Download presentation
Presentation is loading. Please wait.
1
Pengfei Zhou, Yuanqing Zheng, Mo Li -twohsien 2012.9.3
How Long to Wait?: Predicting Bus Arrival Time with Mobile Phone based Participatory Sensing Pengfei Zhou, Yuanqing Zheng, Mo Li -twohsien
2
Outline Introduction System design Evaluation Limitations Conclusion
3
Introduction Who will pay for this? $$$$$$$$$$$$
Why travelers do not like to travel by bus? Excessively long waiting time Existing methods to predict arrival time Timetable ( operating hours, time intervals, etc.) Special location tracking devices on buses Who will pay for this? $$$$$$$$$$$$
4
Objective Crowd-participated approach Energy friendly Sharing users
Querying users Backend server Energy friendly Microphone, accelerometer Mobile Phone
5
Main idea Map the bus routes to a space featured by sequences of nearby cellular towers
6
Challenges Bus Detection Bus Classification Information Assembling
7
System Design
8
Pre-processing Celltower Data
Top-3 strongest cell towers 300 meters apart
9
Example
10
Bus Detection Audio detection : short beep audio response
Peak at 1 kHz and 3kHz
11
Bus Detection Sliding window, size: 32 samples
Empirical threshold: three standard deviation
12
Bus Detection Accelerometer detection Bus v.s. Rapid train
13
Bus Detection Threshold Small: trains will be misdetected as buses
Big: miss detection of actual buses
14
Bus Classification Cell tower sequence matching
Smith-Waterman algorithm If ui = Cw ∈ Sj , ui and Sj are matching with each other, and mismatching otherwise
15
Bus Classification 𝑓 𝑠 𝑤 = 0.5 𝑤− w: rank of signal strenth penalty cost for mismatches : -0.5
16
Overlapped route Survey 50 bus route Range of cell tower:
meters threshold of celltower sequence length : 7
17
Cell tower Sequence Concatenation
18
Arrival Time Prediction
19
Evaluation
20
Experimental Methodology
Mobile phones Samsung Galaxy S2 i9100 HTC Desire Experiment environment 4 campus shuttle bus routes 2 SBS transit bus route 179 and 241
21
Bus Detection Performance
22
Bus vs. MRT Train False detection: Driving along straight routes late during night time
23
Bus Classification Performance
24
Arrival Time Prediction
25
Arrival Time Prediction
26
System Overhead Battery lifetime
27
Limitation and On-going Work
Alternative reference points Number of passengers First few bus stops Overlapped routes
28
Conclusion Present a crowd-participated bus arrival time prediction system using commodity mobile phones. Evaluate the system through a prototype system deployed on the Android platform with two types of mobile phones.
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.