Abstract
Summary form only given. Cellphones have been adopted faster than any other technology in human history. As of 2010, the number of cellphone subscribers exceeds 4.5 billion. Recently cellphones (more accurately smartphones) have attracted the attention of networking and ubiquitous computing research communities due to their potential for acting as sensor nodes for city-wide sensing applications. In this talk, I will describe two pieces of my work for employing the smartphone as the mobile sensor. The location information captured in the cellphone are in terms of low level data units, and it is difficult to use these logs for building high level context-based search and collaborative sensing applications. In this first piece of work, we studied the problem of discovering spatiotemporal mobility patterns and mobility profiles from cellphone based location logs. In order to capture the mobility behaviors of cellphone users at a level of abstraction suitable for reasoning and analysis, we introduced formal definitions for the concepts of mobility path (denoting a user's travel from one end-location to another), mobility pattern (denoting a popular travel for the user supported by his mobility paths), and mobility profile (providing a synopsis of a user's mobility behavior by integrating the frequent mobility patterns, contextual data, and time distribution data for the user). Our results from this Mobility Profiler project yield important lessons for employing the smartphone as a mobile sensor. From our experiments on the Reality Mining dataset, we find that users spend approximately 85% of their time in 3-5 favorite locations, such as home, work, shopping. The remaining 15% of user's time is spent in locations that each appear with less than 1% of total time. In the second work, we focused on the practical issues for deploying a crowdsourced sensing system. Despite the ubiquitous availability of the sensor and smartphone devices, the-state-of-the-art falls short of the ubiquitous computing vision. We argue that the reason for this gap is the lack of an infrastructure to task/utilize these devices for collaboration. We proposed that Twitter can provide an “open” publish-subscribe infrastructure for sensors and smartphones, and pave the way for crowdsourced sensing and collaboration applications. We designed and implemented a crowdsourced sensing system over Twitter, and deployed a crowdsourced weather radar and noise mapping application using our system. Our results from real-world Twitter experiments show promise for the feasibility of this approach.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.