270 likes | 392 Views
BikeTrack. Tracking Stolen Bikes through Everyday Mobile Phones and Participatory Sensing. Ted Tsung-Te Lai Chun-Yi Lin Ya-Yunn Su Hao-Hua Chu National Taiwan University. Bikes are everywhere. Cyclists face many problems … . Safety ( CyberBike , HotMobile10).
E N D
BikeTrack Tracking Stolen Bikes through Everyday Mobile Phones and Participatory Sensing Ted Tsung-Te Lai Chun-Yi Lin Ya-Yunn Su Hao-Hua Chu National Taiwan University
Bikes are everywhere Cyclists face many problems…
Fitness (BikeNet, SenSys07) Sensors: -Heart rate -GPS -Accelerometer …etc
Bike Theft Survey (208 students) 1 out of 1.8 person has bike stolen experience 1 out of 3.7 stolen bikes was recovered Mostly found on campus “Is it possible to use participatory sensing to recover stolen bikes?”
Outline • Motivation • BikeTrack System design • Evaluation and preliminary results • Future work • Conclusion
BikeTrack overview Server for bike location query data Log BluetoothID/Location/Timestamp Users use phone to scan Bluetooth Bluetooth Bike
Bluetooth beacon tag Spec: 20-meter radio range 1.5-month lifetime 16 USD/tag Customization: Only broadcast beacon ID Why Bluetooth? Available on almost every phone
Phone implementation • Android 2.1 • Scan Bluetooth ID every 20secs in background • When a Bluetooth ID is found, it logs • Auto-upload data during network availability
Server implementation • Linux + Apache + MySQL • Web interface to query bike location on google map Bike locations
Outline • Motivation • BikeTrack system design • Evaluation and preliminary results • Future work • Conclusion
User study • Two-week during summer • 11 CS grad students • Dataset: 3700 bluetooth/location/times entries • 3500 self-detection; 200 detection of other users • Constraint: CS department layout
Evaluation and preliminary results • How well does participatory sensing work in tracking bikes? • Is it possible to locate stolen bike on campus? • Is it possible to reduce battery consumption based on user behaviors ?
Avg. Bluetooth detections/day • All bikes were detected • Avg. detection rate: 5.1 times/day
Evaluation and preliminary results • How well does participatory sensing work in tracking bikes? • Is it possible to locate stolen bike on campus? • Is it possible to reduce battery consumption based on user behaviors ?
Evaluation and preliminary results • How well does participatory sensing work in tracking bikes? • Is it possible to locate stolen bike on campus? • Is it possible toreduce phone battery consumption based on user behaviors ?
Avg. user detection pattern during a day • Detection happened at noon, dinner, end of a day • Detection pattern varies with users • Future optimization (currently scan/20 seconds)
Outline • Motivation • BikeTrack System design • Evaluation and preliminary results • Future work • Conclusion
Formulating deployment strategy • How to incorporate user spatial-temporal model to reduce phone overhead? • How to incentivize participation?
Outline • Motivation • System design • Evaluation and preliminary results • Future work • Conclusion
Conclusion • BikeTrack - A low cost participatory sensing system for bike tracking • Preliminary result shows that BikeTrack is a promising system to locate bikes
Questions & Answers BikeTrack: Tracking Stolen Bikes through Everyday Mobile Phones and Participatory Sensing Ted Tsung-te Lai Chun,Yi Lin, Ya-Yunn Su, Hao-Hua Chu National Taiwan University