Presentation is loading. Please wait.

Presentation is loading. Please wait.

WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 16 1 1 1 2 2 2 3 3 3 4 3 55 6 6 8 8 9 6 PROBLEM: How to get from A to B Many Paths.

Published byShavonne Cain Modified over 8 years ago

Similar presentations

Presentation on theme: "WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 16 1 1 1 2 2 2 3 3 3 4 3 55 6 6 8 8 9 6 PROBLEM: How to get from A to B Many Paths."— Presentation transcript:

1 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 16 1 1 1 2 2 2 3 3 3 4 3 55 6 6 8 8 9 6 PROBLEM: How to get from A to B Many Paths Each with a Different Value to the Decision Maker Each Segment Changing with Uncertainty over Time Addressing the Real-time Aspects In Turn-by-turn Navigation 4

2 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Link Travel Times Historic, Actual & Forecast During Day One week-day on one link Things change!

3 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 The Measurement Problem How to collect the real time Speed Data? –Incremental Infrastructure In pavement loop detectors (single point) radar/laser/video signpost systems (single point) EZ Pass readers (2 point span measurement, Excellent) –Processing “Existing” Data Wireless Location Technology (Cellular Probes, see Fontaine, et al) –Cell-tower trilateration »Yet to demonstrate sufficient accuracy –Cell-handoff processing »maybe OK for simple networks Floating Car (Vehicle Probe) data processing (see Demers et al)

4 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Cell Probe Technology Practical success requires more than cell phones Cell phone movement based on cell location and “hand-offs” from one cell to another Pattern recognition techniques filter out data from those not on the highway Then traffic algorithms generate travel times and speeds on roadway links Cell phones need to be turned on, but not necessarily in use Full regional systems in place in Baltimore, Antwerp, and Tel Aviv = 4,600 miles, Shanghai

5 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Cell Probe Technology

6 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Cell Probe Privacy

7 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Handset 49, part 1

8 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Handset 49, part 2

9 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Handset 49, part 3

10 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Handset 49, part 4

11 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Handset 49, part 5

12 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Handset 49, part6

13 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Handset 49, full trip

14 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Handset 49, full trip

15 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Path-Finding Drive Tests

16 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Baltimore MMTIS Provides first regional deployment of commercial- quality cellular traffic probes in North America Mutually profitable public-private partnership –Test commercial markets during project –Integrate with existing public data – including transit and E-911 –Encourage public applications beyond traditional ITS Contract signed September 2004; data flow to Maryland DOT began April 2005

17 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Baltimore MMTIS – Private Firms Delcan-NET –Transportation and technology consultants –Fifty plus years in business –Profitable every year; staff = 500 plus ITIS Holdings –Leader in traffic probes; staff = 100 –Commercial customers – 16 automobile firms, for-profit 511 –Profitable! –Publicly traded on London exchange National cellular firms

18 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9

19 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 MARYLAND DOT CAMERAS SHOW ACCURACY OF TRAFFIC INFORMATION BEING CAPTURED USING CELL PROBES I-695 at HARTFORD ROAD Monday, June 6 th 2005 9:02:18 am

20 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 I-695 at HARTFORD ROAD Monday, June 6 th 2005 9:33:06 am CELL PROBES ACCURATELY UPDATE TRAFFIC CONDITIONS AS CHANGES OCCUR

21 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Produced by Dr Hillel Bar Gerd, Associate Professor, Ben Gurion Negev University, Israel

22 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Baltimore Comparison with RTMS Data

23 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Analysis Route Overview

24 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Performance data I-695 – July 2005

25 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Baltimore I-695 Weekday Patterns

26 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Baltimore I-695 Saturday Patterns

27 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Baltimore I-695 Route Travel Time

28 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9

29 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9

30 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9

31 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Vehicle Probes Assign Speed data to network segments of Digital Map database, or Maintain travel times between strategically located virtual monuments

32 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 North American Monument Network ~ 125,000 North American “Monuments” ~10 6 (m i, m j ) Can create Median travel Tims by Time-of-Day – For Example: AM Peak, Midday, PM Peak, Night, Weekend day (mi, mj) near Troy (mi, mj) larger area

33 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Median Speed (by direction) on National Highway Network 1:30pm 11/14/07 > 40 mph < 40 mph 1:30pm 11/14/07 height ~ speed

34 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Average Speed (by direction) on National Highway Network 1:30pm 11/14/07 > 40 mph < 40 mph 1:30pm 11/14/07 height ~ speed

35 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Real-Time Dynamic Minimum ETA Sat/Nav 250 Volunteers using CoPilot|Live commuting to/from RPI CoPilot continuously shares real-time probe-based traffic data CoPilot continuously seeks a minimum ETA route “Advance” project Illinois Universities Transportation Research Consortium The late 90s Conducted its version of the abandoned “ADVANCE” ( Advanced Driver and Vehicle Advisory Navigation ConcEpt ) project & Won ITS America’s 2007 “Best Innovative Research” Award

36 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Project Objectives Create: real-time data collection from vehicles and dissemination to vehicles of congestion avoidance information which is used to automatically reroute drivers onto the fastest paths to their destinations Target locations: small to medium-sized urban areas Aspects: operations, observability, controllability, users, information transfer to travelers

37 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 3-month field test Capital District (Albany), NY, USA Journey-to-work 200 participants 80 Tech Park employees 120 HVCC staff & students “Techy” travelers Network: Freeways & signalized arterials Congested links Path choices exist Experiment Details

38 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Basic Operational Architecture Two-way cellular data communications between Customized Live|Server at ALK Customized CoPilot|Live In vehicles 6 Destinati on 1 2, 4 3 5 7 8

39 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Every Second CoPilot|Live Determines “Where am I”, Then… CoPilot|Live “Where Am I”, Then… ALK Server Updates: TT(m i, m j ) If Momument, m j, is passed Send m i, m j, tt k (m i, m j )= t(m i ) - t(m i ) (52 bytes) Set i=j

40 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Every “n” Minutes ALK Server Builds: set U k Sends: TT(m i, m j ) for every (i,j) in U k CoPilot|Live … Send… Current Location & Destination, Last update time (42 bytes) ALK Server … Send… New TT(m i, m j ) for every (i,j) in U k (280 bytes/100arcs) CoPilot|Live … Updates TT(m i, m j ) in U k, ETA on current route, Finds new MinETA route, if MinETA “substantially” better then… Adopt new route ALK Server … Determines U k : set of TT(m i, m j ) within “bounding polygon” of (Location;Destination) k that have changed more than “y%” since last update. CoPilot|Live Sends: “Where am I”, Dest., Last update Receives/Posts: updates Computes: MinETA Updates route, if better

41 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 When Available ALK Server … Receives: Other congestion information from various source, blends them in TT(m i, m j ) ALK Server Updates: TT(m i, m j )

42 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 What We Heard I find it interesting how willing I am to listen to a machine tell me which route to take I like using it for when I have no idea on how to get somewhere, and it is good for my normal route because it keeps me out of traffic on route 4. It is great, it took a while to trust it telling me where to go, but i like it because i cant get lost! Thanks. This thing is awesome. I was a little skeptical at first but once i got the hang of it I don’t know how I went along without it. I think any student commuting to school will benefit from this. I'm very impressed with the CoPilot program thus far. The directions are accurate and it adapts quickly to route changes.

43 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 1 2 3 also Can Watch Vehicles

44 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Forecasting Travel Times Using Exponential Smoothig

45 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Historical Expectation: Concepts Patterns Differ over Days & Time of Day Most Significant Difference is Between Weekdays and Weekends Zoo Interchange – Hale Interchange (All Days)

46 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Historical Expectation: Concepts Two Peak Periods Each appears to be Bell Shaped Afternoon Peak Period Appears to have “Extra Hump”

47 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Historical Expectation: Solution

48 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Historical Expectation: Application Minimize the SSE between Historical Estimation Function and actual data points Downtown – Zoo Interchange

49 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Historical Expectation: Application

50 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Using Real-Time Information to Improve our Estimate

51 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Including Real-Time Information: Concepts Real-Time Information “Since a desirable route needs to be given when the driver asks for it, but the computation of such a route requires travel times which occur later, we need to be able to forecast such travel times.” DEFINITION: A real-time travel time is a data point that can be received or constructed and measures the time it takes to traverse a specific route from one location to another location ending now.

52 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Including Real-Time Information: Concepts Peak Hour Characteristics & Return to Normalcy During Peak Hours, Traffic Patterns Remain at a relatively constant distance to Historical Estimate There will be a time at which traffic patterns will return to free flow conditions Moorland - Downtown Burleigh - Zoo

53 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Method of “smoothing” a time series of observations Most recent observations are given a high weight and previous observations are given lower weights that decrease exponentially with the age of the observation Including Real-Time Information: Concepts Exponential Smoothing Single Double Triple

54 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Including Real-Time Information: Solution During Peak Periods: Adaptation of Double Exponential Smoothing Trend is the Trend of the Historical Estimate Observation weighted with Most Recent Estimate + Slope for Smoothed Estimate Forecast done by adding trend to most recent estimate

55 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Including Real-Time Information: Solution During Non-Peak Periods Adaptation of Double Exponential Smoothing Trend is decay to free flow Conditions

56 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Including Real-Time Information: Solution Burleigh – Zoo (June 14)

57 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 Including Real-Time Information: Application

58 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 THETA0.3000 Time Step0:03:00 PHE0.8000 CAI0.5000 C0.85 Progression Through Sample Day: Moorland – DowntownJune 14, 2002

59 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 THETA0.3000 Time Step0:03:00 PHE0.8000 CAI0.5000 C0.85 Progression Through Sample Day: Moorland – DowntownJune 14, 2002

60 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 THETA0.3000 Time Step0:03:00 PHE0.8000 CAI0.5000 C0.85 Progression Through Sample Day: Moorland – DowntownJune 14, 2002

61 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 THETA0.3000 Time Step0:03:00 PHE0.8000 CAI0.5000 C0.85 Progression Through Sample Day: Moorland – DowntownJune 14, 2002

62 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 THETA0.3000 Time Step0:03:00 PHE0.8000 CAI0.5000 C0.85 Progression Through Sample Day: Moorland – DowntownJune 14, 2002

63 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 THETA0.3000 Time Step0:03:00 PHE0.8000 CAI0.5000 C0.85 Progression Through Sample Day: Moorland – DowntownJune 14, 2002

64 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 THETA0.3000 Time Step0:03:00 PHE0.8000 CAI0.5000 C0.85 Progression Through Sample Day: Moorland – DowntownJune 14, 2002

65 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 THETA0.3000 Time Step0:03:00 PHE0.8000 CAI0.5000 C0.85 Progression Through Sample Day: Moorland – DowntownJune 14, 2002

66 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 THETA0.3000 Time Step0:03:00 PHE0.8000 CAI0.5000 C0.85 Progression Through Sample Day: Moorland – DowntownJune 14, 2002

67 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 THETA0.3000 Time Step0:03:00 PHE0.8000 CAI0.5000 C0.85 Progression Through Sample Day: Moorland – DowntownJune 14, 2002

68 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 THETA0.3000 Time Step0:03:00 PHE0.8000 CAI0.5000 C0.85 Progression Through Sample Day: Moorland – DowntownJune 14, 2002

69 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 THETA0.3000 Time Step0:03:00 PHE0.8000 CAI0.5000 C0.85 Progression Through Sample Day: Moorland – DowntownJune 14, 2002

70 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 THETA0.3000 Time Step0:03:00 PHE0.8000 CAI0.5000 C0.85 Progression Through Sample Day: Moorland – DowntownJune 14, 2002

71 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 THETA0.3000 Time Step0:03:00 PHE0.8000 CAI0.5000 C0.85 Progression Through Sample Day: Moorland – DowntownJune 14, 2002

72 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 THETA0.3000 Time Step0:03:00 PHE0.8000 CAI0.5000 C0.85 Progression Through Sample Day: Moorland – DowntownJune 14, 2002

73 WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 THETA0.3000 Time Step0:03:00 PHE0.8000 CAI0.5000 C0.85 Progression Through Sample Day: Moorland – DowntownJune 14, 2002

Download ppt "WWS 527a – Transportation Policy Analysis Fall 2007/8 11/20/2007Week 9 16 1 1 1 2 2 2 3 3 3 4 3 55 6 6 8 8 9 6 PROBLEM: How to get from A to B Many Paths."

Similar presentations

SV-ITS PROGRAM: Silicon Valley Smart Corridor Project Overview

SV-ITS PROGRAM: Silicon Valley Smart Corridor Project Overview
2 5 Y e a r s o f T r a n s p o r t a t i o n T e c h n o l o g y L e a d e r s h i p CoPilot|MinETA Real-Time Dynamic Minimum ETA Sat/Nav Operational.

2 5 Y e a r s o f T r a n s p o r t a t i o n T e c h n o l o g y L e a d e r s h i p CoPilot|MinETA Real-Time Dynamic Minimum ETA Sat/Nav Operational.
Forecasting Models With Linear Trend. Linear Trend Model If a modeled is hypothesized that has only linear trend and random effects, it will be of the.

Forecasting Models With Linear Trend. Linear Trend Model If a modeled is hypothesized that has only linear trend and random effects, it will be of the.
The Practical Side of Cell Phones as Traffic Probes Dr. Richard Mudge, Delcan-NET October 10, 2005 The information contained in this document is considered.

The Practical Side of Cell Phones as Traffic Probes Dr. Richard Mudge, Delcan-NET October 10, 2005 The information contained in this document is considered.
VTrack: Accurate, Energy-Aware Road Traffic Delay Estimation Using Mobile Phones Arvind Thiagarajan, Lenin Ravindranath, Katrina LaCurts, Sivan Toledo,

VTrack: Accurate, Energy-Aware Road Traffic Delay Estimation Using Mobile Phones Arvind Thiagarajan, Lenin Ravindranath, Katrina LaCurts, Sivan Toledo,
Analysis, Characterization and Visualization of Freeway Traffic Data in Los Angeles Alain L. Kornhauser Professor, Operations Research & Financial Engineering.

Analysis, Characterization and Visualization of Freeway Traffic Data in Los Angeles Alain L. Kornhauser Professor, Operations Research & Financial Engineering.
INRIX Data Evaluation I-95 Corridor Coalition – Vehicle Probe Project (VPP) I-95 Corridor Coalition – Vehicle Probe Project (VPP) January 3, 2012.

INRIX Data Evaluation I-95 Corridor Coalition – Vehicle Probe Project (VPP) I-95 Corridor Coalition – Vehicle Probe Project (VPP) January 3, 2012.
11October 19, 2011 Comparison of Queue Estimation Models at Traffic Signals Jingcheng Wu October 19, 2011 Presented at the 18th World Congress on ITS.

11October 19, 2011 Comparison of Queue Estimation Models at Traffic Signals Jingcheng Wu October 19, 2011 Presented at the 18th World Congress on ITS.
The Structure of Networks with emphasis on information and social networks T-214-SINE Summer 2011 Chapter 8 Ýmir Vigfússon.

The Structure of Networks with emphasis on information and social networks T-214-SINE Summer 2011 Chapter 8 Ýmir Vigfússon.
February 9, 2006TransNow Student Conference Using Ground Truth Geospatial Data to Validate Advanced Traveler Information Systems Freeway Travel Time Messages.

February 9, 2006TransNow Student Conference Using Ground Truth Geospatial Data to Validate Advanced Traveler Information Systems Freeway Travel Time Messages.
Orf 467 – Transportation Systems Analysis Fall 2007/8 11/9/2007Week 8 16 1 1 1 2 2 2 3 3 3 4 3 55 6 6 8 8 9 6 PROBLEM: How to get from A to B Many Paths.

Orf 467 – Transportation Systems Analysis Fall 2007/8 11/9/2007Week PROBLEM: How to get from A to B Many Paths.
Archived Data User Services (ADUS). ITS Produce Data The (sensor) data are used for to help take transportation management actions –Traffic control systems.

Archived Data User Services (ADUS). ITS Produce Data The (sensor) data are used for to help take transportation management actions –Traffic control systems.
ORF 510: Directed Research II “Analyzing travel time distributions using GPS data” Santiago Arroyo Advisor: Prof. Alain L. Kornhauser January 13 th, 2004.

ORF 510: Directed Research II “Analyzing travel time distributions using GPS data” Santiago Arroyo Advisor: Prof. Alain L. Kornhauser January 13 th, 2004.
June 16, 2004 Dr. Robert Bertini Michael Rose Evaluation of the “COMET” Incident Response Program Oregon Department of Transportation.

June 16, 2004 Dr. Robert Bertini Michael Rose Evaluation of the “COMET” Incident Response Program Oregon Department of Transportation.
Commuters Helping Commuters: Findings from a Field Test of a Probe-based, Wireless, Traveler Information System William Wallace, Earl E. Lee, Jeffrey Wojtowicz.

Commuters Helping Commuters: Findings from a Field Test of a Probe-based, Wireless, Traveler Information System William Wallace, Earl E. Lee, Jeffrey Wojtowicz.
Princeton University Prospect Eleven Dec. 6, 2005 Towards Real-Time MinETA Routing Tuesday, December 6, 2005 RPI, Troy, NY Alain L. Kornhauser Professor,

Princeton University Prospect Eleven Dec. 6, 2005 Towards Real-Time MinETA Routing Tuesday, December 6, 2005 RPI, Troy, NY Alain L. Kornhauser Professor,
TEMPLATE DESIGN © 2008 www.PosterPresentations.com Issues and Challenges in Route Guidance: Mr. Tremaine Rawls, Mr. Timothy Hulitt, Dr. Fatma Mili Norfolk.

TEMPLATE DESIGN © Issues and Challenges in Route Guidance: Mr. Tremaine Rawls, Mr. Timothy Hulitt, Dr. Fatma Mili Norfolk.
Month XX, 2004 Dr. Robert Bertini Using Archived Data to Measure Operational Benefits of ITS Investments: Ramp Meters Oregon Department of Transportation.

Month XX, 2004 Dr. Robert Bertini Using Archived Data to Measure Operational Benefits of ITS Investments: Ramp Meters Oregon Department of Transportation.
Use of Truck GPS Data for Travel Model Improvements Talking Freight Seminar April 21, 2010.

Use of Truck GPS Data for Travel Model Improvements Talking Freight Seminar April 21, 2010.
Rutgers: Gayathri Chandrasekaran, Tam Vu, Marco Gruteser, Rich Martin,

Rutgers: Gayathri Chandrasekaran, Tam Vu, Marco Gruteser, Rich Martin,

Similar presentations

Ads by Google