Journal of Applied Science and Engineering

Published by Tamkang University Press

ESCI jase impact factor scopus logo open access rate of Scopus journal

Feature Selection for High-Dimensional Power Grid Data Based on Iterative Soft-Threshold Learning Algorithms

 2026

 Volume 35

Zheng Wu Lue, Chen Qing Peng, Zhang Xin, Yuan Wen Jun, and Wang Hao

China Southern Power Grid Co., Ltd. EHV Transmission Company, GuangZhou 510000, China

Received: October 23, 2025
Accepted: May 30, 2026
Publication Date: September 18, 2026

上傳圖片

NMI with Different Feature Numbers Selected on AMI User Electricity Dataset

 Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: BibTeX | http://dx.doi.org/10.6180/jase.202612_35.049

Download PDF

Power grid data faces challenges like high dimensionality, heterogeneity, and strong coupling, leading to redundancy and weak discriminative power in feature selection. To address this, a novel feature selection method based on the Learning Iterative Soft Thresholding Algorithm (LISTA) is proposed. Unlike traditional ISTA, LISTA introduces a secant line linear search to dynamically optimize step sizes, improving convergence. By integrating sparse regression and manifold learning, the method captures complex feature relationships. Experimental results show significant improvements, reducing selected features by 51.4% and achieving better clustering. The method enhances real-world power grid decision-making by enabling faster, more accurate fault detection and grid management.

Keywords: Iterative Soft Threshold Learning; Power Grid Data; High Dimensionality; Feature Selection; Tangent Line Linear Search; Feature Weighting

  1. [1] M. Reza, F. Faraji, and J. N. Kutz, (2024) “Data-driven inference of high-dimensional spatiotemporal state of plasma systems” Journal of Applied Physics 136(18): 183301. DOI: https://doi.org/10.1063/5.0230056.
  2. [2] I. B. Petrov, V. I. Golubev, A. V. Shevchenko, and A. Sharma, (2024) “Three-Dimensional Grid-Characteristic Schemes of High Order of Approximation” Doklady Mathematics 110(3): 457-463. DOI: https://doi.org/10.1134/S1064562424601343.
  3. [3] P. G. Poličar and B. Zupan, (2025) “Uncovering temporal patterns in visualizations of high-dimensional data” Machine Learning 114(2): 35. DOI: https://doi.org/10.1007/s10994-025-06734-z.
  4. [4] K. Borah, H. S. Das, S. Seth, K. Mallick, Z. Rahaman, and S. Mallik, (2024) “A review on advancements in feature selection and feature extraction for high-dimensional NGS data analysis” Functional and Integrative Genomics 24(5): 139. DOI: https://doi.org/10.1007/s10142-024-01415-x.
  5. [5] A. Bhattacharjee and S. Halder, (2025) “Weight index of high-dimensional time-to-event feature selection method” Iran Journal of Computer Science 8(2): 647-657. DOI: https://doi.org/10.1007/s42044-024-00218-4.
  6. [6] H. Hassani, E. Hallaji, R. Razavi-Far, and M. Saif, (2025) “Learning from high-dimensional cyber-physical data streams: a case of large-scale smart grid” International Journal of Machine Learning and Cybernetics 16(3): 1819-1831. DOI: https://doi.org/10.1007/s13042-024-02365-3.
  7. [7] A. K. Aryanti, R. Herteno, F. Indriani, R. A. Nugroho, and M. Muliadi, (2025) “Implementation of Copeland Method on Wrapper-Based Feature Selection Using Random Forest For Software Defect Prediction” Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics 7(1): 90-101. DOI: https://doi.org/10.35882/2pgffc67.
  8. [8] Z. Cao, X. Xie, F. Sun, and J. Qian, (2023) “Consensus cluster structure guided multi-view unsupervised feature selection” Knowledge-Based Systems 271: 110578. DOI: https://doi.org/10.1016/j.knosys.2023.110578.
  9. [9] R. R. Mostafa, A. M. Khedr, Z. Al Aghbari, I. Afyouni, I. Kamel, and N. Ahmed, (2024) “An adaptive hybrid mutated differential evolution feature selection method for low and high-dimensional medical datasets” Knowledge-Based Systems 283: 111218. DOI: https://doi.org/10.1016/j.knosys.2023.111218.
  10. [10] H. Chamlal, T. Ouaderhman, and B. El Mourtji, (2023) “Feature selection in high dimensional data: A specific preordonnances-based memetic algorithm” Knowledge-Based Systems 266: 110420. DOI: https://doi.org/10.1016/j.knosys.2023.110420.
  11. [11] Z. Kun, L. Hongren, W. Xin, X. Daxing, and S. Xiaokai, (2024) “Deep Multiscale Soft-Threshold Support Vector Data Description for Enhanced Heavy-Duty Gas Turbine Generator Sets’ Anomaly Detection” Shock and Vibration 2024(1): 3374107. DOI: https://doi.org/10.1155/2024/3374107.
  12. [12] B. H. Tozlu, (2025) “Feature Selection and Classification Optimization of Transformer Oil Odor Data With Recursive Feature Elimination Using Grid Search and Cross-Validation” IEEE Access 13: 21043-21051. DOI: https://doi.org/10.1109/ACCESS.2025.3536288.
  13. [13] A. K. Mahapatra, N. Panda, and B. K. Pattanayak, (2025) “Adaptive dimensional search-based orthogonal experimentation SSA (ADOX-SSA) for training RBF neural network and optimal feature selection” Journal of Supercomputing 81(1): 212. DOI: https://doi.org/10.1007/s11227-024-06507-w.
  14. [14] M. Braik, M. A. Awadallah, H. Alzoubi, and H. Al-Hiary, (2025) “Heterogeneous cognitive learning chameleon swarm algorithm for high-dimensional feature selection” Journal of Supercomputing 81(5): 652. DOI: https://doi.org/10.1007/s11227-025-07139-4.
  15. [15] N. Nekouie, M. Romoozi, and M. Esmaeili, (2023) “Multimodal feature selection from microarray data based on Dempster-Shafer evidence fusion” Journal of Supercomputing 79(11): 12591-12621. DOI: https://doi.org/10.1007/s11227-023-05138-x.
  16. [16] S. S. Baawi, E. Hakem, A. A. Al-Hamzawi, D. Al-Shammary, A. Ibaida, and A. M. Mahdi, (2025) “Hilbert similarity convex for efficient EEG feature selections” Journal of Supercomputing 81(5): 736. DOI: https://doi.org/10.1007/s11227-025-07199-6.
  17. [17] M. S. Oh, A. B. Das, T. Kim, D. J. Love, and C. G. Brinton, (2024) “Minimum Description Feature Selection for Complexity Reduction in Machine Learning-Based Wireless Positioning” IEEE Journal on Selected Areas in Communications 42(9): 2585-2600. DOI: https://doi.org/10.1109/JSAC.2024.3413977.
  18. [18] E. Hancer, B. Xue, and M. Zhang, (2023) “An evolutionary filter approach to feature selection in classification for both single- and multi-objective scenarios” Knowledge-Based Systems 280: 111008. DOI: https://doi.org/10.1016/j.knosys.2023.111008.
  19. [19] M. Firouznia, P. Ruiu, and G. A. Trunfio, (2023) “Adaptive cooperative coevolutionary differential evolution for parallel feature selection in high-dimensional datasets” Journal of Supercomputing 79(14): 15215-15244. DOI: https://doi.org/10.1007/s11227-023-05226-y.
  20. [20] L. N. Felber, H. Harbrecht, and M. Schmidlin, (2024) “Identification of Sparsely Representable Diffusion Parameters in Elliptic Problems” SIAM Journal on Imaging Sciences 17(1): 61-90. DOI: https://doi.org/10.1137/23M1565346.