A Linear Discriminant Analysis model based on Sliced Inverse Regression lifting
DOI:
https://doi.org/10.54097/07bdff79Keywords:
Data Dimensionality Reduction, Linear Discriminant Analysis, Sliced Inverse Regression.Abstract
Linear Discriminant Analysis is a dimension-reduction tool for high-dimensional data in the classical field of machine learning. However, for the binary classification problem in the case of high-dimensional prediction, the dimension of the dimension reduction space of the Linear Discriminant Analysis model cannot be greater than the number of categories, that is, it can only be reduced to one dimension, which will greatly lose the effective information of the original prediction variable for the response variable. Based on this, this paper proposes an improved Linear Discriminant Analysis model based on sufficient dimensionality reduction auxiliary slice. On the one hand, by using the Sliced Inverse Regression method, the proposed method can construct auxiliary slice response variables without losing any effective information about the response variables; On the other hand, this method can increase the number of reduced dimensions of the reduced dimension space to any dimension not greater than the number of slices. The analysis results of simulated data and real data show that the proposed method is more accurate and robust than the classical Linear Discriminant Analysis model.
Downloads
References
Xie Z. Research and application of data dimensionality reduction algorithm based on SIR [D] Jiangsu: Nanjing University of Posts and Telecommunications, 2018.
Hu D., Nie F., Li X. Hash technology based on deep Linear Discriminant Analysis [J]. Chinese Science: Information Science, 2021, 51(02): 279-293.
Kong D., Dong R., Cui Y., et al. Research on oil identification method based on three-dimensional fluorescence spectroscopy combined with two-dimensional Linear Discriminant Analysis [J]. Spectroscopy and Spectral Analysis, 2021, 41(08): 2505-2510.
Zhu M., Yang H., Li Z. Early detection and recognition of rice sheath blight based on hyperspectral image and chlorophyll content [J]. Spectroscopy and Spectral Analysis, 2019, 39(06): 1898-1904.
Ricciardi C., Valente A.S., Edmund K., et al. Linear Discriminant Analysis and principal component analysis to predict coronary artery disease. Health Informatics Journal. 2020;26(3):2181-2192.
Huo D., Zhang M., Hou C., et al. Liquor brand identification method based on principal component analysis and discriminant analysis [J]. Transactions of the Chinese Society of Agricultural Engineering, 2011, 27(S2): 297-301.
Wen, Jie, et al. "Robust sparse Linear Discriminant Analysis." IEEE Transactions on Circuits and Systems for Video Technology 29.2 (2018): 390-403. Feiping Nie, Zheng Wang, Rong Wang, Zhen Wang, and Xue long Li. 2020. Adaptive Local Linear Discriminant Analysis. ACM Trans. Knowl. Discov. Data 14, 1, Article 9 (February 2020).
Nie F., Wang Z., Wang R., et al. Adaptive local Linear Discriminant Analysis[J]. ACM Transactions on Knowledge Discovery from Data (TKDD), 2020, 14(1): 1-19.
T. Tony Cai, Lin jun Zhang, High Dimensional Linear Discriminant Analysis: Optimality, Adaptive Algorithm and Missing Data, Journal of the Royal Statistical Society Series B: Statistical Methodology, Volume 81, Issue 4, September 2019, Pages 675–705.
Wang Y. Application Research of face image recognition based on PCA, LDA and SVM [D]. Lanzhou Jiaotong University, 2024.
Olszewski R.T. Generalized Feature Extraction for Structural Pattern Recognition in Time-Series Data[J]. Time Series Data Ph.D. Dissertation Carnagie Mellon University, 2001.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Highlights in Science, Engineering and Technology

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.







