Mohammad Miralinaghi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Mohammad Miralinaghi has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Abolfazl (Kouros) Mohammadian
University of Illinois Chicago
3 shared publications - Alireza Talebpour
Department of Civil and Environmental Engineering, University of Illinois at Urbana-Champaign, Urbana, IL
3 shared publications - Mohammadhosein Pourgholamali
Lyles School of Civil and Construction Engineering, Center for Connected and Automated Transportation, Purdue University, West Lafayette, IN 47907, USA
3 shared publications Samuel Labi
3 shared publications- Samuel Labi
Purdue Univ
3 shared publications Yingyan Lou
3 shared publications
Latest Publications
- Open Access
- 8 October 2026
- Published by Elsevier in Computer-Aided Civil and Infrastructure Engineering
- Vol. 52
Vehicle Trajectory Reconstruction in Long Work Zones Using a Vehicle Group Aware Physics–Behavior Informed Generative Framework
- 8 October 2026
- Published by Elsevier in Computer-Aided Civil and Infrastructure Engineering
- Vol. 52
Open AccessVehicle Trajectory Reconstruction in Long Work Zones Using a Vehicle Group Aware Physics–Behavior Informed Generative Framework
- Open Access
- 30 May 2026
- Published by Elsevier in SSRN Electronic Journal
Vehicle Trajectory Reconstruction in Long Work Zones Using a Vehicle Group Aware Physics–Behavior Informed Generative Framework
Trajectory reconstruction is a persistent challenge in vehicle trajectory analysis, particularly in long work-zone activity areas where tracking continuity is frequently disrupted by missing observations, camera jitter, and ID mismatch. Reliable recovery of missing trajectory segments for long gaps under varying prediction horizons and noisy conditions remains difficult for computer vision based data extraction systems. This study proposes a two-stage framework for missing vehicle trajectory reconstruction. First, a Graph Transformer-based model learns spatiotemporal dependencies from target and surrounding vehicle trajectories to generate multiple candidate reconstructions for each missing interval. Second, a refinement stage selects the final trajectory using physics- and behavior-guided consistency criteria. Two variants are developed: M1, which uses physics-based motion constraints, and M2, which further incorporates behavioral rules for more realistic car-following and lane-changing representation. A dynamic temporal window is used to adapt the reconstruction context to local motion conditions. The framework is evaluated across different prediction horizons and Gaussian noise levels using MSE, ADE, FDE, Plausibility Score, and Noise Robustness, and compared with benchmark methods. The results show that both proposed models outperform the baselines, with M2 yielding the strongest accuracy, robustness, and plausibility, especially under longer horizons and higher noise levels. Cross-dataset evaluation on the Work Zone, NGSIM, and HighD datasets provides promising evidence of cross-dataset robustness across heterogeneous traffic environments, while further validation is needed to establish full transferability under additional work-zone geometries and sensing conditions. The framework is practically applicable to both controlled masked gaps and real-world work-zone discontinuities.
- 30 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessVehicle Trajectory Reconstruction in Long Work Zones Using a Vehicle Group Aware Physics–Behavior Informed Generative Framework
Trajectory reconstruction is a persistent challenge in vehicle trajectory analysis, particularly in long work-zone activity areas where tracking continuity is frequently disrupted by missing observations, camera jitter, and ID mismatch. Reliable recovery of missing trajectory segments for long gaps under varying prediction horizons and noisy conditions remains difficult for computer vision based data extraction systems. This study proposes a two-stage framework for missing vehicle trajectory reconstruction. First, a Graph Transformer-based model learns spatiotemporal dependencies from target and surrounding vehicle trajectories to generate multiple candidate reconstructions for each missing interval. Second, a refinement stage selects the final trajectory using physics- and behavior-guided consistency criteria. Two variants are developed: M1, which uses physics-based motion constraints, and M2, which further incorporates behavioral rules for more realistic car-following and lane-changing representation. A dynamic temporal window is used to adapt the reconstruction context to local motion conditions. The framework is evaluated across different prediction horizons and Gaussian noise levels using MSE, ADE, FDE, Plausibility Score, and Noise Robustness, and compared with benchmark methods. The results show that both proposed models outperform the baselines, with M2 yielding the strongest accuracy, robustness, and plausibility, especially under longer horizons and higher noise levels. Cross-dataset evaluation on the Work Zone, NGSIM, and HighD datasets provides promising evidence of cross-dataset robustness across heterogeneous traffic environments, while further validation is needed to establish full transferability under additional work-zone geometries and sensing conditions. The framework is practically applicable to both controlled masked gaps and real-world work-zone discontinuities.
- Open Access
- 1 March 2026
- Published by MDPI AG in Urban Science
- Vol. 10 (3) , 132
Enhancing Transit Signal Priority Implementation Through a Multi-Perspective Analysis
Transit Signal Priority (TSP) enhances transit reliability by minimizing delays at signalized intersections, but its broader implementation is often hindered by organizational and procedural challenges. Although many studies have examined the technical performance of TSP systems, fewer have explored the organizational, regulatory, and procedural factors that affect their successful implementation. This study investigates TSP business procedures across multiple U.S. states by conducting structured interviews with key stakeholders and performing a SWOT (Strengths, Weaknesses, Opportunities, Threats) analysis. The study identified recurring barriers, including unclear leadership, staffing shortages, inconsistent permitting processes, incompatible equipment, and outdated infrastructure. In contrast, successful programs relied on regular interagency coordination, assigned TSP staff, centralized management, and simplified funding processes. We propose strategies such as assigning a lead agency, streamlining permitting through blanket procedures, shifting to cloud-based control systems, and linking grant funding to performance data.
- 1 March 2026
- Published by MDPI AG in Urban Science
- Vol. 10 (3) , 132
Open AccessEnhancing Transit Signal Priority Implementation Through a Multi-Perspective Analysis
Transit Signal Priority (TSP) enhances transit reliability by minimizing delays at signalized intersections, but its broader implementation is often hindered by organizational and procedural challenges. Although many studies have examined the technical performance of TSP systems, fewer have explored the organizational, regulatory, and procedural factors that affect their successful implementation. This study investigates TSP business procedures across multiple U.S. states by conducting structured interviews with key stakeholders and performing a SWOT (Strengths, Weaknesses, Opportunities, Threats) analysis. The study identified recurring barriers, including unclear leadership, staffing shortages, inconsistent permitting processes, incompatible equipment, and outdated infrastructure. In contrast, successful programs relied on regular interagency coordination, assigned TSP staff, centralized management, and simplified funding processes. We propose strategies such as assigning a lead agency, streamlining permitting through blanket procedures, shifting to cloud-based control systems, and linking grant funding to performance data.
- 1 June 2025
- Published by Illinois Center for Transportation
State Department of Transportation Support for Operationalizing Transit Signal Priority
Transit signal priority (TSP) systems have become an integral part of regional intelligent transportation systems integration. They modify signal operations to facilitate faster transit through intersections, improve transit service reliability, reduce delays, and enhance overall transit operational efficiency. Agencies are planning and implementing next-generation TSP systems. However, multifaceted challenges complicate TSP implementation, particularly in urban regions with high traffic density and multiple stakeholders. Exploring these challenges can help develop more efficient deployment strategies and improve system performance. This study’s researchers, therefore, examined TSP implementation challenges in the metropolitan Chicago area and interviewed stakeholders and experts from Illinois and other states to identify successes and obstacles in TSP deployment. They applied a thematic analysis and a non-negative matrix factorization method to identify key barriers. To prioritize these challenges, they developed a survey using the fuzzy analytic hierarchy process framework and had experts directly involved in TSP operations in the Chicago region participate in this survey. Study findings indicated that organizational factors—such as interagency coordination issues and labor shortages—are significant challenges. Regulatory and policy constraints, including the absence of standardized regional guidelines and concerns over equipment compatibility, further hinder TSP deployment. Financial constraints, particularly the reliance on fragmented funding sources, create uncertainty in project execution. Technological limitations, such as integration difficulties with legacy traffic control systems and the high costs of infrastructure upgrades, also impede implementation.
- 1 June 2025
- Published by Illinois Center for Transportation
State Department of Transportation Support for Operationalizing Transit Signal Priority
Transit signal priority (TSP) systems have become an integral part of regional intelligent transportation systems integration. They modify signal operations to facilitate faster transit through intersections, improve transit service reliability, reduce delays, and enhance overall transit operational efficiency. Agencies are planning and implementing next-generation TSP systems. However, multifaceted challenges complicate TSP implementation, particularly in urban regions with high traffic density and multiple stakeholders. Exploring these challenges can help develop more efficient deployment strategies and improve system performance. This study’s researchers, therefore, examined TSP implementation challenges in the metropolitan Chicago area and interviewed stakeholders and experts from Illinois and other states to identify successes and obstacles in TSP deployment. They applied a thematic analysis and a non-negative matrix factorization method to identify key barriers. To prioritize these challenges, they developed a survey using the fuzzy analytic hierarchy process framework and had experts directly involved in TSP operations in the Chicago region participate in this survey. Study findings indicated that organizational factors—such as interagency coordination issues and labor shortages—are significant challenges. Regulatory and policy constraints, including the absence of standardized regional guidelines and concerns over equipment compatibility, further hinder TSP deployment. Financial constraints, particularly the reliance on fragmented funding sources, create uncertainty in project execution. Technological limitations, such as integration difficulties with legacy traffic control systems and the high costs of infrastructure upgrades, also impede implementation.
- Open Access
- 24 December 2024
- Published by MDPI AG in Sustainability
- Vol. 17 (1) , 1
Sustainable Planning of Electric Vehicle Charging Stations: A Bi-Level Optimization Framework for Reducing Vehicular Emissions in Urban Road Networks
This paper proposes a decision-making framework for a multiple-period planning of electric vehicle (EV) charging station development. In this proposed framework, transportation planners seek to implement a phased provision of electric charging stations as well as repurposing gas stations at selected locations. The developed framework is presented as a bi-level optimization problem that determines the optimal electric charging network design while capturing the practical constraints and travelers’ decisions. The upper level minimizes overall vehicle CO emissions by selecting optimal charging stations and their capacities, while the lower-level models travelers’ choices of vehicle class (EV or conventional) and travel routes. A genetic algorithm is developed to solve this problem. The results of the numerical experiments describe the sensitive nature of EV market penetration rates in the urban traffic stream and overall vehicle CO emissions to EV charging station availability and capacity. The findings can assist transportation agencies in designing effective EV charging infrastructure by identifying optimal locations and capacities, as well as in creating policies to encourage EV use over time. This study supports broader efforts to reduce air pollution and promote sustainable transportation by promoting EV adoption in the long term.
- 24 December 2024
- Published by MDPI AG in Sustainability
- Vol. 17 (1) , 1
Open AccessSustainable Planning of Electric Vehicle Charging Stations: A Bi-Level Optimization Framework for Reducing Vehicular Emissions in Urban Road Networks
This paper proposes a decision-making framework for a multiple-period planning of electric vehicle (EV) charging station development. In this proposed framework, transportation planners seek to implement a phased provision of electric charging stations as well as repurposing gas stations at selected locations. The developed framework is presented as a bi-level optimization problem that determines the optimal electric charging network design while capturing the practical constraints and travelers’ decisions. The upper level minimizes overall vehicle CO emissions by selecting optimal charging stations and their capacities, while the lower-level models travelers’ choices of vehicle class (EV or conventional) and travel routes. A genetic algorithm is developed to solve this problem. The results of the numerical experiments describe the sensitive nature of EV market penetration rates in the urban traffic stream and overall vehicle CO emissions to EV charging station availability and capacity. The findings can assist transportation agencies in designing effective EV charging infrastructure by identifying optimal locations and capacities, as well as in creating policies to encourage EV use over time. This study supports broader efforts to reduce air pollution and promote sustainable transportation by promoting EV adoption in the long term.
- 20 August 2022
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2676 (10) , 708-721
Research on Features of Pedestrians Using Smartphones at Transit Stations Based on Social Force Model
The smartphone has become nearly indispensable in people’s daily lives. Prevalent smartphone usage can be observed on various occasions, even during walking. However, pedestrians’ perception of their surroundings may decline because they are absorbed by using the smartphone. The behavior of pedestrians using smartphones while walking at transit stations can be viewed as disturbance to pedestrian flows, thereby reducing the efficiency of station operation or even creating safety problems. This study seeks to describe such behavioral features mathematically and provide relevant implications for transit station design. Based on the social force model, the parameters reflecting the effect of smartphone usage on the perceived driving and repulsive forces are added and calibrated. By extracting trajectory data from the videos filmed in the field, the genetic algorithm is employed for the calibration process to minimize the gaps between the actual and projected trajectories. Two sets of parameter settings, for pedestrians with and without using smartphones, are determined and further applied to microscopic pedestrian simulation for a transfer station of the metro system in Taipei, Taiwan. The results indicate that pedestrians using smartphones are more prone to being affected by other pedestrians, revealing that their velocities are relatively unstable, while they need longer relaxation time to attain their desired walking statuses. The simulation results also visualize the potential bottlenecks in the station, where smartphone users may become obstacles to other pedestrians and increase the congestion level, highlighting the importance of incorporating the behavior modeling of pedestrians using smartphones into transit station design.
- 20 August 2022
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2676 (10) , 708-721
Research on Features of Pedestrians Using Smartphones at Transit Stations Based on Social Force Model
The smartphone has become nearly indispensable in people’s daily lives. Prevalent smartphone usage can be observed on various occasions, even during walking. However, pedestrians’ perception of their surroundings may decline because they are absorbed by using the smartphone. The behavior of pedestrians using smartphones while walking at transit stations can be viewed as disturbance to pedestrian flows, thereby reducing the efficiency of station operation or even creating safety problems. This study seeks to describe such behavioral features mathematically and provide relevant implications for transit station design. Based on the social force model, the parameters reflecting the effect of smartphone usage on the perceived driving and repulsive forces are added and calibrated. By extracting trajectory data from the videos filmed in the field, the genetic algorithm is employed for the calibration process to minimize the gaps between the actual and projected trajectories. Two sets of parameter settings, for pedestrians with and without using smartphones, are determined and further applied to microscopic pedestrian simulation for a transfer station of the metro system in Taipei, Taiwan. The results indicate that pedestrians using smartphones are more prone to being affected by other pedestrians, revealing that their velocities are relatively unstable, while they need longer relaxation time to attain their desired walking statuses. The simulation results also visualize the potential bottlenecks in the station, where smartphone users may become obstacles to other pedestrians and increase the congestion level, highlighting the importance of incorporating the behavior modeling of pedestrians using smartphones into transit station design.
- 1 September 2021
- Published by American Society of Civil Engineers (ASCE) in Journal of Infrastructure Systems
- Vol. 27 (3) , 04021011
Repositioning Shared Urban Personal Transport Units: Considerations of Travel Cost and Demand Uncertainty
Operators of personal transport units (PTUs) face the challenge of intelligently balancing the locational demand and supply of PTUs in order to mitigate surpluses or deficits at PTU pickup stations. To accomplish this goal, operators need to be able to reliably predict the spatial distribution of PTU demand and to optimize the distributional allocation of resources to meet this demand. This paper proposes a three-step mathematical programming approach that addresses PTU supply vehicle routing and PTU repositioning that minimize the weighted total travel costs and unmet user demand. The methodology combines discrete wavelet transform (DWT) and artificial neural network (ANN) techniques to predict the demand at PTU stations, considers travel cost and unmet user demand in a multiobjective model and solves it with a multiobjective coevolutionary algorithm (MOCA), and incorporates the demand uncertainty to ensure robustness of the optimal repositioning and routing strategy for all the PTU stations. The paper demonstrated the proposed approach using real-world bicycle-sharing data from Nanjing, China, and showed that the proposed approaches for demand prediction (DWT-ANN) and optimization (MOCA) significantly produce superior results compared with traditional methods. Sensitivity analysis demonstrated the robustness of the proposed approaches.
- 1 September 2021
- Published by American Society of Civil Engineers (ASCE) in Journal of Infrastructure Systems
- Vol. 27 (3) , 04021011
Repositioning Shared Urban Personal Transport Units: Considerations of Travel Cost and Demand Uncertainty
Operators of personal transport units (PTUs) face the challenge of intelligently balancing the locational demand and supply of PTUs in order to mitigate surpluses or deficits at PTU pickup stations. To accomplish this goal, operators need to be able to reliably predict the spatial distribution of PTU demand and to optimize the distributional allocation of resources to meet this demand. This paper proposes a three-step mathematical programming approach that addresses PTU supply vehicle routing and PTU repositioning that minimize the weighted total travel costs and unmet user demand. The methodology combines discrete wavelet transform (DWT) and artificial neural network (ANN) techniques to predict the demand at PTU stations, considers travel cost and unmet user demand in a multiobjective model and solves it with a multiobjective coevolutionary algorithm (MOCA), and incorporates the demand uncertainty to ensure robustness of the optimal repositioning and routing strategy for all the PTU stations. The paper demonstrated the proposed approach using real-world bicycle-sharing data from Nanjing, China, and showed that the proposed approaches for demand prediction (DWT-ANN) and optimization (MOCA) significantly produce superior results compared with traditional methods. Sensitivity analysis demonstrated the robustness of the proposed approaches.