Download presentation
Presentation is loading. Please wait.
Published byDavion Byerly Modified over 9 years ago
1
The BikeNet Mobile Sensing System for Cyclist Experience Mapping Shane B. Eisenman**, Emiliano Miluzzo*, Nicholas D. Lane* Ron A. Peterson*, Gahng-Seop Ahn** and Andrew T. Campbell* *Dartmouth College, **Columbia University
2
Sequence The MetroSense Project & BikeNet The sensing system Sensor data! Lessons Related work Wrap up BikeNet niclane@cs.dartmouth.edu
3
MetroSense People-centric Sensing Bringing sensor networks into mainstream use by the general population Sensing systems applied to everyday activities BikeNet Representative of this class of sensing systems Focused on recreational sensing BikeNet niclane@cs.dartmouth.edu
4
Recreational Sensing: Cyclist Experience Mapping 57 million cyclists in the U.S. A diversity of requirements BikeNet BikeNet niclane@cs.dartmouth.edu Fun and Leisure Athletic Training Means of Transport
5
Social Network Shared Data Public Utility Sensing Demonstrating the faces of people-centric sensing systems: Sensing power for the people BikeNet BikeNet niclane@cs.dartmouth.edu Air Quality CoastingNoise Distance Braking Car Density Cyclist Community Cyclist Experience Mapping Personal Sensing
6
The Sensing System BikeNet niclane@cs.dartmouth.edu Physical Bike Area Network (BAN)
7
The Sensing System BikeNet niclane@cs.dartmouth.edu Logical Bike Area Network (BAN)
8
The Sensing System BikeNet niclane@cs.dartmouth.edu Simplifying the prototype
9
The Sensing System BikeNet niclane@cs.dartmouth.edu Hardware Prototypes
10
The Sensing System BikeNet niclane@cs.dartmouth.edu Sampling meaningful sensor data required sensor type specific consideration of: Mounting Housing Calibration Meeting these requirements were as challenging as any part of the system. Example: Tilt Sensor
11
The Sensing System BikeNet niclane@cs.dartmouth.edu Example: Tilt Sensor (slope of path) Used 2-D Accelerometer Complicated by: Noise from bike frame vibration Difference in precise orientation angle. Bike specific error characteristics demanding bike specific calibration 3 point calibration process with known stationary angles
12
The Sensing System BikeNet niclane@cs.dartmouth.edu BANs Hanover, NH USA
13
The Sensing System BikeNet niclane@cs.dartmouth.edu BANs
14
The Sensing System BikeNet niclane@cs.dartmouth.edu Sensor Access Points (SAPs)
15
The Sensing System BikeNet niclane@cs.dartmouth.edu Backend Services
16
The Sensing System BikeNet niclane@cs.dartmouth.edu Tasking
17
The Sensing System BikeNet niclane@cs.dartmouth.edu Sensing
18
The Sensing System BikeNet niclane@cs.dartmouth.edu Delivery
19
The Sensing System BikeNet niclane@cs.dartmouth.edu Presentation + Sharing
20
Sensor Data! BikeNet niclane@cs.dartmouth.edu Data collection began in the summer of 2006 Participants included members of the sensor lab and the general public More than 100 kilometers of data collected Anonymized traces available soon on Crawdad archive
21
Performance Index BikeNet niclane@cs.dartmouth.edu
22
Performance Index BikeNet niclane@cs.dartmouth.edu Distance Duration Speed Path Slope Coasting
23
Performance Inputs: Slope and Coasting BikeNet niclane@cs.dartmouth.edu
24
Health Index BikeNet niclane@cs.dartmouth.edu
25
Health Index BikeNet niclane@cs.dartmouth.edu Noise C0 2 Level Traffic Density
26
Health Input: Car Density BikeNet niclane@cs.dartmouth.edu
27
Health Input: C0 2 Level BikeNet niclane@cs.dartmouth.edu
28
BikeView: Present and Share BikeNet niclane@cs.dartmouth.edu
29
Public Utility Sensing: CO 2 Map ~ Hanover NH BikeNet niclane@cs.dartmouth.edu
30
Lessons BikeNet niclane@cs.dartmouth.edu Mobility and people bring new challenges to experimental system development. How to debug and perform evaluation? Experiments require much more time and effort to perform Experiments are less predictable with people in the loop Difficulties exist in finding an experimental methodology (i.e., repeatability).
31
Lessons BikeNet niclane@cs.dartmouth.edu Debugging on the go!
32
Lessons BikeNet niclane@cs.dartmouth.edu Moving from protocols to caring about the payload changes everything! Noisy data. Vibrations from the bike frame. Consider physical solutions (i.e. improving the mounting) before attempting post processing solutions Validating inferences and collected sensor data requires time and effort. Counting cars by hand with button clicks from a bike (tricky and dangerous) Manual measurement of road angles Ground Truth Helmet
33
Lessons BikeNet niclane@cs.dartmouth.edu Sometimes it takes 190 odd kilometers to get it right
34
Lessons BikeNet niclane@cs.dartmouth.edu Moving from protocols to caring about the payload changes everything! Noisy data. Vibration in the bike frame. Determining appropriate sampling rates. Consider physical solutions (i.e. improving the mounting) before attempting post processing solutions Validating inferences and sensor data requires time and effort. Counting cars by hand with button clicks from a bike (tricky and dangerous) Manual measurement of road angles Ground Truth Helmet
35
Lessons BikeNet niclane@cs.dartmouth.edu Ground-Truth Validation Helmet
36
Related Projects BikeNet niclane@cs.dartmouth.edu Existing Cyclist Systems Stovepipe commercial solutions Body Area Networks and Personal Area Networks SATIRE, MIThrill DTNs, Mobile Sensing Systems Haggle, Cartel, ZebraNet People-Centric Sensing MIT Media Labs, UCLA, UIUC, Nokia Research, Intel Research, Microsoft Research, Motorola
37
Wrap Up BikeNet niclane@cs.dartmouth.edu BikeNet Platform for experimentation with mobile sensing systems supporting: Personal Sensing Sharing sensor data within Social Networks Public Utility Sensing
38
BikeNet niclane@cs.dartmouth.edu Cheers for listening http://bikenet.cs.dartmouth.edu Sponsors
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.