Về một thuật toán lai ghép lọc-đóng gói lựa chọn thuộc tính trên hệ thông tin quyết định theo tiếp cận tập thô lân cận mờ
Abstract
Neighborhood rough set theory is an effective tool for solving the problem of attribute selection in information systems with continuous numerical value domains. However, this model still has many limitations in describing the relationships between objects within the same neighborhood class. This leads to inefficiency in measures when only considering neighborhood classes entirely within a decision class. Clearly, ignoring the remaining neighborhood classes will significantly affect efficiency, even though they still hold informational value and contribute to the measures. To address these challenges, the initial research will present a new extension called the fuzzy neighborhood rough set. This model is effective in reducing noise and simplifying the computational space. Additionally, this model fully describes the characteristics of the membership degree of objects in a neighborhood class. Based on these advantages, the research also proposes a new measure to evaluate the classification capability of fuzzy neighborhood information granules. Accordingly, the analysis and proof of the effectiveness of the measures in evaluating the significance of attributes in both consistent and inconsistent information systems will be clarified. Next, we will redefine a new reduct to design an algorithm following the filter-wrapper approach for selecting an optimal subset of attributes in decision information systems. Several experimental results demonstrated the effectiveness of the proposed algorithm compared to other algorithms based on the fuzzy rough set approach.
References
Z. Pawlak, "Rough sets", International Journal of Computer & Information Sciences, vol. 11, pp. 341–356, 1982.
N. L. Giang and V. D. Thi, "An attribute reduction algorithm in a decision based on improved entropy", Journal of Computer Science and Cybernetics, vol. 27, no. 2, pp. 166–175, 2012.
N. L. Giang, N. T. Tung, and V. D. Thi, "A new method for attribute reduction to imcomplete decision table based on metric", Journal of Computer Science and Cybernetics, vol. 28, no. 2, pp. 129–140, 2012.
P. V. Anh, V. D. Thi, and N. N. Cuong, "A novel algorithm for finding all reducts in the incomplete decision table", Journal of Computer Science and Cybernetics, vol. 39, no. 4, p. 313–321, 2023.
L. A. Zadeh, "Fuzzy sets", Information and Control, vol. 8, pp. 338–353, 1965.
D. Dubois and H. Prade, "Putting rough sets and fuzzy sets together", Intelligent Decision Support, vol. 11. Dordrecht, The Netherlands: Springer, 1992, pp. 203–232.
X. Zhang, C. Mei, D. Chen, and Y. Yang, "A fuzzy rough set-based feature selection method using epresentative instances", knowledge Based Systems, vol. 151, pp. 216–229, 2018.
T. K. Sheeja and A. S. Kuriakose, "A novel feature selection method using fuzzy rough sets", Computers in Industry, vol. 97, pp. 111–116, 2018.
X. Che, D. Chen, and J. Mi, "Label correlation in multi-label classification using local attribute reductions with fuzzy rough sets", Fuzzy Sets and Systems, vol. 426, pp. 121–144, 2022.
Q. Hu, D. Yu, and Z. Xie, "Information-preserving hybrid data reduction based on fuzzy-rough techniques", Pattern Recognition Letters, vol. 27, no. 5, pp. 414–423, 2006.
B. Liang, L. Wang, and Y. Liu, "Attribute reduction based on improved information entropy", Journal of Intelligent & Fuzzy Systems, vol. 36, no. 1, pp. 709–718, 2019.
C. Wang, Y. Huang, M. Shao, and X. Fan, "Fuzzy rough set-based attribute reduction using distance measures", knowledge-Based Systems, vol. 164, pp. 205–212, 2019.
P. M. N. Ha, N. L. Giang, N. V. Thien, and N. B. Quang, "An Incremental Algorithm for Finding Reducts of Incomplete Decision Tables", Research, Development and Application on Information and Communication Technology, vol. 2019, no. 1, 2019.
V. V. Dinh, V. D. Thi, N. L. Giang, and N. Q. Tao, "Partition Distance Based Attribute Reduction in Incomplete
Decision Tables, Research", Development and Application on Information and Communication Technology, vol. 2, no. 1, 2015.
G. C. Y. Tsang, D. Chen, E. C. C. Tsang, J. W. T. Lee, and D. S. Yeung, "On attributes reduction with fuzzy rough sets", Proc. IEEE Int. Conf. Syst., Man, Cybern., vol. 3, no. 3, pp. 2775–2780, 2005.
W. L. Hung, M. S. Yang, "Similarity measures of intuitionistic fuzzy sets based on lp metric", International Journal of Approximate Reasoning, vol. 46, no. 1, pp. 120–136, 2007.
P. V. Anh, N. L. Giang, N. N. Thuy, N. T. Thuy, and P. D. Khanh, "A Novel Incremental Algorithm for Finding
the Reduct on the Decision Table when Deleting the Object Set", Research, Development and Application on Information and Communication Technology, vol. 2023, no. 2, 2023.
P. V. Anh, N. N. Thuy, V. D. Thi, and N. L. Giang, "On distance-based attribute reduction with ????, ????-level intuitionistic fuzzy sets", IEEE Access 11, pp. 138095–138107, 2023.
C. Wang, M. Shao, Q. He, Y. Qian, and Y. Qi, "Feature subset selection based on fuzzy neighborhood rough sets", KBS, vol. 111, pp. 173-179, 2016.
Q. Hu, D. Yu, J. Liu, and C. Wu, "Neighborhood rough set based heterogeneous feature subset selection", KBS, vol. 178, pp. 3577-3594, 2008.
N. L. Giang, L. H. Son, T. T. Ngan, T. M. Tuan, H. T. Phuong and et al., "Novel Incremental Algorithms for Attribute Reduction From Dynamic Decision Tables Using Hybrid Filter– Wrapper With Fuzzy Partition Distance", IEEE Transactions on Fuzzy Systems, vol. 28, no. 5, 2020.
C. Wang, Q. Hu, X. Wang, D. Chen, Y .Qian and Z. Dong, "Feature Selection Based on Neighborhood DiscriminationIndex Index", IEEE Transactions on Neural Networks and Learning Systems, vol. 29, 2017.
X. Zhang, Y. Fan and J. Yang, "Feature selection based on fuzzy-neighborhood relative decision entropy", Pattern Recognition Letters, vol. 146, 2021.
UCI Machine learning repository, “Data,” 2024. https:// archive.ics.uci.edu/
Openml machine learning platform, “Data,” 2024. https://www.openml.org/
