Min Mun
Deborah Estrin
ABSTRACT
PEIR, the Personal Environmental Impact Report, is a participatory sensing application that uses location data sampled from everyday mobile phones to calculate personalized estimates of environmental impact and exposure. It is an example of an important class of emerging mobile systems that combine the distributed processing capacity of the web with the personal reach of mobile technology. This paper documents and evaluates the running PEIR system, which includes mobile handset based GPS location data collection, and server-side processing stages such as HMM-based activity classification (to determine transportation mode); automatic location data segmentation into "trips''; lookup of traffic, weather, and other context data needed by the models; and environmental impact and exposure calculation using efficient implementations of established models. Additionally, we describe the user interface components of PEIR and present usage statistics from a two month snapshot of system use. The paper also outlines new algorithmic components developed based on experience with the system and undergoing testing for integration into PEIR, including: new map-matching and GSM-augmented activity classification techniques, and a selective hiding mechanism that generates believable proxy traces for times a user does not want their real location revealed.
- J. Burke, D. Estrin, M. Hansen, A. Parker, N. Ramanathan, S. Reddy, and M.B. Srivastava. Participatory sensing. In ACM Sensys WSW Workshop, 2006.Google Scholar
- Ecorio. http://ecorio.org, 2008.Google Scholar
- Carbondiem. http://carbonhero.com, 2008.Google Scholar
- Ubigreen. http://dub.washington.edu/ubigreen, 2008.Google Scholar
- E. Moretti J. Currie, S. DellaVigna and V. Pathania. The effect of fast food restaurants on obesity. Working Paper 14721, National Bureau of Economic Research, February 2009.Google Scholar
- CA. Pope III, M. Ezzati, DW. Dockery. Fine-Particulate Air Pollution and Life Expectancy in the United States. New England Journal of Medicine, 360(4):376--386, 2009.Google ScholarCross Ref
- K. Shilton, J. Burke, D. Estrin, M. Hansen, and M. Srivastava. Participatory Privacy in Urban Sensing. MODUS, 2008.Google Scholar
- K. Shilton, J. Burke, D. Estrin, and M. Hansen. Privacy and Participation in Urban Sensing. Interaction, 21:235--272, 2008.Google Scholar
- K. Shilton, J. Burke, D. Estrin, M. Hansen, and M. Srivastava. Achieving Participatory Privacy Regulation: Guidelines for Urban Sensing. CENS, UCLA, 2008.Google Scholar
- Gpsbabel. http://gpsbabel.sourceforge.net, 2008.Google Scholar
- A. Joki, J. Burke, and D. Estrin. Campaignr-a framework for participatory data collection on mobile phones. Technical report, CENS, UCLA, 2007.Google Scholar
- Nokia nokoscope. http://alpha.nokoscope.com, 2008.Google Scholar
- Postgis. http://postgis.refractions.net, 2008.Google Scholar
- Wordpress. http://wordpress.org, 2008.Google Scholar
- Modest maps. http://modestmaps.com, 2008.Google Scholar
- D. J. Patterson, L. Liao, D. Fox, and H. Kautz. Inferring High-Level Behavior from Low-Level Sensors. Lecture Notes in Computer Science, pages 73--89, 2003.Google Scholar
- L. Liao, D.J. Patterson, D. Fox, and H. Kautz. Learning and inferring transportation routines. Artificial Intelligence, 171(5-6):311--331, 2007. Google ScholarDigital Library
- L. Liao, D. Fox, and H. Kautz. Extracting Places and Activities from GPS Traces Using Hierarchical Conditional Random Fields. The International Journal of Robotics Research, 26(1):119, 2007. Google ScholarDigital Library
- L. Liao, D. Fox, and H. Kautz. Location-based activity recognition using relational Markov networks. In Proc. of the International Joint Conference on Artificial Intelligence (IJCAI), 2005. Google ScholarDigital Library
- M.A. Quddus, W.Y. Ochieng, and R.B. Noland. Current map-matching algorithms for transport applications: State-of-the art and future research directions. Transportation Research Part C, 15(5):312--328, 2007.Google ScholarCross Ref
- LR Rabiner. A tutorial on hidden Markov models and selected applications inspeech recognition. Proceedings of the IEEE, 77(2):257--286, 1989.Google ScholarDigital Library
- G. Rigoll, A. Kosmala, and S. Eickeler. High Performance Real-Time Gesture Recognition Using Hidden Markov Models. LNCS, pages 69--80, 1998.Google ScholarCross Ref
- GD Forney Jr. The viterbi algorithm. Proceedings of the IEEE, 61(3):268--278, 1973.Google ScholarCross Ref
- Google maps with my location. http://google.com/mobile/gmm/mylocation/, 2008.Google Scholar
- I. Anderson and H. Muller. Practical activity recognition using GSM data. Technical report, CSTR-06-016, Computer Science, University of Bristol, 2006.Google Scholar
- T. Sohn, A. Varshavsky, A. LaMarca, M.Y. Chen, T. Choudhury, I. Smith, S. Consolvo, J. Hightower, W.G. Griswold, and E. de Lara. Mobility Detection Using Everyday GSM Traces. LNCS, 4206:212, 2006. Google ScholarDigital Library
- 64 million smart phones shipped worldwide in 2006. http://canalys.com/pr/2007/r2007024.htm, 2006.Google Scholar
- J.R. Quinlan. C4. 5: Programs for Machine Learning. Morgan Kaufmann, 1993. Google ScholarDigital Library
- S. Consolvo, D.W. McDonald, T. Toscos, M.Y. Chen, J. Froehlich, B. Harrison, P. Klasnja, A. LaMarca, L. LeGrand, R. Libby, et al. Activity sensing in the wild: a field trial of ubifit garden. 2008.Google Scholar
- Y. Zheng, L. Liu, L. Wang, and X. Xie. Learning transportation mode from raw gps data for geographic applications on the web. 2008.Google Scholar
- S. Reddy, J. Burke, D. Estrin, M. Hansen, and M. Srivastava. Determining Transportation Mode On Mobile Phones.Google Scholar
- E. Miluzzo, N.D. Lane, S.B. Eisenman, and A.T. Campbell. CenceMe-Injecting Sensing Presence into Social Networking Applications. LNCS, 4793:1, 2007. Google ScholarDigital Library
- M. Mun, D. Estrin, J. Burke, and M. Hansen. Parsimonious Mobility Classification using GSM and WiFi Traces, 2008.Google Scholar
- ESRI. ArcGIS 8. ESRI, Redlands, CA.Google Scholar
- La county department of public health facility list. http://publichealth.lacounty.gov/rating/, 2008.Google Scholar
- MF Barth, PA Miller, and AE MacDonald. MADIS: The Meteorological Assimilation Data Ingest System. In Symp. on Observations, Data Assimilation, and Probabilistic Prediction, pages 20--25, 2002.Google Scholar
- U.s. census bureau zip code tabulation areas. http://census.gov/geo/ZCTA/zcta.html, 2008.Google Scholar
- Southern california association of governments traffic flow model. http://scag.ca.gov, 2008.Google Scholar
- CAR. Board. EMFAC: Emissions Factor Model, 2000.Google Scholar
- C.J. Stone, M. Hansen, C. Kooperberg, and Y.K. Truong. Polynomial splines and their tensor products in extended linear modeling. Ann. Statist, 1997.Google Scholar
- R. Ihaka and R. Gentleman. R: A Language for Data Analysis and Graphics. Journal of Computational Graphical Statistics, 5:299--314, 1996.Google ScholarCross Ref
- S. Amin, S. Andrews, S. Apte, J. Arnold, J. Ban, M. Benko, A.M. Bayen, B. Chiou, C. Claudel, C. Claudel, et al. Mobile century-using GPS mobile phones as traffic sensors: a field experiment. In World congress on ITS, pages 16--20, 2008.Google Scholar
- P. Ong, M. Graham, and D. Houston. Policy and Programmatic Importance of Spatial Alignment of Data Sources, 2006.Google Scholar
- D.J. Weitzner, H Abelson, T. Berners-Lee, J. Feigenbaum, J. Hendler, and G.J. Sussman. Information Accountability. Comm. of the ACM, 51(6):82--87, 2008. Google ScholarDigital Library
- H. Nissenbaum. Protecting Privacy in an Information Age: The Problem of Privacy in Public. Law and Philosophy, 17(5):559--596, 1998.Google Scholar
- J.E. COHEN. Privacy, Visibility, Transparency, and Exposure. Univ. of Chicago Law Review, 75(1), 2008.Google Scholar
- L. Palen and P. Dourish. Unpacking Privacy for a Networked World. In CHI'03, 2003. Google ScholarDigital Library
- R. Agrawal and R. Srikant. Privacy-preserving data mining. ACM SIGMOD Record, 29(2):439--450, 2000. Google ScholarDigital Library
- J. Krumm. Inference Attacks on Location Tracks. Lecture Notes in Computer Science, 4480:127, 2007. Google ScholarDigital Library
- L. Bannon. Forgetting as a feature, not a bug: the duality of memory and implications for ubiquitous computing. CoDesign, 2(1):3--15, 2006.Google ScholarCross Ref
- J.F. Blanchette and D.G. Johnson. Data Retention and the Panoptic Society: The Social Benefits of Forgetfulness. The Information Society, 18(1):33--45, 2002.Google ScholarCross Ref
- V. Mayer-Schoenberger. Useful Void: The Art of Forgetting in the Age of Ubiquitous Computing. 2007.Google Scholar
- R. Perlman. The Ephemerizer: Making Data Disappear. Info. System Security, 1(1):51--68, 2005.Google Scholar
Index Terms
- PEIR, the personal environmental impact report, as a platform for participatory sensing systems research
Recommendations
A Mobile Platform for Managing Mobile MapReduce Participatory Sensing Data
SAINT '12: Proceedings of the 2012 IEEE/IPSJ 12th International Symposium on Applications and the InternetThe proliferation of powerful, programmable mobile devices along with the availability of wide-area connectivity has created opportunities for participatory sensing applications where users sense and share location, motion and acoustic data in a network ...
Participatory sensing: applications and architecture
MobiSys '10: Proceedings of the 8th international conference on Mobile systems, applications, and servicesParticipatory sensing is the process whereby individuals and communities use ever-more-capable mobile phones and cloud services to collect and analyze systematic data for use in discovery. The convergence of technology and analytical innovation with a ...
Participatory sensing based traffic condition monitoring using horn detection
SAC '13: Proceedings of the 28th Annual ACM Symposium on Applied ComputingRate of vehicular horn is an important parameter to estimate the traffic congestion of a street in an urban area in developing nations. In this paper we propose a participatory sensing based approach for traffic condition monitoring using horn detection ...
Reviews
Susan Loretta Fowler
To do participatory sensing means to be part of a group of people who keep track of and make public where, when, and why they are in a particular spot, usually via a mobile global positioning system (GPS). Until recently, most of the buzz around sensing one's location based on cell phones concentrated on advertising-if you're within a few feet of a Saks Fifth Avenue, your phone tells you about the store's sales. In the personal environmental impact report (PEIR) system, however, the information goes in the opposite direction-it determines what your carbon impact is, depending on where you are and what you're doing. Your phone keeps track of four dimensions: your carbon impact (are you walking or driving__?__), whether you're emitting airborne particulates near hospitals and schools, your exposure to smog (for example, on the freeway), and how much time you're spending in or near fast-food restaurants (according to the authors, proximity to fast food has been found to correlate with increased obesity). By solving these four tracking problems, Mun et al. also solve problems for other projects and developers. For example, how do you know if a PEIR member is on the freeway or walking down the block__?__ You can't look at feet per hour to differentiate between walking and driving-if you're stuck in traffic, you may be crawling along at a walking pace. Well, how about identifying the street__?__ Unfortunately, there are enough GPS errors that finding the closest road usually isn't enough. Also, even though a surface road might appear to be your location, you may actually be on the highway that passes over or next to the surface road. So, the PEIR developers created an "intersection based map-matching." Instead of accepting the first street identified, the algorithm watches for intersections. If, for example, the user first passes Sawtelle Blvd. and National Blvd., and then passes Sepulveda Blvd. and National Blvd., then he or she is probably on National, not Sawtelle or Sepulveda. It is clear to me that the ten authors really thought this system through. They developed a clever algorithm for hiding users' routes. No doubt, partway into the study, some of their users pointed out that they might not want some of their routes to be public (there is a link to Facebook). So, the authors developed a way to substitute innocuous routes for the ones the users want to keep private, without losing the metrics associated with the real route. Very clever! Although the system was designed to track carbon footprints, the ideas that Mun et al. propose, tested in the field and revised, can be generalized for other uses. The paper is fun to read also, because you, as a reader, can trace their routes through the problems they find and solve, in the same way they trace people through the physical world. Online Computing Reviews Service
Access critical reviews of Computing literature here
Become a reviewer for Computing Reviews.
Comments