Data-Driven Approach to Quantify and Reduce Error Associated with Assigning Short Duration Counts to Traffic Pattern Groups

Abstract

Traffic monitoring agencies collect traffic data samples to estimate annual average daily traffic (AADT) at short duration count sites. The steps to estimate AADT from sample data introduce error that manifests as uncertainty in the AADT statistic and its applications. Past research suggests that the assignment of a short duration count site to a traffic pattern group (TPG), characterized by known traffic periodicities, represents a significant but poorly quantified source of error. This paper presents an approach to quantify the range of errors arising from such assignments and to mitigate these errors using a novel data-driven assignment method. The approach uses simulated 48-hour short duration counts sampled from continuous count sites with known AADT to develop a benchmark of the total error expected when AADT is estimated from such samples. Likewise, the analysis produces a set of AADT estimates using temporal factors from pre-defined TPGs to quantify the range of assignment errors. The data-driven assignment method aims to mitigate these errors by minimizing the absolute mean deviation in AADT estimates produced from multiple short duration counts in a single year. The approach is applied to traffic data collected in Manitoba, Canada, as a case study. The results indicate that the mean absolute error from 48-hour short duration counts is 6.40% of the true AADT and that improper assignment can lead to a range in mean absolute errors of 9%. When applied to previously unassigned sites, the data-driven assignment method reduced mean absolute errors from 10.32%, using a conventional assignment method, to 7.86%.

Construction of Dynamic Traffic Pattern Recognition and Prediction Model Based on Deep Learning in the Background of Intelligent Cities

“…It was validated that this method's effectiveness was superior to that of traditional methods [17]. To reduce the error of estimating annual average daily traffic from sample data, experts such as G. Grande proposed a method to quantify the error range, and used a new data-driven allocation method to lessen the error, which could reduce the average absolute error by 2.46% [18]. Z. Liu and other researchers proposed a pattern recognition method based on image processing to reduce the incidence of highway traffic accidents.…”

“…The main function of the CNN model is to collect features from data, and it mainly includes convolutional, activated, pooling and fully connected layers [40][41]. Common activation function of CNN models include Sigmoid [42], ReLU [43] and tanh functions [44], and their calculations are shown in equation (18). 18), ϕ is the input variable.…”