Author(s)

JiaYuan Zhang

Affiliation(s)

SWUFE-UD Institute of Data Science at SWUFE, Southwestern University of Finance and Economics, Chengdu 611130, Sichuan, China.

Corresponding Author

JiaYuan Zhang

ABSTRACT

In the digital era, the explosive growth of high-dimensional data poses significant challenges to storage, transmission, and computational efficiency. Mine data, characterized by its multi-source heterogeneity, high dynamism, and high dimensionality, presents particularly acute challenges. This paper proposes a novel method for dimensionality reduction and fitting of high-dimensional data by combining Singular Value Decomposition (SVD) with least squares, and demonstrates its first application in mine data processing. The method achieves efficient data compression and precise fitting by extracting principal singular values and vectors via SVD, projecting high-dimensional data into a low-dimensional space, and solving for optimal weight vectors using least squares. A pseudo-inverse is constructed to avoid numerical instability, ultimately completing the fitting of the target dataset. Experimental results show that the method performs exceptionally well in terms of residual distribution, model bias, data noise, and fitting adequacy: residuals approximate a normal distribution, confirming that errors primarily stem from data noise. This study provides a reliable technical pathway for processing high-dimensional mine data, with future optimizations possible through the introduction of noise reduction modules.

KEYWORDS

SVD method; Least squares fitting; Data dimensionality reduction; Mine data processing; Error analysis

CITE THIS PAPER

JiaYuan Zhang. Dimensionality reduction and fitting method for high-dimensional data based on SVD and least squares—a case study of mine data processing. World Journal of Information Technology. 2025, 3(4): 46-50. DOI: https://doi.org/10.61784/wjit3052.

REFERENCES

[1] Vats D, Sharma A. Dimensionality Reduction Techniques: Comparative Analysis. Journal of Computational and Theoretical Nanoscience, 2020, 17(6): 2684-2688.

[2] Hastie T, Mazumder R, Lee J D, et al. Matrix Completion and Low-Rank SVD via Fast Alternating Least Squares. Journal of machine learning research, 2015, 16: 3367-3402.

[3] M E Hochstenbach. Harmonic and Refined Extraction Methods for the Singular Value Problem, with Applications in Least Squares Problems. BIT numerical mathematics, 2004, 44(4): 721-754.

[4] Alkiviadis G A, Gennadi I M. Applications of singular-value decomposition (SVD). Mathematics and Computers in Simulation, 2004, 67(1): 15-31.

[5] Zhang Chongchong, Shi Yannan, Liu Jiangong, et al. A denoising method of mine microseismic signal based on NAEEMD and frequency-constrained SVD. The Journal of Supercomputing, 2022, 78(15): 17095-17113.

[6] Li Shanshan, Tian Wenquan, Pan Zhenggao. Multi-label Learning Algorithm Based on SVD and Kernel Extreme Learning Machine. Journal of Suzhou University, 2020, 35(10): 70-74.

[7] Yang Xinyu, Li Aiping, Duan Liguo, et al. WSN data compression based on dictionary learning and compressed sensing. Computer Engineering and Design, 2022, 43(09): 2448-2455.

[8] Li Ke. Randomized Low-Rank Approximate Algorithms on High Dimensionality Reduction with Applications. China University of Mining and Technology, 2023.

[9] Zhu Quanjie, Sui Longkun, Chen Xuexi, et al. Denoising method and application of mine microseismic signal based on EMD-SVD. Safety and Environmental Engineering, 2024, 31(03): 110-119.

[10] Tang Fei, Liu Zhiwen. Study on multi-layer joint noise of mine microseismic signal. Nonferrous Metals (Mining Section), 2024, 76(04): 92-101.