计算机科学 ›› 2025, Vol. 52 ›› Issue (7): 75-81.doi: 10.11896/jsjkx.240500086
王维, 赵云龙, 彭小玉, 潘小东
WANG Wei, ZHAO Yunlong, PENG Xiaoyu, PAN Xiaodong
摘要： Takagi-Sugeno-Kang(TSK)模糊系统作为特殊的非线性回归系统,能够解决机器学习任务,但其处理高维问题的效果并不理想,且对于规则的确定和调整较为困难。为了优化该系统,将沿用模糊IF-THEN规则。首先运用模糊C均值聚类对数据集进行划分,将数据点嵌入表征点到模糊聚类中心隶属度的空间,进而利用孪生支持向量回归机(TSVR)确定两个回归平面,从而得到回归值。考虑到不同数据集适应不同的关键参数,如聚类数等,采用遗传算法(GA)进行统一参数寻优,简化了领域知识的先验设置,形成了TSVR-GA-TSK(TG-TSK)模糊系统。实验结果表明,相比于经典回归算法和典型的TSK模糊系统,TG-TSK模糊系统具有良好的回归精度和鲁棒性,在Nemenyi检验的两两比较中具有显著优势。
中图分类号:
| [1]SUGENO M,KANG G T.Structure identification of fuzzy mo-del[J].Fuzzy Sets and Systems,1988,28(1):15-33. [2]WANG L X.Fuzzy System and Fuzzy Control Course[M].Beijing:Tsinghua University Press,2003. [3]CAI Q F,HAO Z F,LIU W.TSK Fuzzy System based on Fuzzy Partition and Support Vector Machine[J].Pattern Recognition and Artificial Intelligence,2009(3):411-416. [4]LIANG Y M,SU F,LI Q,et al.Self-organization algorithm of T-S Fuzzy model based on support vector Machine regression and its application[J].Acta Automatica Sinica,2013,39(12):2143-2149. [5]CHEN S G,WU X J.A new fuzzy twin support vector machine for pattern classification[J].International Journal of Machine Learning and Cybernetics,2018,9:1553-1564. [6]JIANG Y Z,HUA L,ZHANG Q,et al.Multi-task TSK fuzzy system model driven by multi-task fuzzy clustering[J].Chinese Journal of Applied Sciences,2019,38(5):742-760. [7]ZHOU T,DENG Z H,JIANG Y Z,et al.Multi-module TSKfuzzy system based on training space reconstruction[J].Journal of Software,2020,31(11):3506-3518. [8]LOU Q,DENG Z,XIAO Z,et al.Multilabel Takagi-Sugeno-Kang Fuzzy System[J].IEEE Transactions on Fuzzy Systems,2021,30(9):3410-3425. [9]GUO F,LIU J,LI M,et al.A concise TSK fuzzy ensemble classifier integrating dropout and bagging for high-dimensional problems[J].IEEE Transactions on Fuzzy Systems,2021,30(8):3176-3190. [10]GU X Q,NI T G,ZHANG C,et al.Probabilistic TSK fuzzy system for collaborative Learning of structure Identification and parameter Optimization[J].Acta Automatica Sinica,2021,47(2):349-362. [11]BRIKH L,GUENOUNOU O,BAKIR T.Selection of minimum rules from a fuzzy TSK model using a PSO-FCM combination[J].Journal of Control,Automation and Electrical Systems,2023,34(2):384-393. [12]PENG X.TSVR:An efficient twin support vector machine for regression[J].Neural Networks,2010,23(3):365-372. [13]LI H.Statistical Learning Methods(2nd Ed.)[M].Beijing:Tsinghua University Press,2012. [14]OPTIMIZATION S M.A fast algorithm for training supportvector machines[J].CiteSeerX,1998,10(1.43):4376. [15]BURGES C J C.A tutorial on support vector machine for pattern recognition[J].Data Mining and Knowledge Discovery,1998,2(2):955-974. [16]XU B Y,GU B J,PAN F,et al.Weighted smooth projection twin support vector regression algorithm[J].Computer Engineering,2022,48(12):104-111,118. [17]DEMSAR J.Statistical comparisons of classifiers over multiple data sets[J].Journal of Machine Learning Research,2006,7(1):1-30. |
|
||
首页