计算机科学 ›› 2021, Vol. 48 ›› Issue (11A): 204-210.doi: 10.11896/jsjkx.210500129

• 大数据&数据科学 • 上一篇    下一篇

用于多元时间序列预测的自适应频域模型

王晓迪1,3, 刘鑫2,3, 于晓2,3   

  1. 1 山东财经大学财政税务学院 济南250014
    2 山东财经大学计算机科学与技术学院 济南250014
    3 山东省数字媒体技术重点实验室 济南250014
  • 出版日期:2021-11-10 发布日期:2021-11-12
  • 通讯作者: 王晓迪(20049447@sdufe.edu.cn)
  • 基金资助:
    国家自然科学基金(62072274)

Adaptive Frequency Domain Model for Multivariate Time Series Forecasting

WANG Xiao-di1,3, LIU Xin2,3, YU Xiao2,3   

  1. 1 School of Public Finance and Taxation,Shandong University of Finance and Economics,Jinan 250014,China
    2 School of Computer Science and Technology,Shandong University of Finance and Economics,Jinan 250014,China
    3 Shandong Key Laboratory of Digital Media Technology,Jinan 250014,China
  • Online:2021-11-10 Published:2021-11-12
  • About author:WANG Xiao-di,born in 1981,master.His main research interests include artificial intelligence,data mining and so on.
  • Supported by:
    National Natural Science Foundation of China(62072274).

摘要: 近年来,学术和工业领域对时间序列数据的研究热潮不断增长,但其中蕴含的频率信息仍缺乏有效的建模。研究发现,时间序列预测依赖于不同的频率模式,为未来的趋势预测提供有用的线索:短期的序列预测更多依赖于高频分量,而长期预测则更多关注低频数据。为更好地挖掘时间序列的多频模式,提出了一个多特征自适应频域预测模型MAFD。该模型分为两个阶段:在第一阶段中,模型通过XGBoost算法对输入向量进行重要性度量,选择高重要性特征;在第二阶段,模型将时间序列的频率特征提取和目标序列的频域建模集成到一起,并根据时间序列对频率模式的依赖特点构建一个端到端的预测网络。MAFD的创新性体现在预测网络能够根据输入序列的动态演变自动关注不同的频率分量,从而揭示时间序列的多频模式,强化模型的学习能力。采用4种不同领域的数据集对模型进行了性能验证,实验结果表明,与现有经典的预测模型相比,MAFD具有更高的准确性和更小的滞后性。

关键词: XGBoost, 多频模式, 深度学习, 时间序列预测, 自适应建模

Abstract: In recent years,the research enthusiasm for time series data in academic and industrial fields has been increasing,but the frequency information contained in it still lacks effective modeling.The studies found that time series forecasting relies on different frequency patterns,providing useful clues for future trend forecasting:short-term series forecasting relies more on high-frequency components,while long-term forecasting focuses more on low-frequency data.In order to better mine the multi-frequency mode of time series,this paper proposes a multi-feature adaptive frequency domain prediction model (MAFD).MAFD is composed of two stages.In the first stage,it uses XGBoost algorithm to measure the importance of the input vector and selects high-importance features.In the second stage,the model integrates the frequency feature extraction of the time series and the frequency domain modeling of the target sequence,and builds an end-to-end prediction network based on the dependence of the time series on the frequency mode.The innovation of MAFD is reflected in the predictive network's ability to automatically focus on diffe-rent frequency components according to the dynamic evolution of the input sequence,thereby revealing the multi-frequency pattern of the time series and strengthening the learning ability of the model.This work uses 4 datasets from different fields to verify the performance of the model.The experimental results show that compared with the existing classic prediction models,MAFD has higher accuracy and smaller lag.

Key words: Adaptive modeling, Deep learning, Multi-frequency pattern, Time series prediction, XGBoost

中图分类号: 

  • TP391
[1]KAYACAN E,ULUTAS B,KAYNAK O.Grey system theory-based models in time series prediction[J].Expert Systems with Applications,2010,37(2):1784-1789.
[2]KROGH A,LARSSON B,VON H G,et al.Predicting transmembrane protein topology with a hidden Markov model:application to complete genomes[J].Journal of Molecular Biology,2001,305(3):567-580.
[3]SINGH S N,MOHAPATRA A.Repeated wavelet transformbased ARIMA model for very short-term wind speed forecasting[J].Renewable Energy,2019,136:758-768.
[4]WEINSTEIN S,EBERT P.Data transmission by frequency-division multiplexing using the discrete Fourier transform[J].IEEE Transactions on Communication Technology,1971,19(5):628-634.
[5]DAMERVAL C,MEIGNEN S,PERRIER V.A fast algorithm for bidimensional EMD[J].IEEE Signal Processing Letters,2005,12(10):701-704.
[6]XUAN Z Y,YANG G X.Application of EMD in the Atmos-phere Time Series Prediction[J].Acta Automatica Sinica,2008,34(1):97-101.
[7]AMOR L B,LAHYANI I,JMAIEL M.Recursive and Rolling Windows for Medical Time Series Forecasting:A Comparative Study[C]// Recursive and Rolling Windows for Medical Time Series Forecasting:A Comparative Study.IEEE Computer So-ciety,2016.
[8]ZHONG X,DAVID E.Forecasting daily stock market returnusing dimensionality reduction[J].Expert Systems with Applications,2017,67:126-139.
[9]QING X Y,YU G N.Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM[J].Energy,2018,148:461-468.
[10]WANG D C,LU Y Y,ZOU Y J.Multi-output IntuitionisticFuzzy Least Squares Support Vector Regression Algorithm[J].Computer Science,2019,46(5):163-168.
[11]TANG J,LIU F,ZHANG W,et al.Lane-changes predictionbased on adaptive fuzzy neural network[J].Expert Systems with Applications,2018,91:452-463.
[12]HU Y,FENG B,ZHANG X,et al.Stock trading rule discovery with an evolutionary trend following model[J].Expert Systems with Applications,2015,42(1):212-222.
[13]ROUNAGHI M M,ZADEH F N.Investigation of market efficiency and financial stability between S&P 500 and London Stock Exchange:Monthly and yearly Forecasting of Time Series Stock Returns using ARMA model[J].Physica A:Statistical Mechanics and its Applications,2016,456:10-21.
[14]JIDONG W,PENG L,RAN R,et al.A Short-Term Photovoltaic Power Prediction Model Based on the Gradient Boost Decision Tree[J].Applied Sciences,2018,8(5):689.
[15]LV M Q,HONG Z X,CHEN T M.Traffic Flow ForecastingMethod Combining Spatio-Temporal Correlations and Social Events[J].Computer Science,2021,48(2):264-270.
[16]CONNOR J T,MARTIN R D,Atlas L E.Recurrent neural networks and robust time series prediction[J].IEEE Transactions on Neural Networks,1994,5(2):240-254.
[17]HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
[18]PETERSEN N C,RODRIGUES F,PEREIRA F C.Multi-output bus travel time prediction with convolutional LSTM neural network[J].Expert Systems with Applications,2019,120:426-435.
[19]HU H,GUO J Q.State-Frequency Memory Recurrent NeuralNetworks[C]//International Conference on Machine Learning.New York:ACM,2017:1568-1577.
[20]MOUATADID S,ADAMOWSKI J F,TIWARI M K,et al.Coupling the maximum overlap discrete wavelet transform and long short-term memory networks for irrigation flow forecasting[J].Agricultural Water Management,2019,219:72-85.
[21]ZHANG L H,AGGARWAL C,QI G J.Stock price prediction via discovering multi-frequency trading patterns[C]//Procee-dings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York:ACM,2017:2141-2149.
[22]OUYANG L,ZHU F,XIONG G,et al.Short-term traffic flow forecasting based on wavelet transform and neural network[C]//2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC).NJ:IEEE,2017:1-6.
[23]CHEN T Q,GUESTRIN C.Xgboost:A scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York:ACM,2016:785-794.
[24]ZHENG H,YUAN J,CHEN L.Short-term load forecasting using EMD-LSTM neural networks with a XGBoost algorithm for feature importance evaluation[J].Energies,2017,10(8):1168.
[25]HSIEH C P,CHEN Y T,BEH W K,et al.Feature SelectionFramework for XGBoost based on Electrodermal Activity in Stress Detection[C]//2019 IEEE International Workshop on Signal Processing Systems (SiPS).NJ:IEEE,2019:330-335.
[26]KE J,ZHENG H,YANG H,et al.Short-term forecasting of passenger demand under on-demand ride services:A spatio-temporal deep learning approach[J].Transportation Research,2017,85c(dec):591-608.
[27]LAI G,CHANG W C,YANG Y,et al.Modeling Long- andShort-Term Temporal Patterns with Deep Neural Networks [C]//The 41st International ACM SIGIR Conference.New York:ACM,2018.
[28]CHU B,LI Z S,ZHANG M L,et al.Improvement Research on Feature Selection Algorithm Based on Forest Optimization[J].Journal of Software,2018,29(9):2547-2558.
[29]DASH M,LIU H.Feature selection for classification[J].Intelligent Data Analysis,1997,1(3):131-156.
[30]MA X,SHA J,WANG D,et al.Study on a prediction of P2P network loan default based on the machine learning LightGBM and XGboost algorithms according to different high dimensional data cleaning[J].Electronic Commerce Research and Applications,2018,31:24-39.
[31]TORLAY L,PERRONE B M,THOMAS E.Machine learning-XGBoost analysis of language networks to classify patients with epilepsy[J].Brain Informatics,2017,4(3):159-169.
[32]DAUBECHIES I.The wavelet transform,time frequency localization and signal analysis[J].IEEE Transactions on Information Theory,1990,36(5):961-1005.
[33] HUANG G B.Learning capability and storage capacity of two-hidden-layer feed forward networks[J].IEEE Transactions on Neural Networks,2003,14(2):274-281.
[34]LI Y F,XIE M G,THONG N.A study of project selection and feature weighting for analogy based software cost estimation[J].Journal of Systems and Software,2009,82(2):241-252.
[35]FAMA E F.Random walks in stock market prices[J].Financial Analysts Journal,1995,51(1):75-80.
[36]AL-SHUBIRI F N.Analysis the determinants of market stockprice movements:An empirical study of Jordanian commercial banks[J].International Journal of Business and Management,2010,5(10):137.
[1] 徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺.
时序知识图谱表示学习
Temporal Knowledge Graph Representation Learning
计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204
[2] 饶志双, 贾真, 张凡, 李天瑞.
基于Key-Value关联记忆网络的知识图谱问答方法
Key-Value Relational Memory Networks for Question Answering over Knowledge Graph
计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[3] 汤凌韬, 王迪, 张鲁飞, 刘盛云.
基于安全多方计算和差分隐私的联邦学习方案
Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy
计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108
[4] 王剑, 彭雨琦, 赵宇斐, 杨健.
基于深度学习的社交网络舆情信息抽取方法综述
Survey of Social Network Public Opinion Information Extraction Based on Deep Learning
计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099
[5] 郝志荣, 陈龙, 黄嘉成.
面向文本分类的类别区分式通用对抗攻击方法
Class Discriminative Universal Adversarial Attack for Text Classification
计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077
[6] 姜梦函, 李邵梅, 郑洪浩, 张建朋.
基于改进位置编码的谣言检测模型
Rumor Detection Model Based on Improved Position Embedding
计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046
[7] 孙奇, 吉根林, 张杰.
基于非局部注意力生成对抗网络的视频异常事件检测方法
Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection
计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[8] 胡艳羽, 赵龙, 董祥军.
一种用于癌症分类的两阶段深度特征选择提取算法
Two-stage Deep Feature Selection Extraction Algorithm for Cancer Classification
计算机科学, 2022, 49(7): 73-78. https://doi.org/10.11896/jsjkx.210500092
[9] 程成, 降爱莲.
基于多路径特征提取的实时语义分割方法
Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction
计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157
[10] 侯钰涛, 阿布都克力木·阿布力孜, 哈里旦木·阿布都克里木.
中文预训练模型研究进展
Advances in Chinese Pre-training Models
计算机科学, 2022, 49(7): 148-163. https://doi.org/10.11896/jsjkx.211200018
[11] 周慧, 施皓晨, 屠要峰, 黄圣君.
基于主动采样的深度鲁棒神经网络学习
Robust Deep Neural Network Learning Based on Active Sampling
计算机科学, 2022, 49(7): 164-169. https://doi.org/10.11896/jsjkx.210600044
[12] 苏丹宁, 曹桂涛, 王燕楠, 王宏, 任赫.
小样本雷达辐射源识别的深度学习方法综述
Survey of Deep Learning for Radar Emitter Identification Based on Small Sample
计算机科学, 2022, 49(7): 226-235. https://doi.org/10.11896/jsjkx.210600138
[13] 祝文韬, 兰先超, 罗唤霖, 岳彬, 汪洋.
改进Faster R-CNN的光学遥感飞机目标检测
Remote Sensing Aircraft Target Detection Based on Improved Faster R-CNN
计算机科学, 2022, 49(6A): 378-383. https://doi.org/10.11896/jsjkx.210300121
[14] 王建明, 陈响育, 杨自忠, 史晨阳, 张宇航, 钱正坤.
不同数据增强方法对模型识别精度的影响
Influence of Different Data Augmentation Methods on Model Recognition Accuracy
计算机科学, 2022, 49(6A): 418-423. https://doi.org/10.11896/jsjkx.210700210
[15] 毛典辉, 黄晖煜, 赵爽.
符合监管合规性的自动合成新闻检测方法研究
Study on Automatic Synthetic News Detection Method Complying with Regulatory Compliance
计算机科学, 2022, 49(6A): 523-530. https://doi.org/10.11896/jsjkx.210300083
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!