Site Search
Computer Science


Christie Ezeife, Ph.D.Dr. Christie Ezeife
Dr. Christie Ezeife
Windsor WaterfrontWindsor Waterfront Park
Windsor Waterfront Park
Xiaobu Yuan, Ph.D.Dr. Xiaobu Yuan
Dr. Xiaobu Yuan
Jessica Chen, Ph.D.Dr. Jessica Chen
Dr. Jessica Chen
Arunita Jaekel, Ph.D.Dr. Arunita Jaekel
Dr. Arunita Jaekel
Robin Gras, Ph.D.Dr. Robin Gras
Dr. Robin Gras
Imran Ahmad, Ph.D.Dr. Imran Ahmad
Dr. Imran Ahmad
Dr. Robert KentDr. Robert Kent
Dr. Robert Kent
Alioune Ngom, Ph.D.Dr. Alioune Ngom
Dr. Alioune Ngom
Dr. Ziad Kobti lecturingDr. Ziad Kobti
Dr. Ziad Kobti
Lambton TowerLambton Tower
Lambton Tower
Dr. Scott GoodwinDr. Scott Goodwin
Dr. Scott Goodwin
Dr. Luis RuedaDr. Luis Rueda
Dr. Luis Rueda

A hybrid approach using wavelet transform and fuzzy logic system to predict traffic flow

Add this event into your calendar using the iCAL format
  • Tue, 02/14/2017 - 1:00pm - 3:00pm

A hybrid approach using wavelet transform and fuzzy logic system to predict traffic flow

MSc Thesis Proposal by:

Jabed Hossain

Date:  Tuesday, February 14th, 2016
Time:  1: 00 pm – 3:00 pm
Location: 3105, Lambton Tower

Abstract: The increasing fleet size of vehicles has a huge impact on the transportation system around and between most of the urban cities. Across Canada, statistics indicate that the average loss of time reached 79 hours last year, leading to at least tens of billions in lost revenue every year. For almost four decades, active research has been going on to improve transportation management by developing methods to analyze traffic data and to forecast traffic flow.

Presented in this proposal is a hybrid approach that first uses wavelet transform to separate traffic data into segments with similar trends and then uses fuzzy logic to capture the characteristics of traffic segments for classification and matching. In the new approach after applying wavelet transform, datasets in-between sharp variation points exhibit a similar trend of traffic flow. After historical data are categorized in such a way into different memberships with additional information, e.g., time and weather, they can be compared with real-time data according to the rules of a fuzzy logic system. A matched dataset becomes a reliable source of information for traffic prediction. Considering the number of vehicles as crisp inputs in the fuzzy logic system, if there is any sudden change (antecedent) in traffic flow, fuzzy model implements fuzzy IF-THEN rules to generate crisp output (conclusion).

In addition to details of the proposed approach for traffic prediction, this present is also going to discuss software tools for implementation, traffic dataset for experiments, and a plan to finish the work within a scheduled timeframe. It is anticipated that the hybrid approach is going to produce more accurate and robust results for traffic prediction in different conditions.

Thesis Committee:
Internal Reader: Dr. Mehdi Kargar
External Reader: Dr. Kevin W Li
Advisor: Dr. Xiaobu Yuan

See More: