Modeling Urban Link Travel Time with Inductive Loop Detector Data by Using the k-NN Method

Abstract

The need to measure urban link travel time (ULTT) is becoming increasingly important for the purposes both of network management and traveller information provision. This paper proposes the use of the k nearest neighbors (k-NN) technique to estimate ULTT using single loop inductive loop detector (ILD) data. This paper explores the sensitivity of travel time estimates to various k-NN design parameters. It finds that the k-NN method is not particularly sensitive to the distance metric, although care must be taken in selecting the right combination of local estimation method (LEM) and value of k. A robust LEM should be used. The optimised k-NN model is found to provide more accurate estimates than other ULTT methods. A potential application of this approach could be to aggregate GPS probe vehicle ULTT records from different times but the same underlying travel time distribution together, to obtain a more accurate estimate of ULTT.

A temporal case retrieval model to predict railway passenger arrivals

“…Clark (2003) integrated three different sources of traffic data to calculate similarity among samples. Robinson and Polak (2006) found that the 0957-4174/$ -see front matter Ó 2008 Elsevier Ltd. All rights reserved. doi:10.1016/j.eswa.2008.11.025 number of selected samples is related to weighting methods.…”

An Exploratory Shockwave Approach to Estimating Queue Length Using Probe Trajectories

“…The model carefully calculates the delay as the sum of signal delay, queuing delay, and oversaturation delay. By the same token, other work uses stochastic theories (Geroliminis & Skabardonis, 2005;Viti & van Zuylen, 2009) or artificial intelligence methods (Cheu, Lee, & Xie, 2001;Robinson & Polak, 2005). Growing interests in the second area develop along with the emerging and advancement of traffic probe technologies; new data sources and high-resolution data become available, such as individual vehicle arrival data from advanced signal control devices (Balke et al, 2005;Liu, Ma, Wu, & Hu, 2008), vehicle reidentification data (Coifman, 2002;Liu, Oh, Oh, Chu, & Recker, 2001;Ritchie, Jeng, Tok, & Park, 2008;Wilson, 2008), and probe data (Ahmed, El-Darieby, Abdulhai, & Morgan, 2008;Ban, Herring, Hao, & Bayen, 2009;Fontaine & Smith, 2007;Pan, Lu, Wang, & Ran, 2007;Qiu & Ran, 2008).…”

Development of a Post-Processing Automation Procedure for the GPS-Based Travel Time Data Collection Technique

“…The use of traditional sensors installed on major roads (e.g. inductive loops, AVI sensors) [9][10][11] or more recent Bluetooth sensors [12] along arterials and freeways for collecting data is necessary but not sufficient because of their limited coverage and expensive costs for setting up and maintaining the required infrastructure [13]. As a relatively low-cost and high accuracy solution, GPS related data collection techniques have gained acceptance among transportation engineers and practitioners [14].…”