基于输出空间知识引导的模糊规则分类器
A Knowledge-Guided Fuzzy Rule Classifier Based on Output Space Information
摘要: 传统模糊规则分类器前件划分多依赖无监督聚类,未充分利用输出空间判别信息,制约了分类性能与泛化能力。为此,本文提出知识引导的模糊规则分类器框架(KGFRC),将输出空间知识引导的判别模糊划分与后件规则学习融合为两阶段监督学习范式。模糊划分阶段引入邻近度模糊C均值(PFCM)和改进型模糊C均值(RFCM),并提出成对约束改进型模糊C均值算法(PC-RFCM),在全局输出相似度加权基础上融入局部成对约束,增强模糊边界判别能力。在后件学习阶段,以L2正则化的交叉熵损失为目标函数,优化TSK规则后件权重。在12个UCI标准数据集上实验,与多种经典分类器及模糊方法对比,KGFRC综合性能优于所有对比算法,统计检验中平均排名最优。
Abstract: Traditional fuzzy rule classifiers often rely on unsupervised clustering for antecedent partitioning, failing to fully exploit the discriminative information in the output space, which limits their classification performance and generalization ability. To address this issue, this paper proposes a knowledge-guided fuzzy rule classifier framework (KGFRC), which integrates output-space knowledge-guided discriminative fuzzy partitioning with consequent rule learning into a two-stage supervised learning paradigm. In the fuzzy partitioning stage, two strategies are introduced: proximity fuzzy C-means (PFCM) and refined fuzzy C-means (RFCM). Furthermore, a pairwise constraint-based refined fuzzy C-means algorithm (PC-RFCM) is proposed, which incorporates local pairwise constraints into global output-similarity weighting to enhance the discriminative ability of fuzzy boundaries. In the consequent learning stage, a cross-entropy loss with L2 regularization is adopted as the objective function to optimize the consequent weights of TSK rules. Experiments are conducted on 12 UCI standard datasets, comparing the proposed method with various classical classifiers and fuzzy methods. The results demonstrate that KGFRC outperforms all comparison algorithms in overall performance, and the proposed method achieves the best average rank in the statistical tests.
文章引用:马艺华, 张大庆. 基于输出空间知识引导的模糊规则分类器[J]. 应用数学进展, 2026, 15(11): 152-166. https://doi.org/10.12677/aam.2026.1511439

参考文献

[1] Yang, J., Liu, Z., Wang, G., Zhang, Q., Xia, S., Wu, D., et al. (2025) Constructing Three-Way Decision with Fuzzy Granular-Ball Rough Sets Based on Uncertainty Invariance. IEEE Transactions on Fuzzy Systems, 33, 1781-1792.
https://doi.org/10.1109/tfuzz.2025.3536564
[2] Li, M., Zang, Z., Lu, W. and Pedrycz, W. (2026) A Linguistically Interpretable Fuzzy Fault Diagnosis Model: Knowledge Distillation Perspective. IEEE Transactions on Fuzzy Systems, 34, 189-203.
https://doi.org/10.1109/tfuzz.2025.3624974
[3] Huang, Q., Gao, S., Li, G. and Wang, W. (2026) Fuzzy Knowledge Perception with Fault Tolerance and Brain-Inspired Reasoning for Diagnosis of Ultrasound Images. IEEE Transactions on Fuzzy Systems, 34, 1295-1306.
https://doi.org/10.1109/tfuzz.2026.3655414
[4] Zadeh, L.A. (1965) Fuzzy Sets. Information and Control, 8, 338-353.
https://doi.org/10.1016/s0019-9958(65)90241-x
[5] Mamdani, E.H. and Assilian, S. (1975) An Experiment in Linguistic Synthesis with a Fuzzy Logic Controller. International Journal of Man-Machine Studies, 7, 1-13.
https://doi.org/10.1016/s0020-7373(75)80002-2
[6] Takagi, T. and Sugeno, M. (1985) Fuzzy Identification of Systems and Its Applications to Modeling and Control. IEEE Transactions on Systems, Man, and Cybernetics, 15, 116-132.
https://doi.org/10.1109/tsmc.1985.6313399
[7] Wang, L.-X. and Mendel, J.M. (1992) Generating Fuzzy Rules by Learning from Examples. IEEE Transactions on Systems, Man, and Cybernetics, 22, 1414-1427.
https://doi.org/10.1109/21.199466
[8] Shen, Y., Pedrycz, W. and Wang, X. (2019) Clustering Homogeneous Granular Data: Formation and Evaluation. IEEE Transactions on Cybernetics, 49, 1391-1402.
https://doi.org/10.1109/tcyb.2018.2802453
[9] Zhou, X., Zhang, Q., Zhao, F., Wang, Y., Yin, L. and Wang, G. (2026) A Novel Multigranularity Clustering Algorithm Based on Grid Partition and Fuzzy Quotient Space. IEEE Transactions on Fuzzy Systems, 34, 311-323.
https://doi.org/10.1109/tfuzz.2025.3636149
[10] Zhou, C.-J., Liu, Z.-K. and Yao, W. (2026) Clustering Based on Transitive Closure of Distance Functions. IEEE Transactions on Fuzzy Systems, 34, 263-272.
https://doi.org/10.1109/tfuzz.2025.3633781
[11] Shen, Y., Pedrycz, W., Jing, X., Gacek, A., Wang, X. and Liu, B. (2021) Identification of Fuzzy Rule-Based Models with Output Space Knowledge Guidance. IEEE Transactions on Fuzzy Systems, 29, 3504-3518.
https://doi.org/10.1109/tfuzz.2020.3024804
[12] Jang, J.-R. (1993) ANFIS: Adaptive-Network-Based Fuzzy Inference System. IEEE Transactions on Systems, Man, and Cybernetics, 23, 665-685.
https://doi.org/10.1109/21.256541
[13] del Jesus, M.J., Hoffmann, F., JuncoNavascues, L. and Sanchez, L. (2004) Induction of Fuzzy-Rule-Based Classifiers with Evolutionary Boosting Algorithms. IEEE Transactions on Fuzzy Systems, 12, 296-308.
https://doi.org/10.1109/tfuzz.2004.825972
[14] Ishibuchi, H., Yamamoto, T. and Nakashima, T. (2005) Hybridization of Fuzzy GBML Approaches for Pattern Classification Problems. IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics), 35, 359-365.
https://doi.org/10.1109/tsmcb.2004.842257
[15] Jiménez, F., Sánchez, G. and Juárez, J.M. (2014) Multi-Objective Evolutionary Algorithms for Fuzzy Classification in Survival Prediction. Artificial Intelligence in Medicine, 60, 197-219.
https://doi.org/10.1016/j.artmed.2013.12.006
[16] Zhang, Y., Ishibuchi, H. and Wang, S. (2018) Deep Takagi-Sugeno-Kang Fuzzy Classifier with Shared Linguistic Fuzzy Rules. IEEE Transactions on Fuzzy Systems, 26, 1535-1549.
https://doi.org/10.1109/tfuzz.2017.2729507
[17] Wagstaff, K., Cardie, C., Rogers, S. and Schrodl, S. (2001) Constrained k-Means Clustering with Background Knowledge. In: Proceedings of the Eighteenth International Conference on Machine Learning, Morgan Kaufmann Publishers Inc., 577-584.
[18] Huang, Q., Fan, Q., Xing, Z., Yang, X. and He, X. (2025) Convergence Analysis of a Novel High Order Networks Model Based on Entropy Error Function. Mathematics and Computers in Simulation, 227, 405-419.
https://doi.org/10.1016/j.matcom.2024.08.014
[19] Fan, Q., Niu, L. and Kang, Q. (2020) Regression and Multiclass Classification Using Sparse Extreme Learning Machine via Smoothing Group l1/2 Regularizer. IEEE Access, 8, 191482-191494.
https://doi.org/10.1109/access.2020.3031647
[20] Alcala-Fdez, J., Fernandez, A., Luengo, J., Derrac, J., Garcia, S., Sanchez, L. and Herrera, F. (2011) KEEL Data-Mining Software Tool: Data Set Repository, Integration of Algorithms and Experimental Analysis Framework. Journal of Multiple-Valued Logic & Soft Computing, 17, 255-287.
[21] Hill, M.G., Connolly, P.G., Reutemann, P. and Fletcher, D. (2014) The Use of Data Mining to Assist Crop Protection Decisions on Kiwifruit in New Zealand. Computers and Electronics in Agriculture, 108, 250-257.
https://doi.org/10.1016/j.compag.2014.08.011
[22] Hajek, P. and Novotny, J. (2022) Fuzzy Rule-Based Prediction of Gold Prices Using News Affect. Expert Systems with Applications, 193, Article ID: 116487.
https://doi.org/10.1016/j.eswa.2021.116487
[23] Demšar, J. and Schuurmans, D. (2006) Statistical Comparisons of Classifiers over Multiple Data Sets. Journal of Machine Learning Research, 7, 1-30.