Adaptive Feature Selection of Unbalanced Data for Skiing Teaching

Tao  Feng

doi:10.6180/jase.202603_29(3).0006

Adaptive Feature Selection of Unbalanced Data for Skiing Teaching

Physics

Tao FengThis email address is being protected from spambots. You need JavaScript enabled to view it.

Physical Education Teaching and Research Department, Harbin Finance University, Harbin 150030 China

Received: May 14, 2025
Accepted: June 16, 2025
Publication Date: June 26, 2025

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: ||https://doi.org/10.6180/jase.202603_29(3).0006

In skiing teaching, the data may show an unbalanced distribution. For example, the sample size of some common movements(such as straight downhill) may be much larger than that of some difficult movements (such as aerial spins). If the features are not selected, the model may overly rely on the features of common actions and ignore the features of difficult actions. Through the feature selection of unbalanced data, features that have significant influences on different actions (especially a few types of actions) can be screened out, thereby enhancing the recognition ability and generalization ability for various actions. The high-dimensional characteristics of the skiing dataset will reduce the classification effect of unbalanced learning. Aiming at the classification problem of high-dimensional unbalanced data, this paper proposes an adaptive feature selection method. This new algorithm combines embedded and wrapped feature selection methods and is capable of adaptively selecting the optimal features to form the feature space. Finally, the experimental results on the public imbalanced dataset show that the proposed algorithm effectively improves the classification performance of imbalanced data.

Keywords: skiing teaching; adaptive feature selection; unbalanced data; high-dimensional characteristics

[1] N. Kurpiers and U. G. Kersting, (2017) “The one-ski method—effects of an alternative teaching approach on selected movement patterns in alpine skiing" Cogent Social Sciences 3(1): 1275958. DOI: 10.1080/23311886.2016.1275958.
[2] T. Li, J. Wang, K. Wiltos, and M. Wo´zniak, (2024) “An Intelligent Proofreading for Remote Skiing Actions Based on Variable Shape Basis" Mobile Networks and Applications: 1–14. DOI: 10.1007/s11036-024-02419-4.
[3] J. Lin, (2022) “Classroom teaching design of alpine skiing based on virtual reality technology" Mathematical Problems in Engineering 2022(1): 5721790. DOI: 10.1155/2022/5721790.
[4] Y. Sun, S. Yin, H. Li, L. Teng, and S. Karim, (2019) “GPOGC:Gaussianpigeon-oriented graph clustering algorithm for social networks cluster" IEEE Access 7: 99254–99262. DOI: 10.1109/ACCESS.2019.2926816.
[5] C. Lin, C.-F. Tsai, and W.-C. Lin, (2023) “Towards hybrid over-and under-sampling combination methods for class imbalanced datasets: an experimental study" Artificial Intelligence Review 56(2): 845–863. DOI: 10. 1007/s10462-022-10186-5.
[6] N.WangandE.Zhao,(2024)“Anewmethodforfeature selection based on weighted k-nearest neighborhood rough set" Expert Systems with Applications 238: 122324. DOI: 10.1016/j.eswa.2023.122324.
[7] J. Yu, L. Zhao, S. Yin, and M. Ivanovi´ c, (2024) “News recommendation model based on encoder graph neural network and bat optimization in online social multimedia art education" Computer Science and Information Systems 21(3): 989–1012. DOI: 10.2298/CSIS231225025Y.
[8] J. Liu, Y. Lin, J. Du, H. Zhang, Z. Chen, and J. Zhang, (2023) “ASFS: A novel streaming feature selection for multi-label data based on neighborhood rough set" Ap plied Intelligence 53(2): 1707–1724. DOI: 10.1007/ s10489-022-03366-x.
[9] B. Sang, W. Xu, H. Chen, and T. Li,(2023) “Active antinoise fuzzy dominance rough feature selection using adaptive k-nearest neighbors" IEEE Transactions on Fuzzy Systems 31(11): 3944–3958. DOI: 10.1109/TFUZZ. 2023.3272316.
[10] I. Niño-Adan, I. Landa-Torres, E. Portillo, and D. Manjarres, (2022) “Influence of statistical feature normalisation methods on K-Nearest Neighbours and K-Means in the context of industry 4.0" Engineering Applications of Artificial Intelligence 111: 104807. DOI: 10. 1016/j.engappai.2022.104807.
[11] L. Sun, J. Zhang, W. Ding, and J. Xu, (2022) “Feature reduction for imbalanced data classification using similarity-based feature clustering with adaptive weighted k-nearest neighbors" Information Sciences 593: 591 613. DOI: 10.1016/j.ins.2022.02.004.
[12] S. Chormunge and S. Jena, (2018) “Correlation based feature selection with clustering for high dimensional data" Journal of Electrical Systems and Information Technology 5(3): 542–549. DOI: 10.1016/j.jesit.2017.06.004.
[13] D. Dhabliya, K. Jain, M. Bargavi, A. Dhablia, J. R. R. Kumar, A. Gupta, S. Pramanik, et al. “Item Selection Using K-Means and Cosine Similarity”. In: AI-Driven Marketing Research and Data Analytics. IGI Global, 2024, 228–244. DOI: 10.4018/979-8-3693-2165-2.ch013.
[14] D. Thakur and S. Biswas, (2024) “Permutation importance based modified guided regularized random forest in human activity recognition with smartphone" Engineering Applications of Artificial Intelligence 129: 107681. DOI: 10.1016/j.engappai.2023.107681.
[15] B. Elkari, Y. Chaibi, T. Kousksou, et al., (2024) “Random forest with feature selection and K-fold cross valida tion for predicting the electrical and thermal efficiencies of air based photovoltaic-thermal systems" Energy Reports 12: 988–999. DOI: 10.1016/j.egyr.2024.07.002.
[16] Z. Runchi, X. Liguo, and W. Qin, (2023) “An ensemble credit scoring model based on logistic regression with heterogeneous balancing and weighting effects" Expert Systems with Applications 212: 118732. DOI: 10.1016/j.eswa.2022.118732.
[17] D. Lee and S. Suh, (2025) “Measuring Income and Wealth Inequality: A Note on the Gini Coefficient for Samples with Negative Values" Social Indicators Research 176(3): 947–965. DOI: 10.1007/s11205-024-03488-4.
[18] V. Ignatenko, A. Surkov, and S. Koltcov, (2024) “Random forests with parametric entropy-based information gains for classification and regression problems" PeerJ Computer Science 10: e1775. DOI: 10.7717/peerj-cs.1775.
[19] S. P. Roy, A. Kasat, et al. “Diabetic prediction with ensemble model and feature selection using information gain method”. In: 2024 2nd International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT). IEEE. 2024, 1080–1085. DOI: 10.1109/IDCIoT59759.2024.10467649.
[20] S. Srinivasan, S. Gunasekaran, S. K. Mathivanan, B. A.M.M.B,P.Jayagopal,andG.T.Dalu,(2023)“An active learning machine technique based prediction of cardiovascular heart disease from UCI-repository database" Scientific reports 13(1): 13588. DOI: 10.1038/s41598 023-40717-1.
[21] J. Qu and M. J. Zuo, (2010) “Support vector machine based data processing algorithm for wear degree classification of slurry pump systems" Measurement 43(6): 781–791. DOI: 10.1016/j.measurement.2010.02.014.
[22] Q. Hu, D. Yu, J. Liu, and C. Wu, (2008) “Neighborhood rough set based heterogeneous feature subset selection" Information sciences 178(18): 3577–3594. DOI: 10. 1016/j.ins.2008.05.024.
[23] M.-S. Yang and Y. Nataliani, (2017) “A feature reduction fuzzy clustering algorithm based on feature weighted entropy" IEEE Transactions on Fuzzy Sys tems 26(2): 817–835. DOI: 10.1109/TFUZZ.2017.2692203.
[24] A. R. Yadav, R. S. Anand, M. Dewal, and S. Gupta. “Analysis and classification of hardwood species based on Coiflet DWT feature extraction and WEKA workbench”. In: 2014 International Conference on Signal Processing and Integrated Networks (SPIN). IEEE. 2014, 9–13. DOI: 10.1109/SPIN.2014.6776912.
[25] S. K. Behera and R. Dash, (2022) “A novel feature selection technique for enhancing performance of unbalanced text classification problem" Intelligent Decision Technologies 16(1): 51–69. DOI: 10.3233/IDT-210057.
[26] F. Qin, A. M. Zain, K.-Q. Zhou, N. B. Yusup, D. D. Prasetya, R. A. Jalil, Z. Z. Abidin, M.Bahari,Y.Kamin, and M.A.Majid, (2025) “Hybrid Harmony Search Algorithm Integrating Differential Evolution and Lévy Flight for Engineering Optimization" IEEE Access: DOI: 10. 1109/ACCESS.2025.3529714.
[27] H.T. Phuong and N. L. Giang, (2021) “Fuzzy distance based filter-wrapper incremental algorithms for attribute reduction when adding or deleting attribute set" Vietnam Journal of Science and Technology 59(2): 261–274. DOI: 10.15625/2525-2518/59/2/15698.