skip to main content
10.1145/2462456.2464457acmconferencesArticle/Chapter ViewAbstractPublication PagesmobisysConference Proceedingsconference-collections
research-article

Leveraging graphical models to improve accuracy and reduce privacy risks of mobile sensing

Published: 25 June 2013 Publication History

Abstract

The proliferation of sensors on mobile phones and wearables has led to a plethora of context classifiers designed to sense the individual's context. We argue that a key missing piece in mobile inference is a layer that fuses the outputs of several classifiers to learn deeper insights into an individual's habitual patterns and associated correlations between contexts, thereby enabling new systems optimizations and opportunities. In this paper, we design CQue, a dynamic bayesian network that operates over classifiers for individual contexts, observes relations across these outputs across time, and identifies opportunities for improving energy-efficiency and accuracy by taking advantage of relations. In addition, such a layer provides insights into privacy leakage that might occur when seemingly innocuous user context revealed to different applications on a phone may be combined to reveal more information than originally intended. In terms of system architecture, our key contribution is a clean separation between the detection layer and the fusion layer, enabling classifiers to solely focus on detecting the context, and leverage temporal smoothing and fusion mechanisms to further boost performance by just connecting to our higher-level inference engine. To applications and users, CQue provides a query interface, allowing a) applications to obtain more accurate context results while remaining agnostic of what classifiers/sensors are used and when, and b) users to specify what contexts they wish to keep private, and only allow information that has low leakage with the private context to be revealed. We implemented CQue in Android, and our results show that CQue can i) improve activity classification accuracy up to 42%, ii) reduce energy consumption in classifying social, location and activity contexts with high accuracy(>90%) by reducing the number of required classifiers by at least 33%, and iii) effectively detect and suppress contexts that reveal private information.

References

[1]
Java bayes. http://www.cs.cmu.edu/~javabayes/.
[2]
L. Bao and S. S. Intille. Activity Recognition from User-Annotated Acceleration Data. Pervasive Computing, pages 1--17, 2004.
[3]
D. Chu, A. Deshpande, J. M. Hellerstein, and W. Hong. Approximate Data Collection in Sensor Networks using Probabilistic Models. In ICDE, page~48, 2006.
[4]
D. Chu, N. Lane, T. Lai, C. Pang, F. Li, X. Meng, Q. Guo, and F. Zhao. Balancing energy, latency and accuracy for mobile sensor data classification. In SenSys, pages 54--67, 2011.
[5]
A. Deshpande, C. Guestrin, W. Hong, and S. Madden. Exploiting correlated attributes in acquisitional query processing. In ICDE, pages 143--154, 2005.
[6]
A. Deshpande, C. Guestrin, S. Madden, J. Hellerstein, and W. Hong. Model-driven data acquisition in sensor networks. In VLDB, pages 588--599, 2004.
[7]
N. Friedman, K. Murphy, and S. Russell. Learning the Structure of Dynamic Probabilistic Networks. In UAI, pages 139--147, 1999.
[8]
M. Götz, S. Nath, and J. Gehrke. Maskit: privately releasing user context streams for personalized mobile applications. In SIGMOD, pages 289--300, 2012. ACM.
[9]
M. Hall, E. Frank, G. Holmes, B. Pfahringer, P. Reutemann, and I. H. Witten. The weka data mining software: An update. In SIGKDD Explorations, pages 10--18, 2009.
[10]
A. Krause and C. Guestrin. Near-optimal Nonmyopic Value of Information in Graphical Models. In UAI, pages 324--331, 2005.
[11]
J. Lester, T. Choudhury, N. Kern, G. Borriello, and B. Hannaford. A hybrid discriminative/generative approach for modeling human activities. In IJCAI, pages 766--772, 2005.
[12]
M. Li, D. Ganesan, and P. Shenoy. Presto: feedback-driven data management in sensor networks. In NSDI, page~23, 2006.
[13]
H. Lu, J. Yang, Z. Liu, N. D. Lane, T. Choudhury, and A. Campbell. The jigsaw continuous sensing engine for mobile phone applications. In SenSys, pages 71--84, 2010.
[14]
A. Meliou, C. Guestrin, and J. M. Hellerstein. Approximating sensor network queries using in-network summaries. In IPSN, pages 229--240. IEEE, 2009.
[15]
S. Nath. Ace: exploiting correlation for energy-efficient and continuous context sensing. In Proceedings of the 10th international conference on Mobile systems, applications, and services, MobiSys '12, pages 29--42, New York, NY, USA, 2012. ACM.
[16]
G. L. Nemhauser, L. A. Wolsey, and M. L. Fisher. An analysis of approximations for maximizing submodular set functions-I. Mathematical Programming, 14(1):265--294, Dec. 1978.
[17]
A. Parate and G. Miklau. A framework for safely publishing communication traces. In Proceedings of the 18th ACM conference on Information and knowledge management, CIKM '09, pages 1469--1472, New York, NY, USA, 2009. ACM.
[18]
J. Pearl. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Francisco, USA, 1988.
[19]
R. A. Popa, H. Balakrishnan, and A. J. Blumberg. Vpriv: protecting privacy in location-based vehicular services. In Proceedings of the 18th conference on USENIX security symposium, SSYM'09, pages 335--350, Berkeley, CA, USA, 2009. USENIX Association.
[20]
N. Ravi, N. Dandekar, P. Mysore, and M. L. Littman. Activity recognition from accelerometer data. In IAAI, pages 1541--1546, 2005.
[21]
S. J. Russell and P. Norvig. Artificial Intelligence: A Modern Approach. Prentice Hall, second edition, 2002.

Cited By

View all
  • (2021)Tracking and Behavior Augmented Activity Recognition for Multiple InhabitantsIEEE Transactions on Mobile Computing10.1109/TMC.2019.293638220:1(247-262)Online publication date: 1-Jan-2021
  • (2019)Privacy Preservation in Big Data From the Communication Perspective—A SurveyIEEE Communications Surveys & Tutorials10.1109/COMST.2018.286510721:1(753-778)Online publication date: Sep-2020
  • (2017)Analysis of privacy and utility tradeoffs in anonymized mobile context streamsIntelligent Data Analysis10.3233/IDA-17087021(S21-S39)Online publication date: 1-Apr-2017
  • Show More Cited By

Index Terms

  1. Leveraging graphical models to improve accuracy and reduce privacy risks of mobile sensing

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    MobiSys '13: Proceeding of the 11th annual international conference on Mobile systems, applications, and services
    June 2013
    568 pages
    ISBN:9781450316729
    DOI:10.1145/2462456
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

    Sponsors

    In-Cooperation

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 25 June 2013

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. continuous context-sensing
    2. energy-accuracy-privacy optimizations
    3. mobile computing

    Qualifiers

    • Research-article

    Conference

    MobiSys'13
    Sponsor:

    Acceptance Rates

    MobiSys '13 Paper Acceptance Rate 33 of 211 submissions, 16%;
    Overall Acceptance Rate 274 of 1,679 submissions, 16%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)6
    • Downloads (Last 6 weeks)0
    Reflects downloads up to 20 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2021)Tracking and Behavior Augmented Activity Recognition for Multiple InhabitantsIEEE Transactions on Mobile Computing10.1109/TMC.2019.293638220:1(247-262)Online publication date: 1-Jan-2021
    • (2019)Privacy Preservation in Big Data From the Communication Perspective—A SurveyIEEE Communications Surveys & Tutorials10.1109/COMST.2018.286510721:1(753-778)Online publication date: Sep-2020
    • (2017)Analysis of privacy and utility tradeoffs in anonymized mobile context streamsIntelligent Data Analysis10.3233/IDA-17087021(S21-S39)Online publication date: 1-Apr-2017
    • (2017)Location Anonymization With Considering Errors and Existence ProbabilityIEEE Transactions on Systems, Man, and Cybernetics: Systems10.1109/TSMC.2016.256492847:12(3207-3218)Online publication date: Dec-2017
    • (2017)PLP: Protecting Location Privacy Against Correlation Analyze Attack in CrowdsensingIEEE Transactions on Mobile Computing10.1109/TMC.2016.262473216:9(2588-2598)Online publication date: 1-Sep-2017
    • (2017)Detecting Eating and Smoking Behaviors Using SmartwatchesMobile Health10.1007/978-3-319-51394-2_10(175-201)Online publication date: 13-Jul-2017
    • (2016)Privacy Preservation for Context Sensing on SmartphoneIEEE/ACM Transactions on Networking (TON)10.1109/TNET.2015.251230124:6(3235-3247)Online publication date: 1-Dec-2016
    • (2016)Verification of User-Reported Context Claims with Context Correlation Model2016 13th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON)10.1109/SAHCN.2016.7733025(1-9)Online publication date: Jun-2016
    • (2016)Security, Privacy, and Incentive Provision for Mobile Crowd Sensing SystemsIEEE Internet of Things Journal10.1109/JIOT.2016.25607683:5(839-853)Online publication date: Oct-2016
    • (2016)CACE: Exploiting Behavioral Interactions for Improved Activity Recognition in Multi-inhabitant Smart Homes2016 IEEE 36th International Conference on Distributed Computing Systems (ICDCS)10.1109/ICDCS.2016.61(539-548)Online publication date: Jun-2016
    • Show More Cited By

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media