Fengli Xu

Understanding Mobile Traffic Patterns of Large Scale Cellular Towers in Urban Environment

Understanding mobile traffic patterns of large scale cellular towers in urban environment is extremely valuable for Internet service providers, mobile users, and government managers of modern metropolis. This paper aims at extracting and modeling the traffic patterns of large scale towers deployed in a metropolitan city. To achieve this goal, we need to address several challenges, including lack of appropriate tools for processing large scale traffic measurement data, unknown traffic patterns, as well as handling complicated factors of urban ecology and human behaviors that affect traffic patterns. Our core contribution is a powerful model which combines three dimensional information (time, locations of towers, and traffic frequency spectrum) to extract and model the traffic patterns of thousands of cellular towers. Our empirical analysis reveals the following important observations. First, only five basic time-domain traffic patterns exist among the 9,600 cellular towers. Second, each of the extracted traffic pattern maps to one type of geographical locations related to urban ecology, including residential area, business district, transport, entertainment, and comprehensive area. Third, our frequency domain traffic spectrum analysis suggests that the traffic of any tower among the 9,600 can be constructed using a linear combination of four primary components corresponding to human activity behaviors. We believe that the proposed traffic patterns extraction and modeling methodology, combined with the empirical analysis on the mobile traffic, pave the way toward a deep understanding of the traffic patterns of large scale cellular towers in modern metropolis.

On the Understanding of Interdependency of Mobile App Usage

With the rising popularity of smartphones and the rapid growth of mobile applications, understanding the app usage behavior of mobile users is of growing importance for both app designers and service providers. Different from previous studies mining the correlation between apps and physical world factors, e.g. location, time, etc., in this paper we focus on the interdependency among apps and try to address a series of research problems: what apps are frequently used together? What are the relations between apps (strengthen or undermine the use of each other) belonged to each category? To answer these questions, we employ the frequent pattern mining algorithm to a large-scale real-world dataset, which includes more than 1.7 million users and 5 billion app usage logs, and find out frequent app-sets and association rules with interesting insights. These results are usefulness in app marketing for service providers and in understanding different mobile users for app designers.

Smartphone App Usage Prediction Using Points of Interest

In this paper we present the first population-level, city-scale analysis of application usage on smartphones. Using deep packet inspection at the network operator level, we obtained a geo-tagged dataset with more than 6 million unique devices that launched more than 10,000 unique applications across the city of Shanghai over one week. We develop a technique that leverages transfer learning to predict which applications are most popular and estimate the whole usage distribution based on the Point of Interest (POI) information of that particular location. We demonstrate that our technique has an 83.0% hitrate in successfully identifying the top five popular applications, and a 0.15 RMSE when estimating usage with just 10% sampled sparse data. It outperforms by about 25.7% over the existing state-of-the-art approaches. Our findings pave the way for predicting which apps are relevant to a user given their current location, and which applications are popular where. The implications of our findings are broad: it enables a range of systems to benefit from such timely predictions, including operating systems, network operators, appstores, advertisers, and service providers.

A Bimodal Model to Estimate Dynamic Metropolitan Population by Mobile Phone Data

Accurate, real-time and fine-spatial population distribution is crucial for urban planning, government management, and advertisement promotion. Limited by technics and tools, we rely on the census to obtain this information in the past, which is coarse and costly. The popularity of mobile phones gives us a new opportunity to investigate population estimation. However, real-time and accurate population estimation is still a challenging problem because of the coarse localization and complicated user behaviors. With the help of the passively collected human mobility and locations from the mobile networks including call detail records and mobility management signals, we develop a bimodal model beyond the prior work to better estimate real-time population distribution at metropolitan scales. We discuss how the estimation interval, space granularity, and data type will influence the estimation accuracy, and find the data collected from the mobility management signals with the 30 min estimation interval performs better which reduces the population estimation error by 30% in terms of Root Mean Square Error (RMSE). These results show us the great potential of using bimodal model and mobile phone data to estimate real-time population distribution.

A New Privacy Breach: User Trajectory Recovery From Aggregated Mobility Data

Human mobility data have been ubiquitously collected through cellular networks and mobile applications, and publicly released for academic research and commercial purposes for the last decade. Since releasing individual’s mobility records usually gives rise to privacy issues, data sets owners tend to only publish aggregated mobility data, such as the number of users covered by a cellular tower at a specific timestamp, which is believed to be sufficient for preserving users’ privacy. However, in this paper, we argue and prove that even publishing aggregated mobility data could lead to privacy breach in individuals’ trajectories. We develop an attack system that is able to exploit the uniqueness and regularity of human mobility to recover individual’s trajectories from the aggregated mobility data without any prior knowledge. By conducting experiments on two real-world data sets collected from both the mobile application and cellular network, we reveal that the attack system is able to recover users’ trajectories with an accuracy of about 73%~91% at the scale of thousands to ten thousands of mobile users, which indicates severe privacy leakage in such data sets. Our extensive analysis also reveals that by generalization and perturbation, this kind of privacy leakage can only be mitigated. Through the investigation on aggregated mobility data, this paper recognizes a novel privacy problem in publishing statistic data, which appeals for immediate attentions from both the academy and industry.