Presentation Title

An Intelligent and Real-Time Mobile-based Bus Tracking and Scheduling System

Presenter Information

Chon In Luk, Cal Poly PomonaFollow

Start Date

November 2016

End Date

November 2016

Location

HUB 302-#21

Type of Presentation

Poster

Abstract

The Bronco Shuttle services at Cal Poly Pomona have assisted many students to traverse the vast Cal Poly Pomona campus. Infrastructures and websites were built and utilized to display locations of the shuttles and the prediction for next shuttle at any given stop. However, the official implementation of the prediction services is inefficient and uninformative, and one fatal flaw: there will be periods of time where the service is down and nonfunctional. In this work, we propose a native approach to displaying more information in real-time in comparison to the web-based application. We also propose to use machine learning and prediction algorithm to predict the typical wait time for all stops for given time of the day. Using the data collected during shuttle operation hours as training data for our machine learning model, we can generate algorithm of real time typical wait times and shuttle patterns.

This document is currently not available here.

Share

COinS
 
Nov 12th, 4:00 PM Nov 12th, 5:00 PM

An Intelligent and Real-Time Mobile-based Bus Tracking and Scheduling System

HUB 302-#21

The Bronco Shuttle services at Cal Poly Pomona have assisted many students to traverse the vast Cal Poly Pomona campus. Infrastructures and websites were built and utilized to display locations of the shuttles and the prediction for next shuttle at any given stop. However, the official implementation of the prediction services is inefficient and uninformative, and one fatal flaw: there will be periods of time where the service is down and nonfunctional. In this work, we propose a native approach to displaying more information in real-time in comparison to the web-based application. We also propose to use machine learning and prediction algorithm to predict the typical wait time for all stops for given time of the day. Using the data collected during shuttle operation hours as training data for our machine learning model, we can generate algorithm of real time typical wait times and shuttle patterns.