Arrival Time Prediction Brandon Houghton, Kenji Yonekawa 08-537 - - - PowerPoint PPT Presentation

▶
arrival time prediction
SMART_READER_LITE
LIVE PREVIEW

Arrival Time Prediction Brandon Houghton, Kenji Yonekawa 08-537 - - - PowerPoint PPT Presentation

Sep 22, 2022 8 likes •238 views

Arrival Time Prediction Brandon Houghton, Kenji Yonekawa 08-537 - Fei Fang Background The bus shouldve been Im cold - how much The bus just left.. here 10 minutes ago.. longer should I wait? 2 Motivation High demand for bus arrival

slide-1
SLIDE 1

Arrival Time Prediction

Brandon Houghton, Kenji Yonekawa

08-537 - Fei Fang

slide-2
SLIDE 2

Background

2

The bus just left.. The bus should’ve been here 10 minutes ago.. I’m cold - how much longer should I wait?

slide-3
SLIDE 3

Motivation

  • High demand for bus arrival prediction

○ + 25,000 installs in Pittsburgh alone ○ Consistent daily useage

  • Inefficiency of bus routes
  • Lots of available data

3

slide-4
SLIDE 4

Motivation

  • High demand for bus arrival prediction
  • Inefficiency of bus routes

○ Higher Utilization drives efficiency ○ Real-Time tracking can inform route changes ○ Delay cited as number one deterrent ○ Missing bus due to inaccurate real time info was number three

  • Lots of available data

4

slide-5
SLIDE 5

Motivation

  • High demand for bus arrival prediction
  • Inefficiency of bus routes
  • Lots of available data

○ GPS Bus location tracking ○ Passengers track stops within app ○ Real-time traffic estimation ○ Weather, Events, etc.

5

slide-6
SLIDE 6

Related Work

  • Multiple studies done

○

  • Y. Bin and Y. Zhongzhen and Y. Baozhen, "Bus Arrival Time Prediction Using Support

Vector Machines", 2006 ○

  • W. Treethidtaphat, W. Pattara-Atikom, and S. Khaimook, "Bus Arrival Time Prediction at

Any Distance of Bus Route Using Deep Neural Network Model", 2017 ○

  • J. Lei, D. Chen, F. Li, Q. Han, S. Chen, L. Zeng, and M. Chen, "A Bus Arrival Time

Prediction Method Based on GPS position and Real-time Traffic Flow", 2017 ○

  • P. Zhou and Y. Zheng and M. Li, "How Long to Wait? Predicting Bus Arrival Time With

Mobile Phone Based Participatory Sensing", 2014

  • Problems

○ Often use erroneous location tracking ○ Based on a couple of days of data collection ○ Different setting used (location, time, data)

6

slide-7
SLIDE 7

Data Set

7

  • PAT TrueTime API

○ GPS of bus location ○ Updates every 10 seconds ○ Arrival Estimates

  • Weather API

○ Precipitation, temperature, wind ○ Updates every hour

Stored in GCP

slide-8
SLIDE 8

Evaluation

  • Limited Horizon

○ Riders not interested in accuracy after 15 minutes ○ Buses can change routes

  • Mean Absolute Percentage Error

○ Most common ○ Easy to compare

8

slide-9
SLIDE 9

Evaluation

  • Previous approaches don’t generalize well
  • Pittsburgh is much more diverse

9

MAPE: 36.9% Wall et. al. MAPE: 12%

slide-10
SLIDE 10

Use Velocity Instead of Time

  • Errors do not accumulate
  • Velocity

10

slide-11
SLIDE 11

Qualitative Results

  • Linear Model

○ Highly dependent on number of bins

  • Tree Based Model

○ Does not generalize well to new month of data

  • Mixture Models

○ Feature selection was overfitting validation set

11

slide-12
SLIDE 12

PAT Model

12

Speed

slide-13
SLIDE 13

Model Refinement - Tree Segmentation

13

Speed

slide-14
SLIDE 14

Model Refinement - Linear Interpolation

14

Speed

slide-15
SLIDE 15

Model Refinement - External Observations

15

Speed Weekday Weekend

slide-16
SLIDE 16

Model Refinement - Momentum Model

16

Speed Weekend Weekday

slide-17
SLIDE 17

Model Refinement - Meta Model

17

Speed .6 x 8:42am .4 x 8:49am .2 x 8:12am .8 x 8:24am

slide-18
SLIDE 18

Evaluation Setup

  • Results on one Route (61C) that had the most data.
  • Train data: March 2018: 155,398 data points
  • Test Data: April 2018: 101,504 data points
  • True label: future data acquired from PAT’s API

18

slide-19
SLIDE 19

Evaluation Results

19

# Model name Mean Absolute Percentage Error (MAPE) 1 Linear model

28.48%

2 Piecewise linear model

23.84%

3 Decision tree linear model

22.70%

4 Piecewise linear mixture model

18.53%

5 Decision tree with linear mixture model

15.60%

6 Piecewise linear model with momentum

12.25%

Largely affected by historic data. (slope, intercept becomes negative) Haven’t figured out optimal prediction model PAT’s prediction model

slide-20
SLIDE 20

Future Work

  • Add other data to aid prediction

○ Traffic data from Google’s Real Time Traffic ○ Class schedule for local colleges ○ Holidays and Events

  • Provide our contribution as an API or incorporate with

smartphone applications

○ Allow applications to integrate improved data without changing apps

20

slide-21
SLIDE 21

Summary

  • We tackled the societal challenge of predicting bus

arrival time

  • Evaluated existing research approaches
  • Benchmarked existing API
  • Developed and evaluated new approach
  • New approach outperforms existing API

21

slide-22
SLIDE 22

Thanks for listening!

22

slide-23
SLIDE 23

Reference

Photo Credits:

https://www.nextpittsburgh.com/city-design/port-authority-rolls-out-real-time-bus-tracking/

  • Y. Bin and Y. Zhongzhen and Y. Baozhen, "Bus Arrival Time Prediction Using Support Vector

Machines", 2006

  • W. Treethidtaphat, W. Pattara-Atikom, and S. Khaimook, "Bus Arrival Time Prediction at Any Distance
  • f Bus Route Using Deep Neural Network Model", 2017
  • J. Lei, D. Chen, F. Li, Q. Han, S. Chen, L. Zeng, and M. Chen, "A Bus Arrival Time Prediction

Method Based on GPS position and Real-time Traffic Flow", 2017

  • P. Zhou and Y. Zheng and M. Li, "How Long to Wait? Predicting Bus Arrival Time With Mobile Phone

Based Participatory Sensing", 2014

  • Z. Wall, D. J. Dailey, “An Algorithm for Predicting the Arrival Time of Mass Transit Vehicles Using

Automatic Vehicle Location Data”, Transportation Research Board 78th Annual Meeting January 10-14, 1999

23