Yuanyuan Qiao

Characterizing User Behavior in Mobile Internet

Smart devices bring us the ubiquitous mobile accessing to Internet, making mobile Internet grow rapidly. Using the mobile traffic data collected at core metropolitan 2G and 3G networks of China over a week, this paper studies the mobile user behavior from three aspects: 1) data usage; 2) mobility pattern; and 3) application usage. We classify mobile users into different groups to study the resource consumption in mobile Internet. We observe that traffic heavy users and high mobility users tend to consume massive data and radio resources simultaneously. Both the data usage and the mobility pattern are closely related to the application access behavior of the users. Users can be clustered through their application usage behavior, and application categories can be identified by the ways to attract the users. Our analysis provides an comprehensive understanding of user behavior in mobile Internet, which may be used by network operators to design appropriate mechanisms in resource provision and mobility management for resource consumers based on different categories of applications.

Big Data Driven Hidden Markov Model Based Individual Mobility Prediction at Points of Interest

With the emergence of smartphones and location-based services, user mobility prediction has become a critical enabler for a wide range of applications, like location-based advertising, early warning systems, and citywide traffic planning. A number of techniques have been proposed to either conduct spatio-temporal mobility prediction or forecast the next-place. However, both produce diverse prediction performance for different users and display poor performance for some users. This paper focuses on investigating the effect of living habits on the models of spatio-temporal prediction and next-place prediction, and selects one from these two models for an individual to achieve effective mobility prediction at users’ points of interest. Based on the hidden Markov model (HMM), a spatio-temporal predictor and a next-place predictor are proposed. Living habits are analyzed in terms of entropy, upon which users are clustered into distinct groups. With large-scale factual mobile data captured from a big city, we compare the proposed HMM-based predictors with existing state-of-the-art predictors and apply them to different user groups. The results demonstrate the robust performance of the two proposed mobility predictors, which outperform the state of the art for various user groups.

Mobile big-data-driven rating framework: measuring the relationship between human mobility and app usage behavior

Smart devices bring us ubiquitous mobile access to the Internet, making it possible to surf the Internet in mobile environments. With the pervasiveness of mobile Internet, much evidence shows that human mobility has heavy impact on app usage behavior. However, the relationship between them has not been quantified in any form. In this article, a rating framework is presented to demonstrate the existence of their connection. The core idea of a rating framework selects the most significant mobility features that may influence app usage behavior. In particular, we focus on three aspects of human mobility in urban areas: individual mobility characteristics, location, and travel behavior, from both the crowd and individual points of view. At last, by using a limited number of selected mobility and time features, high forecast accuracy is achieved in terms of app usage behavior of crowds and individuals, which verifies the effectiveness of the rating framework.

Prediction of User Mobility Pattern on a Network Traffic Analysis Platform

The mobile Internet brings tremendous opportunities for researchers to analyze user mobility pattern, which is of great importance for Internet Service Providers (ISP) to provide better location-based services. This paper focuses on predicting user mobility patterns based on their different mobility characteristics. For that, we collect real-world data from Long Term Evolution (LTE) mobile network by a specially developed network traffic analysis platform followed by clustering the user into stationary one or mobile one with a location-entropy-based method for distinguishing groups with distinct mobility characteristics, and then we present the tailored Intelligent Time Division (ITD) method and Time-Based Markov (TBM) predictor for the location prediction of stationary and mobile users respectively. Extensive experiments demonstrate the effectiveness and better performance of our proposed methods compared with the baselines, as well as the adaptabilities of different predictors according to individuals mobility characteristics.

A hybrid Markov-based model for human mobility prediction

Abstract Human mobility behavior is far from random, and its indicators follow non-Gaussian distributions. Predicting human mobility has the potential to enhance location-based services, intelligent transportation systems, urban computing, and so forth. In this paper, we focus on improving the prediction accuracy of non-Gaussian mobility data by constructing a hybrid Markov-based model, which takes the non-Gaussian and spatio-temporal characteristics of real human mobility data into account. More specifically, we (1) estimate the order of the Markov chain predictor by adapting it to the length of frequent individual mobility patterns, instead of using a fixed order, (2) consider the time distribution of mobility patterns occurrences when calculating the transition probability for the next location, and (3) employ the prediction results of users with similar trajectories if the recent context has not been previously seen. We have conducted extensive experiments on real human trajectories collected during 21 days from 3474 individuals in an urban Long Term Evolution (LTE) network, and the results demonstrate that the proposed model for non-Gaussian mobility data can help predicting people’s future movements with more than 56% accuracy.

Oscillation Resolution for Massive Cell Phone Traffic Data

Cellular towers capture logs of mobile subscribers whenever their devices connect to the network. When the logs show data traffic at a cell tower generated by a device, it reveals that this device is close to the tower. The logs can then be used to trace the locations of mobile subscribers for different applications, such as studying customer behaviour, improving location-based services, or helping urban planning. However, the logs often suffer from an oscillation phenomenon. Oscillations may happen when a device, even when not moving, does not only connect to the nearest cell tower, but is instead unpredictably switching between multiple cell towers because of random noise, load balancing, or simply dynamic changes in signal strength. Detecting and removing oscillations are a challenge when analyzing location data collected from the cellular network. In this paper, we propose an algorithm called SOL (Stable, Oscillation, Leap periods) aimed at discovering and reducing oscillations in the collected logs. We apply our algorithm on real datasets which contain about 18.9~TB of traffic logs generated by more than 3~million mobile subscribers covering about 21000 cell towers and collected during 27~days from both GSM and UMTS networks in northern China. Experimental results demonstrate the ability and effectiveness of SOL to reduce oscillations in cellular network logs.

Characterizing and modeling of large-scale traffic in mobile network

Recently, mobile Internet gained a strong momentum of development, which has led to increasing demand on mobile network traffic characterization and modeling. A good model of mobile network traffic can be used to make accurate prediction regarding various performance metrics. Based on the network trace collected from network backbone, our paper studies mobile network traffic characteristics in terms of the flow arrival numbers and flow connection duration. Basically, we employ the Poisson regression from Generalized Linear Model with time window clustering so as to approximate a time-dependent Poisson Process to the flow arrival process. Our analytical results demonstrate the accuracy of the adopted approach. In addition, through approximating the Phase Type distribution to the heavy-tailed distribution, our paper also models the flow connection duration. The obtained results can help us get a comprehensive understanding of the network performance, in accordance with which the resource usage may be optimized, e.g., we can expand network bandwidth or increase the buffer size when the network arrival is high.

Measuring Geospatial Properties: Relating Online Content Browsing Behaviors to Users’ Points of Interest

With the growth of the Mobile Internet, people have become active in both the online and offline worlds. Investigating the relationships between users’ online and offline behaviors is critical for personalization and content caching, as well as improving urban planning. Although some studies have measured the spatial properties of online social relationships, there have been few in-depth investigations of the relationships between users’ online content browsing behaviors and their real-life locations. This paper provides the first insight into the geospatial properties of online content browsing behaviors from the perspectives of both geographical regions and individual users. We first analyze the online browsing patterns across geographical regions. Then, a multilayer-network-based model is presented to discover how inter-user distances affect the distributions of users with similar online browsing interests. Drawing upon results from a comprehensive study of users of three popular online content services in a metropolitan city in China, we achieve a broad understanding of the general and specific geospatial properties of users’ various preferences. Specifically, users with similar online browsing interests exhibit, to a large extent, strong geographic correlations, and different services exhibit distinct geospatial properties in terms of their usage patterns. The results of this work can potentially be exploited to improve a vast number of applications.

A Human-in-the-Loop Architecture for Mobile Network: From the View of Large Scale Mobile Data Traffic

Unlike other radio signal services, 5G is anticipated to play a huge role in offering services to heterogeneous networks, technologies, and devices operating in different geographic regions to fulfill the high expectation of users with relatively low energy consumption, which implies the necessity for moving from a system-centric design to a more user- or even human- and data- centric design paradigm “to keep the human in the loop” in future network. It drives us to design a system with capacity to allocate network resource dynamically according to feedback from users. This paper presents a Human-In-The-Loop architecture for mobile network that discovers users’ needs on network resource by understanding data traffic usage behavior of users. Based on real data traffic of mobile network, we analyze data traffic patterns of heavy and normal users from the view of online browsing behavior and urban functional area to explain how and why the data traffic is consumed. Then we propose a Latent Dirichlet Allocation model based solution to correlate data traffic, user behavior, and urban ecology to gain deep insights into spatio-temporal dynamic of data traffic usage behavior for different groups of users. Drawing upon results from a comprehensive study of users in a metropolitan city in China, we achieve a broad understanding about the difference of data traffic usage patterns of heavy and normal user: (1) besides the amount of generated data traffic, two groups of users can be easily distinguished by usage behavior of limited number of applications at midnight, (2) the functions of locations have huge impact on data usage patterns of users, which implies that urban ecology will shape users’ online behavior. The results of this work can potentially be exploited to help to allocate network resource, improve Quality of Experience according to users’ needs, and even design the future network.

A Survey on Machine Learning-Based Mobile Big Data Analysis: Challenges and Applications

This paper attempts to identify the requirement and the development of machine learning-based mobile big data (MBD) analysis through discussing the insights of challenges in the mobile big data. Furthermore, it reviews the state-of-the-art applications of data analysis in the area of MBD. Firstly, we introduce the development of MBD. Secondly, the frequently applied data analysis methods are reviewed. Three typical applications of MBD analysis, namely, wireless channel modeling, human online and offline behavior analysis, and speech recognition in the Internet of Vehicles, are introduced, respectively. Finally, we summarize the main challenges and future development directions of mobile big data analysis.