Evaluation of Interstate Work Zone Mobility using Probe Vehicle Data and Machine Learning Techniques

Kamyab, Mohsen; Remias, Stephen M.; Najmi, Erfan; Hood, Kerrick; Al-Akshar, Mustafa; Ustun, Ilyas

doi:10.1177/0361198119827936

Cited by 3 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When there are people or heavy equipment in the work area, drivers often adhere to the speed limit in the work area [29]. Kamyab, M. [30] used machine learning to predict the influencing factors of future work areas and found that long-term speed changes are important factors in predicting the impact of work areas on traffic. Pesti, G. [10] developed a method for evaluating the impact of road construction work areas, (a) predicting the network level impact of road construction projects, (b) identifying key sections and corridors with the most severe expected construction impact, and (c) comparing alternative construction plans and schedules.…”

Section: Literature Reviewmentioning

confidence: 99%

Evaluation of Different Work Zone Road-Occupation Schemes for Monorail Construction

Wang,

Pan,

Xie

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Due to the increasing demand for transportation, road renovation is inevitable, and the emergence of work zones has become the most common problem in traffic control. There are many research results on the impact of work zones on traffic operation, but most of them focus on various capacity theoretical models or traffic flow control strategies and are mostly concentrated in highway work areas and urban road subway construction work areas. The location of these work zones is often unable to be changed and is mostly considered reasonable. At present, there is still a gap in selecting and evaluating the location of the work zone. Therefore, this article studied a bidirectional six-lane intersection in Xi’an and investigated the situation of traffic flow distortion caused by the setting of work zones at the intersection. Two different positions and forms of work zones were designed for evaluation and analysis. Firstly, we used VISSIM (2022 student) to simulate the original and proposed work zone road-occupation schemes and analyzed six indicators. Finally, in order to determine the optimal work zone locations under different traffic situations, we applied the entropy weight method (EWM) to assign weights to multiple indicators, thereby achieving a comprehensive assessment of various schemes. The results showed that the highest improvement level among the six indicators was 50.2%, and different schemes adapted to different traffic situations. However, occupying two lanes of the median opposite the exit lane performed better under high traffic volume. Occupying the median and lanes on both sides of the median is suitable for low traffic volume. Occupying two lanes of the entrance lane and using the opposite lane as the left-turn entrance lane is suitable for situations with high traffic volume in the opposite lane.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Evaluation of Different Work Zone Road-Occupation Schemes for Monorail Construction

Wang,

Pan,

Xie

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…These data were verified by numerous sources including the I-95 Corridor coalition ( 21 ). Since then, these data have been used in different areas of work zone traffic mobility including impact measurement ( 22 – 24 ), congestion and bottle neck evaluation ( 25 – 27 ), and traffic mobility prediction ( 11 , 24 , 28 ).…”

Section: Probe Vehicle Datamentioning

confidence: 99%

“…In both studies, hourly traffic volume was used as the critical input to train the predictive models. In the absence of hourly traffic volume, a classification modeling approach was introduced, in an earlier attempt, to predict speed ranges for each highway segment during lane closure events ( 24 ). Distributions of historical traffic speeds were used to provide a mobility baseline for random forest and XGBoost classification algorithms ( 24 ).…”

Section: Probe Vehicle Datamentioning

confidence: 99%

“…In the absence of hourly traffic volume, a classification modeling approach was introduced, in an earlier attempt, to predict speed ranges for each highway segment during lane closure events ( 24 ). Distributions of historical traffic speeds were used to provide a mobility baseline for random forest and XGBoost classification algorithms ( 24 ). These models showed a decent performance, however, there are various approaches that can potentially improve this prediction methodology.…”

Section: Probe Vehicle Datamentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Approach to Forecast Work Zone Mobility using Probe Vehicle Data

Kamyab

Remias

Najmi

et al. 2020

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

The aim of deploying intelligent transportation systems (ITS) is often to help engineers and operators identify traffic congestion. The future of ITS-based traffic management is the prediction of traffic conditions using ubiquitous data sources. There are currently well-developed prediction models for recurrent traffic congestion such as during peak hour. However, there is a need to predict traffic congestion resulting from non-recurring events such as highway lane closures. As agencies begin to understand the value of collecting work zone data, rich data sets will emerge consisting of historical work zone information. In the era of big data, rich mobility data sources are becoming available that enable the application of machine learning to predict mobility for work zones. The purpose of this study is to utilize historical lane closure information with supervised machine learning algorithms to forecast spatio-temporal mobility for future lane closures. Various traffic data sources were collected from 1,160 work zones on Michigan interstates between 2014 and 2017. This study uses probe vehicle data to retrieve a mobility profile for these historical observations, and uses these profiles to apply random forest, XGBoost, and artificial neural network (ANN) classification algorithms. The mobility prediction results showed that the ANN model outperformed the other models by reaching up to 85% accuracy. The objective of this research was to show that machine learning algorithms can be used to capture patterns for non-recurrent traffic congestion even when hourly traffic volume is not available.

show abstract

“…These applications analyze and fuse data from multiple sources to extract useful information or predictions that would otherwise be difficult to elicit. For example, traffic flow and incidents can be used to model and even predict future conditions (13)(14)(15). Similarly, safety research has used machine learning techniques to uncover hidden outcomes by fusing multiple data sources, such as land use and demographics (16)(17)(18).…”

Section: Introductionmentioning

confidence: 99%

Erroneous High Occupancy Vehicle Lane Data: Detecting Misconfigured Traffic Sensors With Machine Learning

Fournier

Farid

Patire

2022

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Quality data are vital to the planning and operation of traffic systems. High occupancy vehicle (HOV) lanes, for instance, must comply with federal performance standards. If an agency fails to meet the standards, the facility is considered to be “degraded” and the agency is required to undertake actions that would return the facility to satisfactory operation. This could include removing exempted vehicles (e.g., low-emission vehicles) or increasing toll prices and passenger occupancy limits. Such policy changes may be costly, and may affect related policy goals, such as promoting clean air vehicles. Owing to constant changes in the system (e.g., roadwork, system upgrades), some of the thousands of HOV sensors in California’s transportation system are misconfigured, such as being labeled as general-purpose lanes. In this situation, HOV lane data may be mistakenly aggregated with general-purpose lane data and vice versa, causing a HOV facility to be erroneously reported as degraded and requiring unnecessary policy action. Detecting these misconfigurations is challenging and labor-intensive to accomplish manually. The purpose of this research was to utilize machine learning techniques to detect sensor misconfigurations and to understand the extent to which they affect performance reporting of HOV lanes. The results for Caltrans District 7 (Los Angeles and Ventura counties) showed that about 5% to 8% of Performance Measurement System HOV sensors are misconfigured. Therefore approximately 27 to 44 mi of HOV lanes are erroneously measured, with approximately 10 to 16 mi (38%) of those reporting an erroneously high degradation rating.

show abstract

Evaluation of Interstate Work Zone Mobility using Probe Vehicle Data and Machine Learning Techniques

Cited by 3 publications

References 12 publications

Evaluation of Different Work Zone Road-Occupation Schemes for Monorail Construction

Evaluation of Different Work Zone Road-Occupation Schemes for Monorail Construction

Machine Learning Approach to Forecast Work Zone Mobility using Probe Vehicle Data

Erroneous High Occupancy Vehicle Lane Data: Detecting Misconfigured Traffic Sensors With Machine Learning

Contact Info

Product

Resources

About