Abstract Arbitrary shape clusters are difficult to be found by the K-means algorithm adopted in the implementation of floating centroids method (FCM). Moreover, K-means algorithm is sensitive to outliers. Aiming at these problems, density-based spatial clustering of applications with noise (DBSCAN) algorithm is used to improve FCM neural network classifier in this paper. The outliers are considered as the points that can not be dealt with, and clusters of arbitrary shape can be found by DBSCAN algorithm. Thus, the color points in the partition space can be divided into several more accurate partitions. In addition, an optimization objective function is defined, and the particle swarm optimization algorithm is employed to optimize the parameters of the neural network to obtain an optimal classification model. Several commonly used datasets from UCI database are selected to conduct a comparative experiment. The experimental results show that the improved FCM method generates better performance on classification accuracy, robustness and running time than that of the original FCM method.
[1] QUINLAN J R. Induction of Decision Trees. Machine Learning, 1986, 1(1): 81-106. [2] FRIEDMAN N, LINIAL M, NACHMAN I, et al. Using Bayesian Networks to Analyze Expression Data. Journal of Computational Biology, 2000, 7(3/4): 601-620. [3] WANG B X, JAPKOWICZ N. Boosting Support Vector Machines for Imbalanced Data Sets. Knowledge and Information Systems, 2010, 25(1): 1-20. [4] KKNAR-TEZEL S, LATECKI L J. Improving SVM Classification on Imbalanced Time Series Data Sets with Ghost Points. Knowledge and Information Systems, 2011, 28(1): 1-23. [5] CRAVEN M W, SHAVLIK J W. Using Neural Networks for Data Mining. Future Generation Computer Systems, 1997, 13(2/3): 211-229. [6] BRIDLE J S. Probabilistic Interpretation of Feedforward Classification Network Outputs, with Relationships to Statistical Pattern Re-cognition // SOULI F F, HRAUT J, eds. Neurocomputing. Be-rlin, Germany:Springer, 1990: 227-236. [7] DIETTERICH T G, BAKIRI G. Solving Multiclass Learning Pro-blems via Error-Correcting Output Codes. Journal of Artificial Intelligence Research, 1995, 2: 263-286. [8] WANG L, YANG B, CHEN Z, et al. A Novel Improvement of Neural Network Classification Using Further Division of Partition Space [EB/OL].[2014-06-28]. http:// www.softcomputing. net/iwinac07_1.pdf. [9] YANG B, WANG L, CHEN Z X, et al. A Novel Classification Method Using the Combination of FDPS and Flexible Neural Tree. Neurocomputing, 2010, 73(4/5/6): 690-699. [10] HAN J W, KAMBER M, PEI J. Data Mining: Concepts and Techniques. 2nd Edition. San Francisco, USA: Morgan Kaufmann, 2006. [11] 聂跃光.基于密度聚类的空间数据挖掘算法研究.硕士学位论文.太原:太原科技大学, 2008. (NIE Y G. Study of Spatial Data Mining Algorithm Based on Density Clustering. Master Dissertation. Taiyuan, China: Taiyuan University of Science and Technology, 2008) [12] 何中胜,刘宗田,庄燕滨.基于数据分区的并行DBSCAN算法.小型微型计算机系统, 2006, 27(1): 114-116. (HE Z S, LIU Z T, ZHUANG Y B. Data-Partitioning-Based Pa-rallel DBSCAN Algorithm. Journal of Chinese Computer Systems, 2006, 27(1): 114-116.) [13] SANDER J, ESTER M, KRIEGEL H P, et al. Density-Based Clustering in Spatial Databases: The Algorithm GDBSCAN and Its Applications. Data Mining and Knowledge Discovery, 1998, 2(2): 169-194. [14] 蔡颖琨,谢昆青,马修军.屏蔽了输入参数敏感性的DBSCAN改进算法.北京大学学报(自然科学版), 2004, 40(3): 480-486. (CAI Y K, XIE K Q, MA X J. An Improved DBSCAN Algorithm Which Is Insensitive to Input Parameters. Acta Scientiarum Naturalium Universitatis Pekinensis, 2004, 40(3): 480-486.) [15] 陈燕俐,洪 龙,金达文,等.一种简单有效的基于密度的聚类分析算法.南京邮电大学学报, 2005, 25(4): 24-29. (CHEN Y L, HONG L, JIN D W, et al. A Simple and Valid Density-Based Clustering Algorithm. Journal of Nanjing University of Posts and Telecommunications, 2005, 25(4): 24-29.) [16] WANG L, YANG B, CHEN Y H, et al. Improvement of Neural Network Classifier Using Floating Centroids. Knowledge and Information Systems, 2012, 31(3): 433-454. [17] 吴夙慧,成 颖,郑彦宁,等.K-means算法研究综述.现代图书情报技术, 2011, 27(5): 28-35. (WU S H, CHENG Y, ZHENG Y N, et al. Survey on K-means Algorithm. New Technology of Library and Information Service, 2011, 27(5): 28-35.) [18] WU J Y. MIMO CMAC Neural Network Classifier for Solving Classification Problems. Applied Soft Computing, 2011, 11(2): 2326-2333. [19] OZYILDIRIM B M, AVCI M. Generalized Classifier Neural Network. Neural Networks, 2013, 39: 18-26. [20] 罗启福.基于云计算的DBSCAN算法研究.硕士学位论文.武汉: 武汉理工大学, 2013. (LUO Q F. Research on DBSCAN Algorithm Based on Cloud Computing. Master Dissertation. Wuhan, China: Wuhan University of Technology, 2013.) [21] POLI R, KENNEDY J, BLACKWELL T. Particle Swarm Optimization: An Overview. Swarm Intelligence, 2007, 1(1): 33-57.
2016, Vol. 29 
