《计算机应用研究》|Application Research of Computers

基于粒计算的多尺度聚类尺度上推算法

Upscale algorithm of multi-scale clustering based on granular computing

免费全文下载 (已被下载 次)  
获取PDF全文
作者 赵骏鹏,赵书良,李超,高琳,池云仙
机构 河北师范大学 a.数学与信息科学学院;b.河北省计算数学与应用重点实验室;c.移动物联网研究院,石家庄 050024
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2018)02-0362-05
DOI 10.3969/j.issn.1001-3695.2018.02.010
摘要 多尺度科学在数据挖掘领域的研究多见于图像和空间数据挖掘,对一般数据的多尺度特性研究较少。传统聚类算法只在单一尺度上进行,无法充分挖掘蕴藏在数据中的知识。引入粒计算思想,进行普适的多尺度聚类方法研究,对数据进行多层次、多角度分析,实现一次挖掘,多次应用。首先,介绍粒计算相关知识;然后,提出多尺度聚类尺度上推算法UAMC(upscaling algorithm of multi-scale clustering),以簇为粒子,簇心为粒子特征进行尺度转换,利用斑块模型得到大尺度知识,避免二次挖掘带来的资源浪费。最后,利用UCI公用数据集和H省全员人口真实数据集对算法性能进行实验验证,结果表明算法在准确性上优于K-means等基准算法,是有效可行的。
关键词 多尺度;粒计算;信息粒度;斑块模型;多尺度聚类
基金项目 国家自然科学基金资助项目(71271067)
国家社科基金重大项目(13&ZD091)
河北省高等学校科学技术研究项目(QN2014196)
河北师范大学硕士基金资助项目(xj2015003)
本文URL http://www.arocmag.com/article/01-2018-02-010.html
英文标题 Upscale algorithm of multi-scale clustering based on granular computing
作者英文名 Zhao Junpeng, Zhao Shuliang, Li Chao, Gao Lin, Chi Yunxian
机构英文名 a.CollegeofMathematics&InformationScience,b.HebeiKeyLaboratoryofComputationalMathematics&Applications,c.InstituteofMobileInternetofThings,HebeiNormalUniversity,Shijiazhuang050024,China
英文摘要 Research of multi-scale scientific mainly focuses on space or image data in the field of data mining, while paying less attention to multi-scale features of general data.Traditional clustering algorithms are implemented based on single scale, which are not able to discover potential knowledge in data.This paper carried out a study of methods on universal multi-scale clustering with the introduction of granular computing, for the purpose of multilayer and multi-angle of data analysis and single-mining-multiple-using.First of all, this paper described knowledge related to granular computing.Then, it proposed an algorithm called UAMC, with clusters as granularity and clustering centers as feature of granularity to scale conversion, obtaining know-ledge of large scale based on mosaic upscaling scheme, for fear of resource waste due to secondly mining.At last, experimental results on datasets from UCI and H province indicate that UAMC algorithm outperforms benchmark algorithms such as K-means in accuracy.Meanwhile, UAMC algorithm is verified to be effective and feasible through the experiments.
英文关键词 multi-scale; granular computing; information granularity; mosaic upscaling scheme; multi-scale clustering
参考文献 查看稿件参考文献
  [1] 王慧贤, 靳惠佳, 王娇龙, 等. K-均值聚类引导的遥感影像多尺度分割优化方法[J] . 测绘学报, 2015, 44(5):526-532.
[2] 余莉, 甘淑, 袁希平, 等. 综合线面特征分布的点目标多尺度聚类方法[J] . 测绘学报, 2015, 44(10):1152-1159.
[3] 苏东海, 赵书良, 柳萌萌, 等. 基于加权向量提升的多尺度聚类挖掘算法[J] . 计算机科学, 2015, 42(4):263-267.
[4] 韩玉辉, 赵书良, 柳萌萌, 等. 多尺度聚类挖掘算法[J] . 计算机科学, 2016, 43(8):244-248.
[5] Lim H W, Song J, Kurtz N. Seismic reliability assessment of lifeline networks using clustering based multi-scale approach[J] . Earthquake Engineering & Structural Dynamics, 2015, 44(3):355-369.
[6] Saffarzadeh V M, Osareh A, Shadgar B. Vessel segmentation in retinal images using multi-scale line operator and K-means clustering[J] . Journal of Medical Signals & Sensors, 2014, 4(2):122-129.
[7] Aljosa O, Alexander H, Francis E, et al. Multi-scale object candidates for generic object tracking in street scenes[C] //Proc of IEEE International Conference on Robotics and Automation. 2016:3180-3187.
[8] 苗夺谦, 王国胤, 刘清, 等. 粒计算:过去、现在与展望[M] . 北京:科学出版社, 2007.
[9] Zadeh L A. Some reflections on soft computing, granular computing and their roles in the conception, design and utilization of information/intelligent systems[J] . Soft Computing, 1998, 2(1):23-25.
[10] Yao Yiyu, Deng Xiaofei. A granular computing paradigm for concept learning[M] // Emerging Paradigms in Machine Learning. Berlin:Springer, 2013:307-326.
[11] Wang Jianghao, Ge Yong, Song Yongze, et al. A geostatistical approach to upscale soil moisture with unequal precision observations[J] . IEEE Geoscience & Remote Sensing Letters, 2014, 11(12):2125-2129.
[12] Wu Jianghua, Zhao Pengxiang, Nigel R, et al. Spatial scaling links the information across scales:a review of methodologies used in regional eco-hydrological modeling[J] . Advance in Earth Science, 2008, 23(2):129-141.
[13] Li Jing, Yao K, Marcus B, et al. Comparing upscaling algorithms from HD to ultra HD by evaluating preference of experience[C] //Proc of the 6th International Workshop on Quality of Multimedia Experience. 2014:208-213.
[14] Andrew W, Nicolas E, Craig T J. A frequency-domain algorithm to upscale ambisonic sound scenes[C] //Proc of IEEE International Conference on Acoustics, Speech and Signal Processing. 2012:385-388.
[15] Yao Yiyu. Notes on rough set approximations and associated measures[J] . Journal of Zhejiang Ocean University:Natural Science, 2010, 29(5):399-410.
[16] 高新波. 模糊聚类分析及其应用[M] . 西安:西安电子科技大学出版社, 2004:42-46.
[17] Teuvo K. Self-organization and associative memory[M] . Berlin:Springer-Verlag, 1984.
[18] Chen Wenyen, Song Yangqiu, Bai Hongjie, et al. Parallel spectral clustering in distributed systems[J] . IEEE Trans on Pattern Analysis & Machine Intelligence, 2011, 33(3):568-586.
[19] Alexander S, Joydeep G. Cluster ensembles:a knowledge reuse framework for combining multiple partitions[J] . Journal of Machine Learning Research, 2002, 3(12):583-617.
收稿日期 2016/9/14
修回日期 2016/10/24
页码 362-366
中图分类号 TP391
文献标志码 A