Tracking Stolen Bikes through Everyday Mobile Phones and Participatory Sensing

  • View
    40

  • Download
    2

Embed Size (px)

DESCRIPTION

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). - PowerPoint PPT Presentation

Text of Tracking Stolen Bikes through Everyday Mobile Phones and Participatory Sensing

1

BikeTrackTracking Stolen Bikes through Everyday Mobile Phones and Participatory SensingTed Tsung-Te Lai Chun-Yi LinYa-Yunn SuHao-Hua Chu

National Taiwan University

11Bikes are everywhere

2Cyclists face many problems2Safety (CyberBike, HotMobile10)3

3Route quality (BikeStatic, CHI10)4

4Fitness (BikeNet, SenSys07)5

Sensors:-Heart rate-GPS-Accelerometeretc

5Bike Theft (BikeTrack)6

6Bike 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?

77MotivationBikeTrack System designEvaluation and preliminary resultsFuture workConclusion

Outline88

BikeTrack overview9

BluetoothBikeUsers use phone to scan BluetoothLog BluetoothID/Location/TimestampServer for bike location query

data9Spec:20-meter radio range1.5-month lifetime16 USD/tagCustomization:Only broadcast beacon IDWhy Bluetooth?Available on almost every phoneBluetooth beacon tag

1010Bluetooth tag mounting on a bike11

11Phone implementationAndroid 2.1Scan Bluetooth ID every 20secs in backgroundWhen a Bluetooth ID is found, it logs

Auto-upload data during network availabilityBluetooth IDLocationTimestamp1212Server implementation

Linux + Apache + MySQLWeb interface to query bike location on google map13Bike locations13MotivationBikeTrack system designEvaluation and preliminary resultsFuture workConclusion

Outline1414User studyTwo-week during summer11 CS grad studentsDataset: 3700 bluetooth/location/times entries3500 self-detection; 200 detection of other usersConstraint:15

CS department layout15How 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 results1616Avg. Bluetooth detections/dayAll bikes were detectedAvg. detection rate: 5.1 times/day

17

17How 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

1818Bike location distribution in Taipei19

19Bike location distribution at NTU

2020How well does participatory sensing work in tracking bikes?Is it possible to locate stolen bike on campus?Is it possible to reduce phone battery consumption based on user behaviors ?

Evaluation and preliminary results

2121

Avg. user detection pattern during a day22

Detection happened at noon, dinner, end of a dayDetection pattern varies with usersFuture optimization (currently scan/20 seconds)22MotivationBikeTrack System designEvaluation and preliminary resultsFuture workConclusion

Outline2323Formulating deployment strategy24How to incorporate user spatial-temporal model to reduce phone overhead?

How to incentivize participation?

24MotivationSystem designEvaluation and preliminary resultsFuture workConclusion

Outline2525BikeTrack - A low cost participatory sensing system for bike tracking

Preliminary result shows that BikeTrack is a promising system to locate bikes

Conclusion2626Questions & Answers

BikeTrack:Tracking Stolen Bikes through Everyday Mobile Phones and Participatory Sensing

Ted Tsung-te LaiChun,Yi Lin, Ya-Yunn Su, Hao-Hua ChuNational Taiwan University

2727