Smartphones can collect considerable context data about the user, ranging from apps used to places visited. Frequent user patterns discovered from longitudinal, multi-modal context data could help personalize and improve overall user experience. Our long term goal is to develop novel middleware and algorithms to efficiently mine user behavior patterns entirely on the phone by utilizing idle processor cycles. Mining patterns on the mobile device provides better privacy guarantees to users, and reduces dependency on cloud connectivity. As an important step in this direction, we develop a novel general-purpose service called MobileMiner that runs on the phone and discovers frequent co-occurrence patterns indicating which context events frequently occur together. Using longitudinal context data collected from 106 users over 1--3 months, we show that MobileMiner efficiently generates patterns using limited phone resources. Further, we find interesting behavior patterns for individual users and across users, ranging from calling patterns to place visitation patterns. Finally, we show how our co-occurrence patterns can be used by developers to improve the phone UI for launching apps or calling contacts.

User interests and behavior will play a key role in the design of future mobile networks. In this paper, we introduce a novel technique for the modeling of mobile users interests based on their online activity and mobility. In this study, we conduct domain-specific and location-based analysis and modeling of mobile user interests based on the amount of their online time. Using KS test, we show that domain-specific and location-based models provide more accuracy than a generic model for mobile users interests. The provided models can be applied for design and evaluation of a myriad of interest-based applications and services for future mobile global Internet.

Users behavior and interests will play a central role in future mobile networks. We introduce a systematic method for large-scale multi-dimensional analysis of online activity for thousands of mobile users across 79 buildings over 100 web domains. We propose a modeling approach based on self-organizing maps for discovering, organizing and visualizing different mobile users' trends from billions of WLAN and netflow records. We find surprisingly that users' trends based on domains or locations can be modeled using a self-organizing map with clearly distinct characteristics. This is the first study to acquire such detailed results for wireless users Internet access patterns.

In very close future, human interests and behavior will play a central role in design of mobile networks. Thus, simulation of user behaviors is imperative for the design and evaluation of future mobile networks. However, multi-dimensionality of human interests makes it difficult for us to provide realistic simulations. In this paper, we address challenges in this regard and propose a multivariate technique based on Gaussian mixture models as the first step for simulation of mobile users' interests considering website visitations. We also introduce an evaluation technique for measuring the quality of high-dimensional simulation output. Using our collected dataset including billions of WLAN netflow records for 100 web domains at 79 buildings, we show that our technique not only keeps the characteristics of hidden behavioral groups, but also is flexible enough to approximate the real dataset with given required accuracy.

User online behavior and interests will play a central role in future mobile networks. We introduce a systematic method for large-scale multi-dimensional modeling and analysis of online activity and mobility for thousands of mobile users across 79 buildings over a variety of web domains. We propose a modeling approach based on kind of neural-networks, called self-organizing maps (SOM), for discovering, organizing and visualizing different mobile users' trends from billions of WLAN records. We find surprisingly that users' trends based on domains and locations can be accurately modeled using a self-organizing map with clearly distinct characteristics. We also find many non-trivial correlations between different types of web domains and locations.

Human behavior and interests will play a central role in future mobile networks. We introduce a systematic method for large-scale multi-dimensional analysis of online activity for thousands of mobile users over 100 web domains. We propose a modeling approach based on self-organizing maps for discovering, organizing and visualizing different mobile users' trends from billions of WLAN and netflow records. We find surprisingly that users' trends can be modeled using a self-organizing map with clearly distinct characteristics while similar domains are modeled by neighboring nodes. This is the first study to acquire such detailed results for mobile Internet usage.

Design and simulation of future mobile networks will center around human interests and behavior. We propose a design paradigm for mobile networks driven by realistic models of users' on-line behavior, based on mining of billions of wireless-LAN records. We introduce a systematic method for large-scale multi-dimensional co-clustering of web activity for thousands of mobile users at 79 locations. We find surprisingly that users can be consistently modeled using ten clusters with disjoint profiles. Access patterns from multiple locations show differential user behavior. This is the first study to obtain such detailed results for mobile Internet usage.