A Time Series Data Regression Model Based on Multi-kernel KPCA Dimension Reduction and Bagging Algorithms

Sitian Xu; Wenfeng Xu

doi:10.54097/hset.v41i.6806

Authors

Sitian Xu
Wenfeng Xu

DOI:

https://doi.org/10.54097/hset.v41i.6806

Keywords:

KPCA, Bagging algorithms, time series data, high-dimensional regression.

Abstract

Regression models for high-dimensional data have always been a hot topic in the field of statistical learning. Considering the case that the predictor variable is a high-frequency time series and the response variable is a continuous scalar, this paper proposes a regression method based on a multi-kernel KPCA Dimension reduction method and the Bagging algorithms. The proposed method adaptively solves the problem of kernel function selection and unsupervised ness in KPCA Dimension reduction by splicing the projection data under various kernel functions and using the Bagging algorithms to mine the relationship between projection data and the response variable. In the real data analysis, this paper selects the multiple regression model, the LASSO regression based on model selection, the multiple regression model based on PCA Dimension reduction and single-kernel KPCA Dimension reduction as comparison methods. The results show that the proposed method has better performance than other comparison methods. Since the basic regressor in the Bagging framework is model-free, some prediction models can be used to improve the prediction accuracy for more complex data situations.

Downloads

Download data is not yet available.

References

Luo Laihui. A Review of Tensor Regression Model and Its Application Research [J]. Statistics and Application, 2020, 9: 855.

Keith T Z. Multiple regression and beyond: An introduction to multiple regression and structural equation modeling [M]. Routledge, 2019.

Zhang Jie, Zhu Jiaming. Prediction of Total Garbage Based on Multiple Regression and Triple Exponential Smoothing Method [J]. Journal of Qilu University of Technology, 2020, 34(04): 69-74.

Jinhai Li. Application of Multiple Regression Analysis in Forecasting [J]. Journal of Hebei University of Technology, 1996, (3): Volume 15.

Quanzhong Wang. Logistic Regression Model for Two Types of Related Data Analysis [J]. Statistical Research, 2007(2): 81-83.

Gaofeng Yue, Wang Liping, Liu Li, et al. Study on forecasting and forecasting of peony flowering period based on meteorological conditions [J]. Jiangxi Agricultural Journal, 2020, 32(2): 105—109.

Li Ji, Xiaoran Liu, Qiang Wu, Qiang Li. Based on PCA to establish a prediction model for the early flowering of wintersweet [J]. Journal of Southwest Normal University (Natural Science Edition), 2022.10.009.

Li Zhiqin, Du Jianqiang, Nie Bin, et al. A review of feature selection methods [J]. Computer Engineering and Applications, 2019, 55(24).

Xuexue Yang, Qiang Liu. Economic loss prediction of storm surge disaster based on KPCA-RBF model [J]. Marine Science, 2021, 45(10): 32-39.

Fu Hua, Fu Yu, Zhao Juncheng, Xu Tong, Lu Wanjie. Gas Emission Prediction Based on KPCA-ARIMA Algorithm [J]. Journal of Liaoning Technical University (Natural Science Edition), 2022, 41(05): 406 -412.

Gen Li, Guohua Zou, Xinyu Zhang. A review of high-dimensional model selection methods [J]. Mathematical Statistics and Management, 2012.04.004.

H.Wang, X.Zhang and G.Zou (2009) Frequentist Model Averaging Estimation: A Review. Journal of Systems Science and Complexity, 22, 732-748.

H.Liang, Zou., Wan, A.T.K. and Zhang, X. (2011) Optimal Weight Choice for Frequentist Model Average Estimators. Journal of the American Statistical Association, 106, 1053-1066.

BREIMAN L. Bagging predictors [J]. Machine Learning, 1996(24): 123-140.

rong Zhu, Guohua Zou, Xinyu Zhang. Model Averaging Method for Partial Function Linear Models [J]. Systems Science and Mathematics, 2018, 38(07): 777-800.