[1]戴邵武,陈强强,刘志豪,等.基于EMD-LSTM的时间序列预测方法[J].深圳大学学报理工版,2020,37(3):265-270.[doi:10.3724/SP.J.1249.2020.03265]
 DAI Shaowu,CHEN Qiangqiang,LIU Zhihao,et al.Time series prediction based on EMD-LSTM model[J].Journal of Shenzhen University Science and Engineering,2020,37(3):265-270.[doi:10.3724/SP.J.1249.2020.03265]
点击复制

基于EMD-LSTM的时间序列预测方法()
分享到:

《深圳大学学报理工版》[ISSN:1000-2618/CN:44-1401/N]

卷:
第37卷
期数:
2020年第3期
页码:
265-270
栏目:
数学与应用数学
出版日期:
2020-05-20

文章信息/Info

Title:
Time series prediction based on EMD-LSTM model
文章编号:
202003008
作者:
戴邵武1陈强强12刘志豪3戴洪德4
1)海军航空大学岸防兵学院,山东烟台 264000
2) 海军92728部队,上海 200040
3)海军92214部队,浙江宁波 315000
4)海军航空大学航空基础学院,山东烟台 264000
Author(s):
DAI Shaowu1 CHEN Qiangqiang1 2 LIU Zhihao3 and DAI Hongde4
1) College of Coastal Defense, Naval Aviation University, Yantai 264000, Shandong Province, P.R.China
2) Naval 92728, Shanghai 200040, P.R.China
3) Naval 92214, Ningbo 315000, Zhejiang Province, P.R.China
4) College of Basic Sciences for Aviation, Naval Aviation University, Yantai 264000, Shandong Province, P.R.China
关键词:
数理统计学 时间序列预测 经验模态分解 长短期记忆网络 PM2.5 机器学习 时间序列分解
Keywords:
mathematical statistics time series prediction empirical mode decomposition long-short term memory network PM2.5 machine learning time series decompose
分类号:
C81
DOI:
10.3724/SP.J.1249.2020.03265
文献标志码:
A
摘要:
工程应用中的时间序列多为非线性、非平稳序列,直接对其进行预测难度较大.本研究通过经验模态分解算法将原始时间序列分解为多个相对平稳,并具有不同特征尺度的本征模态函数及趋势项,在一定程度上降低时间序列的复杂程度;同时,在预测过程中,针对递归神经网络模型难以训练及梯度消失等问题,引入长短期记忆网络算法.利用长短期记忆网络算法对分解的本征模态函数分量及趋势项进行分别预测,叠加预测结果得到最终预测结果.以中国北京市PM2.5浓度为例进行预测分析,并将本预测算法与单一预测算法进行比较,结果表明,所提方法具有更高的模型预测精度,达到预测要求.
Abstract:
The time series in engineering applications are mostly non-stationary and non-linear, which are difficult to be directly predicted. Based on the empirical model decomposition (EMD) method, we decompose the original time series into a number of intrinsic mode functions (IMFs) and trend series with the different feature scales in order to reduce the complexity of time series. Meanwhile, in the prediction process, in order to solve the problems of training difficulty and the gradient disappearance in recurrent neural network (RNN) model, we introduce a long-short term memory (LSTM) network algorithm to predict both the results of the decomposed IMF components and trend series respectively, and obtain the final prediction result by surposing the respective prediction results. Taking the PM2.5 concentration in Beijing as an example for prediction and analysis, we compare our prediction algorithm with the single prediction algorithm. The results show that the proposed prediction model has higher accuracy and can meet the prediction requirements.

参考文献/References:

[1] 陈艳华. 基于机器学习的时间序列预测方法研究与应用[D]. 兰州:兰州大学, 2017.
CHEN Yanhua. The research and applications of time series forecasting methods based on machine learning[D]. Lanzhou: Lanzhou University, 2017.(in Chinese)
[2] 李祥, 彭玲, 邵静, 等. 基于小波分解和ARMA模型的空气污染预报研究[J]. 环境工程, 2016, 34(8):110-113.
LI Xiang, PENG Ling, SHAO Jing, et al. Air pollution forecast based on wavelet decomposition and ARMA model[J]. Environmental Engineering, 2016, 34(8):110-113.(in Chinese)
[3] 牟敬锋, 赵星, 樊静洁, 等. 基于ARIMA模型的深圳市空气质量指数时间序列预测研究[J]. 环境卫生学杂志, 2017, 7(2):102-107.
MOU Jingfeng, ZHAO Xing, FAN Jingjie, et al. Time series prediction of AQI in Shenzhen based on ARIMA model[J]. Journal of Environmental Hygiene, 2017, 7(2):102-107.(in Chinese)
[4] 王威, 陈熙源. 一种基于多尺度和改进支持向量机的光纤陀螺温度漂移建模与补偿方法[J]. 中国惯性技术学报, 2016,24(6): 793-797.
WANG Wei, CHEN Xiyuan. Modeling and compensation method of FOG temperature drift based on multi-scale and improved support vector machine[J]. Journal of Chinese Inertial Technology, 2016, 24(6): 793-797.(in Chinese)
[5] LI Guohui, MA Xiao, YANG Hong. A hybrid model for monthly precipitation time series forecasting based on variational mode decomposition with extreme learning machine[J]. Information, 2018, 9(7): 1-13.
[6] 丁亮, 武林, 刘清民. 基于边缘保持中值滤波和BP神经网络的自然手势识别研究[J]. 现代计算机, 2017(25): 10-13.
DING Liang, WU Lin, LIU Qingmin. Research on natural gesture recognition based on edge preserving median filter and BP neural network[J]. Modern Computer, 2017(25): 10-13.(in Chinese)
[7] LUKOEVIIUS M, JAEGER H. Reservoir computing approaches to recurrent neural network training[J]. Computer Science Review, 2009, 3(3):127-149.
[8] 毛景慧. 基于LSTM深度神经网络的股市时间序列预测精度的影响因素研究[D]. 广州:暨南大学, 2017.
MAO Jinghui. Research on influencing factors of stock market time series prediction accuracy based on LSTM deep neural network[D]. Guangzhou: Jinan University, 2017.(in Chinese)
[9] LEV G, SADEH G, KLEIN B, et al. RNN fisher vectors for action recognition and image annotation[J]. Computer Science, 2016: 833-850.
[10] FU Rui, ZHANG Zuo, LI Li. Using LSTM and GRU neural network methods for traffic flow prediction[C]// The 31st Youth Academic Annual Conference of Chinese Association of Automation. Wuhan, China: IEEE, 2017: 324-328.
[11] ZHANG Boning. Foreign exchange rates forecasting with an EMD-LSTM neural networks model[J]. Journal of Physics Conference, 2018, 1053(1): 5-12.
[12] 杨训政, 柯余洋, 梁肖, 等. 基于LSTM的发电机组污染物排放预测研究[J]. 电气自动化, 2016, 38(5): 22-25.
YANG Xunzheng, KE Yuyang, LIANG Xiao, et al. A study on the prediction of generator set pollutant emissions based on LSTM[J]. Electrical Automation, 2016, 38(5): 22-25.(in Chinese)
[13] HUANG M L, LONG S E, SHIH H H, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings: Mathematical, Physical and Engineering Sciences, 1998, 454(1971): 903-993.
[14] HUANG Yiming, WU Di, ZHANG Zhifen, et al. EMD-based pulsed TIG welding process porosity defect detection and defect diagnosis using GA-SVM[J]. Journal of Materials Processing Technology, 2017, 239: 92-102.
[15] 秦喜文, 刘媛媛, 王新民, 等. 基于整体经验模态分解和支持向量回归的北京市 PM2.5预测[J]. 吉林大学学报地球科学版, 2016, 46(2): 563-568.
QIN Xiwen, LIU Yuanyuan, WANG Xinmin, et al. PM2.5 prediction of Beijing city based on ensemble empirical mode decomposition and support vector regression[J]. Journal of Jilin University Earth Science Edition, 2016, 46(2): 563-568.(in Chinese)
[16] 刘媛媛. 基于整体经验模态分解和随机森林的城市PM2.5预测[D]. 长春:长春工业大学, 2017.
LIU Yuanyuan. A hybrid model for PM2.5 forecasting of cities based on ensemble empirical mode decomposition and a random forest[D]. Changchun: Changchun University of Technology, 2017.(in Chinese)
[17] WILLMOTT C J, MATSUURA K. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance[J]. Climate Research, 2005, 30(1): 79-82.
[18] 冯辅周, 饶国强, 司爱威, 等. 排列熵算法的应用与发展[J]. 装甲兵工程学院学报, 2012, 26(2): 34-38.
FENG Fuzhou, RAO Guoqiang, SI Aiwei, et al. Application and development of permutation entropy algorithm[J]. Journal of Academy of Armored Force Engineering, 2012, 26(2): 34-38.(in Chinese)

备注/Memo

备注/Memo:
Received:2019-03-13;Revised:2019-10-09;Accepted:2019-10-22
Foundation:Natural Science Foundation of Shandong Province (ZR2017MF036); National Defense Science and Technology Foundation of China(F062102009)
Corresponding author:Engineer CHEN Qiangqiang. E-mail: 1195275597@qq.com
Citation:DAI Shaowu, CHEN Qiangqiang, LIU Zhihao, et al. Time series prediction based on EMD-LSTM model[J]. Journal of Shenzhen University Science and Engineering, 2020, 37(3): 265-270.(in Chinese)
基金项目:山东省自然科学基金资助项目(ZR2017MF036); 国防科技基金资助项目(F062102009)
作者简介:戴邵武(1966—),海军航空大学教授.研究方向:飞行器综合导航、时间序列分析.E-mail:13386386392@163.com
引文:戴邵武,陈强强,刘志豪,等.基于EMD-LSTM的时间序列预测方法[J]. 深圳大学学报理工版,2020,37(3):265-270.
更新日期/Last Update: 2020-05-30