首页   官方微博 | 高级检索  
     

基于CRBM算法的时间序列预测模型研究
引用本文:周晓莉,张丰,杜震洪,曹敏杰,刘仁义. 基于CRBM算法的时间序列预测模型研究[J]. 浙江大学学报(理学版), 2016, 43(4): 442-451. DOI: 10.3785/j.issn.1008-9497.2016.04.011
作者姓名:周晓莉  张丰  杜震洪  曹敏杰  刘仁义
作者单位:1. 浙江大学 浙江省资源与环境信息系统重点实验室, 浙江 杭州 310028;
2. 浙江大学 地球科学学院, 浙江 杭州 310027
基金项目:国家自然科学基金资助项目(41471313,41101356,41101371,41171321);国家科技基础性工作专项(2012FY112300);海洋公益性行业科研专项经费资助(2015418003,201305012)
摘    要:针对受限玻尔兹曼机(restricted Boltzmann machines,RBM)算法对时序数据预测存在抽取抽象特征向量能力较差和梯度下降能力有限的问题,基于CRBM(conditional restricted Boltzmann machines)算法以及信念网络(deep belief network,DBN)模型,构建了一种非线性的CRBM-DBN深度学习模型,并采用高斯分布处理输入特征值和对比散度抽样,用于预测时序数据.实验以浙江省近岸海域赤潮时序数据作为输入特征值,讨论该模型的深度及参数选取,并与经典的深度学习模型RBM、DAE和浅层学习中的BP神经网络进行对比,实验验证CRBM对于赤潮时序数据的预测拟合度要明显优于其他3种模型,该模型可有效用于赤潮类时序数据的趋势性预测.

关 键 词:受限玻尔兹曼机  CRBM深度建模  深度信念网络模型  高斯分布  
收稿时间:2015-08-06

A study on time series prediction model based on CRBM algorithm
ZHOU Xiaoli;ZHANG Feng;DU Zhenhong;CAO Minjie;LIU Renyi. A study on time series prediction model based on CRBM algorithm[J]. Journal of Zhejiang University(Sciences Edition), 2016, 43(4): 442-451. DOI: 10.3785/j.issn.1008-9497.2016.04.011
Authors:ZHOU Xiaoli  ZHANG Feng  DU Zhenhong  CAO Minjie  LIU Renyi
Affiliation:1. Zhejiang Provincial Key Laboratory of Resources and Environmental Information System, Zhejiang University , Hangzhou 310028, China;
2. Department of Earth Sciences, Zhejiang University, Hangzhou 310027, China
Abstract:Restricted Boltzmann machines (RBM) algorithm has a poor performance in extracting feature vector and gradient descent when it is used to predict time-series data. To solve the above problems, a non-linear deep learning model was constructed based on conditional restricted Boltzmann machines (CRBM) combining with deep belief network (DBN). The model processed the input feature vectors with Gaussian distribution and samples with classical contrastive divergence to predict continuous time-series data. Our experiment adopted the time-series data of red tide in Zhejiang costal, and discussed the selection of network depth and training parameters in the model, then compared the deep learning model to classical RBM, DAE deep learning network and BP neural network shadow learning. The results showed that the prediction fitting of CRBM was superior to the other three models. This model can effectively predict the time-series of red tide.
Keywords:restricted Boltzmann machines  deep architecture of CRBM  deep belief network model  Gaussian distribution
本文献已被 CNKI 等数据库收录!
点击此处可从《浙江大学学报(理学版)》浏览原始摘要信息
点击此处可从《浙江大学学报(理学版)》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号