Location

London

Event Website

http://www.csce2016.ca/

Description

Travel time is an important measure in traffic engineering and planning with many applications including identification of network bottlenecks, plan to improve traffic mobility, providing commuters with travel time information, and traffic signal control evaluation and control. Currently a number of technologies can provide travel time information such as GPS enabled probes and identifying vehicles with Bluetooth or Wi-Fi devices. The later method detects and matches unique Media Access Control (MAC) address of the Bluetooth or Wi-Fi activated devices to calculate travel time information. This method is a non-intrusive and cost effective and has gained a lot of attention in the past few years. Extensive research has been done on evaluating the accuracy, application, and market penetration rate of using Bluetooth technology for travel time estimation for both urban arterials and highways. However, the application of Wi-Fi MAC address detection and matching for travel time estimation at urban arterials has not been adequately studied. The limited available studies are contradicting with significant differences in terms of travel time accuracy, and penetration rates. This study intended to evaluate the accuracy and reliability of using the combination of Bluetooth and Wi-Fi based travel time estimates through a case study. A sample size analysis is conducted and the expected statistical sampling errors are compared with that of obtained from comparing the Bluetooth and Wi-Fi data with ground truth information which is collected through video footage. The results of this study show that Wi-Fi signals can also provide reliable travel time information. When combined with Bluetooth travel times data, which significantly increases the market penetration rate comparing to using Bluetooth alone. The combination of using Bluetooth and Wi-Fi signal provided penetration rates up to 8% with errors less than 10% compared to ground truth data.


Share

COinS
 
Jun 1st, 12:00 AM Jun 4th, 12:00 AM

TRA-963: EVALUATION OF USING WIFI SIGNALS TO ESTIMATE INTERSECTION TRAVEL TIME

London

Travel time is an important measure in traffic engineering and planning with many applications including identification of network bottlenecks, plan to improve traffic mobility, providing commuters with travel time information, and traffic signal control evaluation and control. Currently a number of technologies can provide travel time information such as GPS enabled probes and identifying vehicles with Bluetooth or Wi-Fi devices. The later method detects and matches unique Media Access Control (MAC) address of the Bluetooth or Wi-Fi activated devices to calculate travel time information. This method is a non-intrusive and cost effective and has gained a lot of attention in the past few years. Extensive research has been done on evaluating the accuracy, application, and market penetration rate of using Bluetooth technology for travel time estimation for both urban arterials and highways. However, the application of Wi-Fi MAC address detection and matching for travel time estimation at urban arterials has not been adequately studied. The limited available studies are contradicting with significant differences in terms of travel time accuracy, and penetration rates. This study intended to evaluate the accuracy and reliability of using the combination of Bluetooth and Wi-Fi based travel time estimates through a case study. A sample size analysis is conducted and the expected statistical sampling errors are compared with that of obtained from comparing the Bluetooth and Wi-Fi data with ground truth information which is collected through video footage. The results of this study show that Wi-Fi signals can also provide reliable travel time information. When combined with Bluetooth travel times data, which significantly increases the market penetration rate comparing to using Bluetooth alone. The combination of using Bluetooth and Wi-Fi signal provided penetration rates up to 8% with errors less than 10% compared to ground truth data.

http://ir.lib.uwo.ca/csce2016/London/Transportation/37