摘要
为了解决处理大样本和超大样本数据集消耗大量时间和准确性问题,将中心约束型最小包含球(CCMEB)理论融合对TSK模糊系统(Takagi-Sugeno-Kang fuzzy system)重新审视和改进而成的双层TSK模糊系统CTSK(centralized TSK fuzzy system)。两种系统取长补短结合成新的适合处理大样本数据的算法系统。仿真实验研究分析了不同的模糊规则对新算法的影响以及所提出的算法与另外三种国际上较为先进的处理大数据算法的性能比较,结果表明所提出的算法对处理大样本数据的有效性和快速性。
In order to solve handling large sample sets or super large sample sets consuming large amount of time and accuracy problems,this paper fused CCMEB theory with the centralized TSK fuzzy system which was re-examined and improved on the TSK fuzzy system. Both systems complemented each other to fit together and formed a new algorithm system suitable for dealing with large sample data. Simulation experimental studied and analyzed the effects of different fuzzy rules to the new algorithm and compared the performance of the new algorithm with three other international algorithms handling large size datasets. The results show that the proposed algorithm's validity and rapidity for handling large size datasets.
引文
[1]孙光华,甘刚.基于模糊理论的主观信任评价模型的研究[J].计算机应用研究,2014,31(3):769-772.
[2]孙家振,朱玉全,周李威,等.基于模糊规则的学习者认知水平估算方法[J].计算机应用研究,2014,31(9):2652-2655.
[3]Mitaim S,Kosko B.The shape of fuzzy sets in adaptive function approximation[J].IEEE Trans on Fuzzy systems,2001,9(4):637-655.
[4]Homoda R Z,Sahari K S M,Almurib H A F,et al.Gradient autotuned Takagi-Sugeno fuzzy forward control of a HVAC system using predicted mean vote index[J].Energy and Buildings,2012,49(1):254-267.
[5]Wu Dongrui.Approaches for reducing the computational cost of interval Type-2 fuzzy logic systems overview and comparisons[J].IEEE Trans on Fuzzy Systems,2013,21(1):80-99.
[6]Jafarzadeh S,Fadali M S,Sonbol A H.Stability analysis and control of discrete Type-1 and Type-2 TSK fuzzy systems:part I.stability analysis[J].IEEE Trans on Fuzzy Systems,2011,19(6):989-1000.
[7]Tseng C L,Wang S Y,Chien S C,et al.Development of a self-tuning TSK-fuzzy speed control strategy for switched reluctance motor[J].IEEE Trans on Power Electronics,2012,27(4):2141-2152.
[8]Juang C F,Chen Chiyou.Data-driven interval Type-2 neural fuzzy system with high learning accuracy and improved model interpretability[J].IEEE Trans on Cybernetics,2012,43(6):1781-1795.
[9]徐华,薛恒新.中心化模糊系统CTSK的分析及应用[J].计算机工程,2008,34(23):7-16.
[10]Megiddo N.Linear-time algorithms for linear programming in R3and related problems[J].SIAM Journal on Computing,1983,12(1):759-776.
[11]Welzl E.Smallest enclosing disks(balls and ellipsoids)[J].New Results and New Trends in Computer Science,1991,3(2):359-370.
[12]Badoiu M,Clarkson K L.Optimal core sets for balls[J].Computational Geometry,2008,40(1):14-22.
[13]Nielsen F,Nock R.Approximating smallest enclosing balls[C]//Proc of International Conference on Computational Science and Its Applications.Berlin:Springer,2004:147-157.
[14]Takagi T,Sugeno M.Fuzzy identification of systems and its applications to modeling and control[J].IEEE Trans on System,Man and Cybernetics,1985,15(1):116-132.
[15]徐华.空气污染和水污染的管理方法模型[D].南京:南京理工大学,2009.
[16]Chung K F L,Duan Jicheng.On multistage fuzzy neural network modeling[J].IEEE Trans on Fuzzy Systems,2000,8(2):125-142.
[17]Shi Jianing,Yin Wotao,Osher S,et al.A fast hybrid algorithm for large-cale L1-regularized logistic regression[J].Journal of Machine Learning Research,2010,11(2):713-741.
[18]Chen Yiping,Li Xiang.Image denoising with gradient projection[C]//Proc of IEEE International Conference on Signal Processing,Communications and Computing.2011:1-4.
[19]蔡前凤,郝志峰,刘伟.基于模糊划分和支持向量机的TSK模糊系统[J].模式识别与人工智能,2009,22(3):411-416.
[20]钱鹏江,王士同,邓赵红,等.基于最小包含球的大数据集快速谱聚类算法[J].电子学报,2010,38(9):2035-2041.
[21]Zhang Yingsong,Kingsbury N.Fast L0-based sparse signal recovery[C]//Proc of IEEE International Workshop on Machine Learning for Signal Processing.[S.l.]:IEEE Press,2010:403-408.
[22]Liu Yan,Wu Wei,Fan Qinwei,et al.A modified gradient learning algorithm with smoothing L1/2 regularization for Takagi-Sugeno fuzzy model[J/OL].2014.http://dx.doi.org/10.1016/j.neucom.2014.01.041.
[23]Lee C H,Zaane O R,Park H H,et al.Clustering high dimensio-nal data:a graph-based relaxed optimization approach[J].Information Sciences,2008,178(23):4501-4511.
[24]Forghani Y,Yazdi H S.Robast support vector machine-trained fuzzy system[J].Neural Networks,2014,50(1):154-165.
[25]Chung F L,Deng Zhaohong,Wang Shitong.From minimum enclosing ball to fast fuzzy inference system training on large datasets[J].IEEE Trans on Fuzzy Systems,2009,17(1):173-184.
[26]Huang Guangbin,Liang Nanying,Rong Haijun,et al.On-line sequential extreme learning machine[C]//Proc of IASTED International Conference on Computer Intelligence.2005:250-257.
[27]Xu Pengcheng,Jayawardena A W,Li W K.Model selection for RBF network via generalized degree of freedom[J].Neurocomputing,2013,99(2):163-171.
[28]许敏,王士同,顾鑫,等.基于最小包含球的大数据集域自适应快速算法[J].模式识别与人工智能,2013,24(10):2312-2326.