Computer Science ›› 2023, Vol. 50 ›› Issue (11A): 221100144-8.doi: 10.11896/jsjkx.221100144

• Big Data & Data Science • Previous Articles     Next Articles

Multivariate Time Series Forecasting Method Based on FRA

WANG Hao, ZHOU Jiantao, HAO Xinyu, WANG Feiyu   

  1. College of Computer Science,Inner Mongolia University,Hohhot 010021,China
    National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian,Hohhot 010021,China
    Engineering Research Center of Ecological Big Data,Ministry of Education,Hohhot 010021,China
    Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software,Hohhot 010021,China
    Inner Mongolia Key Laboratory of Social Computing and Data Processing,Hohhot 010021,China
    Inner Mongolia Engineering Laboratory for Big Data Analysis Technology,Hohhot 010021,China
    Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data,Hohhot 010021,China
    Inner Mongolia Big Data Analysis Technology Engineering Laboratory,Hohhot 010021,China
  • Published:2023-11-09
  • About author:WANG Hao,born in 1998,postgra-duate.His main research interests include big data mining and intelligent analysis technology.
    ZHOU Jiantao,born in 1974,Ph.D,professor,Ph.D supervisor,is a member of China Computer Federation.Her main research interests include cloud computing and software engineering.
  • Supported by:
    National Natural Science Foundation of China(62162046),Inner Mongolia Science and Technology Research Project(2021GG0155),Major Programs of Inner Mongolia Natural Science Foundation(2019ZD15),Inner Mongolia Natural Science Foundation(2019GG372) and Inner Mongolia University/Inner Mongolia Autonomous Region Graduate Scientific Research Innovation Project(11200-121024).

Abstract: Derivative industries in the field of science and technology have accumulated a large amount of high-dimensional time series data due to the general existence of strong time constraints.Severe data pressure makes traditional data modeling and prediction methods limited by data scale and attribute dimensions.Services supporting high-quality put forward higher requirements for big data intelligent prediction technology.How to improve the prediction performance at the data level is a main problem that needs to be solved urgently at this stage.Combined with the above problems,a feature re-abstraction(FRA) algorithm for multivariate time series data is proposed.First,the RobustSTL decomposition algorithm is used to extract trend and seasonality features(TSFs),realize the second-order abstraction of features of multivariate data,and replace the traditional extraction strategy of “labels are features” with “abstract is features”.Then,the correlation strength between the TSFs captured by the re-abstract technology and the target parameters is evaluated by the calculation result of the Pearson correlation coefficient,which confirms the data value of the TSF.On the basis of FRA algorithm,combined with deep learning model,a data-driven multivariate time series prediction algorithm is constructed,and the effectiveness of FRA algorithm is verified by the prediction effect.Experimental results show that the introduction of TSFs as the training vector of the data-driven model can maintain the characteristics of data dimensionality reduction,noise reduction and strong correlation,so as to avoid model overfitting and alleviate model underfitting,and improve the accuracy and robustness of time series prediction algorithms.

Key words: Multivariate time series data, Multivariate time series forecasting algorithms, Feature re-abstraction(FRA), Trend and seasonality feature(TSF), Correlation assessment

CLC Number: 

  • TP311.1
[1]REN S G,ZHANG J X,GU X J,et al.Overview of Feature Extraction Algorithms for Time Series[J].Journal of Chinese Computer Systems,2021,42(2):271-278.
[2]ZHAO D F,HUANG Y L,HUANG D M,et al.Research ontime series motif association rule mining method based on AR_TSM[J].Application Research of Computers,2021,38(2):403-408.
[3]YANG H,WANG H Q,CHENG D J.Series Outlier Data Mi-ning Based on Forecastment[J].Computer Science,2004(4):117-119,146.
[4]YE L,KEOGH E.Time series shapelets:a novel technique that allows accurate,interpretable and fast classification[J].Data Mining and Knowledge Discovery,2011,22:149-182.
[5]WAN C,LI W Z,DING W X,et al.A Multivariate Time Series Forecasting Algorithm Based on Self-Evolution and Pre-training[J].Chinese Journal of Computers,2022,45(3):513-525.
[6]JIA J,HU X S,DENG Z W,et al.Data-driven Comprehensive Evaluation of Lithium-ion Battery State of Health and Abnormal Battery Screening[J].Journal of Mechanical Engineering,2021(3):87-97,57.
[7]SHI X,CHEN Z,WANG H,et al.Convolutional LSTM Net-work:A Machine Learning Approach for Precipitation Nowcas-ting[J].arXiv:1506.04214,2015.
[8]VASWANI A.Attention is All You Need[J].arXiv:1706.03762,2017.
[9]ELHASSAN T A M,RAHIM M S M,SWEE T T,et al.eature Extraction of White Blood Cells Using CMYK-Moment Localization and Deep Learning in Acute Myeloid Leukemia Blood Smear Microscopic Images[C]//IEEE Access.2022:16577-16591.
[10]LIU L,ZHU J C,HAN G J,et al.Bearing health monitoring and fault diagnosis based on joint feature extraction in one-dimensional convolution neural network[J].Ruan Jian Xue Bao/Journal of Software,2021,32(8):2379-2390.
[11]MA C C,DU X H,CAO L F,et al.Burst-Analysis Website Fingerprinting Attack Based on Deep Neural Network[J].Journal of Computer Research and Development,2020,57(4):746-766.
[12]ZOU X Y.TIme series prediction algorithm based on graph laplace transform and extreme learning machine[J].Computer Applications and Software,2021,38(4):288-294.
[13]GUO Y H,LU J Y,HUANG C H,et al.Mesh Texture Smoothing Based on Hybrid Spectral Encoding[J].Chinese Journal of Computers,2021,44(2):318-333.
[14]JIA Z Y,LIN Y F,LIU T H,et al.Motor Imagery Classification Based on Multiscale Feature Extraction and Squeeze-Excitation Model[J].Journal of Computer Research and Development,2020,57(12):2481-2489.
[15]LIU Y Y,LI J P,BAI H F,et al.Trend feature extraction me-thod for time series based on turning point and trend segment[J].Journal of Computer Applications,2020,40( S1):92-97.
[16]ZHOU Q,WU T J.Trend feature extraction method based onimportant points in time series[J].Journal of Zhejiang University(Engineering Science),2007(11):1782-1787.
[17]WIJSEN J.Trends in databases:reasoning and mining[J].IEEE Transactions on Knowledge and Data Engineering,2001,13(3):426-438.
[18]WEN Q,GAO J,SONG X,et al.RobustSTL:A Robust Seasonal-Trend Decomposition Algorithm for Long Time Series[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019:5409-5416.
[19]CLEVELAND R B,CLEVELAND W S.STL:A seasonal-trend decomposition procedure based on Loess[J].Journal of official statistics,1990,6(1):3-73.
[1] WEI Sen, ZHOU Haoran, HU Chuang, CHENG Dazhao. Implementation and Optimization of Apache Spark Cache System Based on Mixed Memory [J]. Computer Science, 2023, 50(6): 10-21.
[2] ZAHO Peng, ZHOU Jiantao, ZHAO Daming. Cloud Computing Load Prediction Method Based on Hybrid Model of CEEMDAN-ConvLSTM [J]. Computer Science, 2023, 50(6A): 220300272-9.
[3] YANG Jie, KUANG Juncheng, WANG Guoyin, LIU Qun. Cost-sensitive Multigranulation Approximation of Neighborhood Rough Fuzzy Sets [J]. Computer Science, 2023, 50(5): 137-145.
[4] ZHANG Renbin, ZUO Yicong, ZHOU Zelin, WANG Long, CUI Yuhang. Multimodal Generative Adversarial Networks Based Multivariate Time Series Anomaly Detection [J]. Computer Science, 2023, 50(5): 355-362.
[5] HAN Jingyu, QIAN Long, GE Kang, MAO Yi. ECG Abnormality Detection Based on Label Co-occurrence and Feature Local Pertinence [J]. Computer Science, 2023, 50(3): 139-146.
[6] ZHANG Kang-wei, ZHANG Jing-wei, YANG Qing, HU Xiao-li, SHAN Mei-jing. DCPFS:Distributed Companion Patterns Mining Framework for Streaming Trajectories [J]. Computer Science, 2022, 49(11A): 211100268-10.
[7] PAN Zhi-yong, CHENG Bao-lei, FAN Jian-xi, BIAN Qing-rong. Algorithm to Construct Node-independent Spanning Trees in Data Center Network BCDC [J]. Computer Science, 2022, 49(7): 287-296.
[8] FU Li-yu, LU Ge-hao, WU Yi-ming, LUO Ya-ling. Overview of Research and Development of Blockchain Technology [J]. Computer Science, 2022, 49(6A): 447-461.
[9] YANG Fei-fei, SHEN Si-yu, SHEN De-rong, NIE Tie-zheng, KOU Yue. Method on Multi-granularity Data Provenance for Data Fusion [J]. Computer Science, 2022, 49(5): 120-128.
[10] WEN Min-hua, WANG Shen-peng, WEI Jian-wen, LI Lin-ying, ZHANG Bin, LIN Xin-hua. DGX-2 Based Optimization of Application for Turbulent Combustion [J]. Computer Science, 2021, 48(12): 43-48.
[11] CHEN Xian-lai, ZHAO Xiao-yu, ZENG Gong-mian, AN Ying. Online Patient Communication Model Based on Blockchain [J]. Computer Science, 2021, 48(11): 28-35.
[12] XIANG A-xin, GAO Hong-feng, TIAN You-liang. Key Update Mechanism in Bitcoin Based on Improved P2PKHCA Script Scheme [J]. Computer Science, 2021, 48(11): 159-169.
[13] MAO Xiang-ke, HUANG Shao-bin, YU Qin-yong. Graph Based Collaborative Extraction Method for Keywords and Summary from Documents [J]. Computer Science, 2021, 48(10): 44-50.
[14] LU Jia-wen, YAN Li. Mapping Method from Object-relational Database to RDF(S) [J]. Computer Science, 2021, 48(10): 145-151.
[15] ZHU Han-qing, MA Wu-bin, ZHOU Hao-hao, WU Ya-hui, HUANG Hong-bin. Microservices User Requests Allocation Strategy Based on Improved Multi-objective Evolutionary Algorithms [J]. Computer Science, 2021, 48(10): 343-350.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!