收稿日期: 2014-03-03
修回日期: 2014-03-28
网络出版日期: 2015-01-15
基金资助
教育部回国留学人员科研启动基金及中国科学院大学校长基金(Y0510IAYOO)资助
Mobile network access time statistical analysis and its application based on kernel method and Gaussian mixture model
Received date: 2014-03-03
Revised date: 2014-03-28
Online published: 2015-01-15
常楠 , 张三国 . 基于核方法和高斯混合模型的手机上网时长统计分析及应用[J]. 中国科学院大学学报, 2015 , 32(1) : 136 -139 . DOI: 10.7523/j.issn.2095-6134.2015.01.022
Based on kernel method and Gaussian mixture model, we analyze the distribution of the mobile network access time from a new view, the mobile model view. The analysis of real data suggests that the distribution of the mobile network has two peaks. We give some reasonable interpretations for such a phenomenon.
[1] Gokul C, Jan B, Daniel G P. Who's who with big-five: analyzing and classifying personality traits with smart-phones[C]//Proceedings of the 15th Annual International Symposium on Wearable Computers. 2011.
[2] Falaki H, Mahajan R, Kandula S, et al. Diversity in s-martphone usage[C]//Proceedings of the 8th Lnternational, Conference on Mobile Systems, Applications, and Services. 2010.
[3] Huang J, Xu Q, Tiwana B, et al. Anatomizing application performance differences on smartphones[C]//Proceedings of the 8th International Conference on Mobile Systems, Applications, and Services. 2010.
[4] Shafiq M Z, Ji L, Liu A X, et al. Characterizing and modeling internet traffic dynamics of cellular devices[C]//Proceedings of the ACM Sigmetrics Joint International Conference on Measurement and Modeling of Computer Systems. 2011.
[5] Li Q, Jeffrey S R. Nonparametric econometrics: theory and practice[M]. Princeton University Press,2011.
[6] Dempster A P, Laird N M, Rubin D B. Maximum likelihood from incomplete data via the EM algorithm[J]. Journal of the Royal Statistical Society. Series B (Methodological), 1977,39(1):1-38.
[7] Wu C F J. On the convergence properties of the EM algorithm[J]. Ann Statist,1983,11(1):95-103.
/
| 〈 |
|
〉 |
