IEEE Transactions on Mobile Computing

IEEE Transactions on Mobile Computing (TMC) is a scholarly archival journal published monthly that focuses on the key technical issues related to Mobile Computing. It is the intent of TMC to publish mature works of research, typically those that have appeared in part in conferences. Furthermore, it is the intent ofTMC to focus on issues at the link-layer and above in wireless communications, and to focus only on topics explicitly or plausibly related to mobile systems. Read the full scope of TMC


From the June 2015 issue

Boosting Mobile Apps under Imbalanced Sensing Data

By Xinglin Zhang, Zheng Yang, Longfei Shangguan, Yunhao Liu, and Lei Chen

featured article thumbnailMobile sensing apps have proliferated rapidly over the recent years. Most of them rely on inference components heavily for detecting interesting activities or contexts. Existing work implements inference components using traditional models designed for balanced data sets, where the sizes of interesting (positive) and non-interesting (negative) data are comparable. Practically, however, the positive and negative sensing data are highly imbalanced. For example, a single daily activity such as bicycling or driving usually occupies a small portion of time, resulting in rare positive instances. Under this circumstance, the trained models based on imbalanced data tend to mislabel positive ones as negative. In this paper, we propose a new inference framework SLIM based on several machine learning techniques in order to accommodate the imbalanced nature of sensing data. Especially, guided under-sampling is employed to obtain balanced labelled subsets, followed by a similarity-based sampling that draws massive unlabelled data to enhance training. To the best of our knowledge, SLIM is the first model that considers data imbalance in mobile sensing. We prototype two sensing apps and the experimental results show that SLIM achieves higher recall (activity recognition rate) while maintaining the precision compared with five classical models. In terms of the overall recall and precision, SLIM is around $12$ percent better than the compared solutions on average.

download PDF View the PDF of this article    csdl View this issue in the digital library


Editorials and Announcements

Announcements

  • According to Thomson Reuters' 2013 Journal Citation Report, TMC has an impact factor of 2.912.
  • Get Your Journals as eBooks for Free
  • We are pleased to announce that Prasant Mohapatra, the Tim Bucher Family Endowed Chair in the Computer Science Department at the University of California, Davis, has been named the new Editor-in-Chief of the IEEE Transactions on Mobile Computing starting in 2014.

Editorials


Reviewers List


Annual Index


Access recently published TMC articles

RSS Subscribe to the RSS feed of latest TMC content added to the digital library.

Mail Sign up for the Transactions Connection newsletter.


Listen to the OnlinePlus podcast: Computer Society Publishing—two more titles migrate to OnlinePlus™ in 2012.

In this podcast, VP of Publications, David Alan Grier talks about Transactions on Mobile Computing and Transactions on Parallel and Distributed Systems migrating to OnlinePlus™.

TMC is a joint publication of the:

IEEE Computer SocietyIEEE Circuits and Systems Society IEEE Comunications Society IEEE Signal Processing Society

 

TMC is published in cooperation with: IEEE Electromagnetic Compatibility Society, IEEE Engineering in Medicine and Biology Society, IEEE Technology Management Council, IEEE Information Theory Society, IEEE Instrumentation and Measurement Society, IEEE Power & Energy Society, IEEE Robotics and Automation Society, and IEEE Systems, Man, and Cybernetics Society

TMC is indexed in ISI

Computing Now
.