[1]司阳,肖秦琨.基于长短时记忆和动态贝叶斯网络的序列预测[J].计算机技术与发展,2018,28(09):59-63.[doi:10.3969/j.issn.1673-629X.2018.09.013]
　SI Yang,XIAO Qin-kun.Time Series Prediction Based on Long-short Time Memory and Dynamic Bayesian Network[J].,2018,28(09):59-63.[doi:10.3969/j.issn.1673-629X.2018.09.013]
点击复制

基于长短时记忆和动态贝叶斯网络的序列预测()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年09期
页码:
59-63
栏目:
智能、算法、系统工程
出版日期:
2018-09-10

文章信息/Info

Title:
Time Series Prediction Based on Long-short Time Memory and Dynamic Bayesian Network
文章编号:
1673-629X(2018)09-0059-05
作者:
司阳;  肖秦琨
西安工业大学 电子信息工程学院,陕西 西安,710021
Author(s):
SI Yang; XIAO Qin-kun
School of Electronic Information Engineering,Xi’an Technological University,Xi’an 710021,China
关键词:
时间序列预测;  长短时记忆;  贝叶斯网络;  图模型
Keywords:
time series prediction; LSTM; DBN; graph model
分类号:
TP39
DOI:
10.3969/j.issn.1673-629X.2018.09.013
文献标志码:
A
摘要:
伴随着计算机视觉技术的迅猛发展,时间序列预测问题在算法优化中扮演着越来越重要的作用.由于数据不确定性的增加,多步预测遇到了巨大的挑战.针对传统预测模型中累积误差造成的预测精度低和算法复杂度等问题,提出了一种基于长短时记忆神经网络(LSTM)和动态贝叶斯网络(DBN)的时间序列预测模型,研究并证明了一种最优估计理论,并在此基础上得到了最优的预测估计.利用递归图模型,通过概率推理提高了预测性能,建立了一种由长短时记忆预测模型和动态贝叶斯网络组合成的新的图模型,称其为基于长短时记忆神经网络和动态贝叶斯网络的时间序列预测模型(LSTM-DBN),用于预测序列数据.仿真结果表明,该模型能够在提高序列预测精度和速度的同时,降低算法的复杂度.
Abstract:
With the rapid development of computer vision technology,time series prediction is playing an increasingly important role in optimization of algorithms. Due to the increase in data uncertainty,the multi-step prediction has encountered great challenges. The prediction accuracy and complexity of the traditional prediction model are low,so we propose a time series prediction model based on combination of the long-short time memory neural network model and the dynamic Bayesian network (DBN). And we research and prove an optimal estimation theorem,and on the basis we can get the optimal prediction estimation. The recursion-based graph model is used to enhance prediction performance through probability inference. A new graph model called LSTM-DBN generated from a combination of LSTM prediction and DBN is developed to predict series data. The simulation shows that the model can improve the accuracy and speed of the sequence prediction and reduce the complexity of the algorithm.

相似文献/References:

[1]肖强.基于多尺度稀疏LSSVM的时间序列预测[J].计算机技术与发展,2011,(03):117.
　XIAO Qiang.Multi-Scale Least Squares Support Vector Machine for Time Series Forecasting[J].,2011,(09):117.
[2]杨玫 郭天杰 陈青华.基于经验模式分解的时间序列预测方法研究[J].计算机技术与发展,2011,(07):25.
　YANG Mei,GUO Tian-jie,CHEN Qing-hua.Research on Prediction of Time Series Based on EMD[J].,2011,(09):25.
[3]余 洋,万定生.基于 WNN-SVM 的水文时间序列预测方法研究[J].计算机技术与发展,2019,29(09):13.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 003]
　YU Yang,WAN Ding-sheng.Research on Hydrological Time Series Prediction Method Based on WNN-SVM[J].,2019,29(09):13.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 003]
[4]王 晓,揣锦华,张立恒.基于 Prophet 算法的铁路客流量预测研究[J].计算机技术与发展,2020,30(06):130.[doi:10. 3969 / j. issn. 1673-629X. 2020. 06. 025]
　WANG Xiao,CHUAI Jin-hua,ZHANG Li-heng.Research on Railway Passenger Flow Forecast Based on Prophet Time Series Algorithm[J].,2020,30(09):130.[doi:10. 3969 / j. issn. 1673-629X. 2020. 06. 025]
[5]刘铭基,田雅楠,张 亮,等.基于 Prophet-ARIMA 模型的民航周转量[J].计算机技术与发展,2022,32(02):148.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 024]
　LIU Ming-ji,TIAN Ya-nan,ZHANG Liang,et al.Application of Prophet-ARIMA Combined Model in Forecast of Civil Aviation Turnover[J].,2022,32(09):148.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 024]

更新日期/Last Update: 2018-09-10