Understanding network behavior patterns of bus Wi-Fi users using surfing data

Nowadays, more and more companies intend to combine public transport system with the mature Wi-Fi technology to bring more passengers value-added services during their travel. It is critical to mobile service market and city management by identify the user's behavior patterns. In this paper, the author firstly analyzes the time regularity of bus Wi-Fi network behavior. Then from the perspective of users and websites, analyzes the behavior features from the number of records, flow, website numbers and the number of users. Based on the results of those feature analysis, we get the most important 1000 websites and use the app classification method, extract 16 features, using TF-IDF to improve the clustering algorithm, successfully divide network behavior patterns into four categories. Finally, the author compares and analyzes the network behavior patterns in different scenarios.

[1]  Chao Li,et al.  Mobile Surfing Pattern Analysis over Time and Location on a Big Access Record , 2015, 2015 IEEE 12th Intl Conf on Ubiquitous Intelligence and Computing and 2015 IEEE 12th Intl Conf on Autonomic and Trusted Computing and 2015 IEEE 15th Intl Conf on Scalable Computing and Communications and Its Associated Workshops (UIC-ATC-ScalCom).

[2]  Luca Delgrossi,et al.  IEEE 802.11p: Towards an International Standard for Wireless Access in Vehicular Environments , 2008, VTC Spring 2008 - IEEE Vehicular Technology Conference.

[3]  Qiang Xu,et al.  Identifying diverse usage behaviors of smartphone apps , 2011, IMC '11.

[4]  Zhi-Li Zhang,et al.  Profiling internet backbone traffic: behavior models and applications , 2005, SIGCOMM '05.

[5]  Hiroshi Esaki,et al.  The impact of residential broadband traffic on Japanese ISP backbones , 2005, CCRV.

[6]  Suman Banerjee,et al.  Beyond deployments and testbeds: experiences with public usage on vehicular WiFi hotspots , 2012, MobiSys '12.

[7]  Suman Banerjee,et al.  MobiCom 2011 poster: AirTrack: locating non-WiFi interferers using commodity WiFi hardware , 2012, MOCO.

[8]  Murad S. Taqqu,et al.  On the Self-Similar Nature of Ethernet Traffic , 1993, SIGCOMM.

[9]  Hari Balakrishnan,et al.  Cabernet: A Content Delivery Network for Moving Vehicles , 2008 .

[10]  Virgílio A. F. Almeida,et al.  Characterizing broadband user behavior , 2004, NRBC '04.

[11]  Walter Willinger,et al.  On the Self-Similar Nature of Ethernet Traffic ( extended version ) , 1995 .

[12]  Suman Banerjee,et al.  Airshark: detecting non-WiFi RF devices using commodity WiFi hardware , 2011, IMC '11.