arXiv subjects

Lee D. Han

Publications and source records attributed to Lee D. Han.

4 recordsLinked to original sources

arXiv2024

Estimating journey time for two-point vehicle re-identification survey with limited observable scope using 2-dimensional truncated distributions

In transportation, Weigh-in motion (WIM) stations, Electronic Toll Collection (ETC) systems, Closed-circuit Television (CCTV) are widely deployed to collect data at different locations. Vehicle re-identification, by matching the same vehicle at different locations, is helpful in understanding the long-distance journey patterns. In this paper, the potential hazards of ignoring the survivorship bias effects are firstly identified and analyzed using a truncated distribution over a 2-dimensional time-time domain. Given journey time modeled as Exponential or Weibull distribution, Maximum Likelihood Estimation (MLE), Fisher Information (F.I.) and Bootstrap methods are formulated to estimate the parameter of interest and their confidence intervals. Besides formulating journey time distributions, an automated framework querying the observable time-time scope are proposed. For complex distributions (e.g, three parameter Weibull), distributions are modeled in PyTorch to automatically find first and second derivatives and estimated results. Three experiments are designed to demonstrate the effectiveness of the proposed method. In conclusion, the paper describes a very unique aspects in understanding and analyzing traffic status. Although the survivorship bias effects are not recognized and long-ignored, by accurately describing travel time over time-time domain, the proposed approach have potentials in travel time reliability analysis, understanding logistics systems, modeling/predicting product lifespans, etc.

stat.AP↗

arXiv2024

An Iterative Algorithm to Impute Truck Information over Nationwide Traffic Networks

Understanding the dynamics of truck volumes and activities across the skeleton traffic network is pivotal for effective traffic planning, traffic management, sustainability analysis, and policy making. Yet, relying solely on average annual daily traffic volume for trucks cannot capture the temporal changes over time. Recently, the Traffic Monitoring Analysis System dataset has emerged as a valuable resource to model the system by providing information on an hourly basis for thousands of detectors across the United States. Combining the average annual daily traffic volume from the Highway Performance Monitoring System and the Traffic Monitoring Analysis System dataset, this study proposes an elegant method of imputing information across the traffic network to generate both truck volumes and vehicle class distributions. A series of experiments evaluated the model's performance on various spatial and temporal scales. The method can be helpful as inputs for emission modeling, network resilience analysis, etc.

cs.NI↗

arXiv2024

GTFS2STN: Analyzing GTFS Transit Data by Generating Spatiotemporal Transit Network

The General Transit Feed Specification (GTFS) is an open standard format for recording transit information, utilized by thousands of transit agencies worldwide. This study introduces GTFS2STN, a novel tool that converts static GTFS transit networks into spatiotemporal networks, connecting bus stops across space and time. This transformation enables comprehensive analysis of transit system accessibility. Additionally, we present a web-based application version of the GTFS2STN tool that allows users to generate spatiotemporal networks online and perform basic analyses, including the creation of isochrone maps from a given origin and the calculation of travel time variability between origin-destination pairs over time. Comparative analysis demonstrates that GTFS2STN produces results similar to those of Mapnificent, an existing open-source tool for generating isochrone maps from GTFS inputs. Compared with Mapnificent, GTFS2STN offers enhanced flexibility for researchers and planners to evaluate transit plans, as it allows users to upload and analyze historical or suggested GTFS feeds from any transit agency. This feature facilitates the assessment of accessibility and travel time variability in transit networks over extended periods, making GTFS2STN a valuable tool for the planning and research for the transit systems.

cs.CE↗

arXiv2024

Improving the accuracy of freight mode choice models: A case study using the 2017 CFS PUF data set and ensemble learning techniques

The US Census Bureau has collected two rounds of experimental data from the Commodity Flow Survey, providing shipment-level characteristics of nationwide commodity movements, published in 2012 (i.e., Public Use Microdata) and in 2017 (i.e., Public Use File). With this information, data-driven methods have become increasingly valuable for understanding detailed patterns in freight logistics. In this study, we used the 2017 Commodity Flow Survey Public Use File data set to explore building a high-performance freight mode choice model, considering three main improvements: (1) constructing local models for each separate commodity/industry category; (2) extracting useful geographical features, particularly the derived distance of each freight mode between origin/destination zones; and (3) applying additional ensemble learning methods such as stacking or voting to combine results from local and unified models for improved performance. The proposed method achieved over 92% accuracy without incorporating external information, an over 19% increase compared to directly fitting Random Forests models over 10,000 samples. Furthermore, SHAP (Shapely Additive Explanations) values were computed to explain the outputs and major patterns obtained from the proposed model. The model framework could enhance the performance and interpretability of existing freight mode choice models.

cs.LG↗