Sami Hasnine
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sami Hasnine has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Khandker Nurul Habib
University of Toronto
7 shared publications Daud Nabi Hridoy
Charles E. Via, Jr. Department of Civil and Environmental Engineering, Virginia Tech, Blacksburg, VA
6 shared publicationsJustin Drummond
Howard University
3 shared publications- Justin Drummond
Department of Civil and Environmental Engineering, Howard University, Washington, DC
3 shared publications - André Romano Alho
Singapore-MIT Alliance for Research and Technology
2 shared publications - Arif Mohaimin Sadri
School of Civil Engineering and Environmental Science, University of Oklahoma, Norman, OK
2 shared publications
Latest Publications
- 23 May 2026
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
Express Lane Route Choice Under Real Time Information: Joint Revealed and Stated Preference Study
Express lanes (ELs) provide reliable travel times in exchange for a toll, which varies dynamically with time and affects travelers’ route choices. This study examines the effect of real time information on people’s route choices using a joint revealed and stated preference (SP) survey conducted in Charlotte, North Carolina, and Washington, D.C. The data was gathered using an online poll in July 2023, with 921 respondents from Charlotte, North Carolina, and 906 from Washington, D.C. To better understand the factors affecting the path choices of ELs, an exploratory data analysis was carried out. These factors included individual-specific characteristics, such as age, income, and gender, as well as trip purpose and urgency, tolls, and journey times. These data sets were used to estimate a dynamic discrete choice model to assess sequential route choices under real time information, capturing the travelers’ state-dependency and forward-looking behavior, where individuals optimize intertemporal payoffs while choosing a route based on SP situations. The discrete choice model reveals that individuals often choose tolled routes for significant travel time savings. Individuals aged 25–60 years are less likely to select the tolled route than those over 60. High-income households prefer tolls in Charlotte, North Carolina; the opposite trend is seen in the Washington, D.C. region. The model results show that individual route selections are influenced by trip urgency and by the relative toll and journey duration values. The results could be applied to the design of congestion pricing, taking into consideration travelers’ sequential decision-making behavior.
- 23 May 2026
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
Express Lane Route Choice Under Real Time Information: Joint Revealed and Stated Preference Study
Express lanes (ELs) provide reliable travel times in exchange for a toll, which varies dynamically with time and affects travelers’ route choices. This study examines the effect of real time information on people’s route choices using a joint revealed and stated preference (SP) survey conducted in Charlotte, North Carolina, and Washington, D.C. The data was gathered using an online poll in July 2023, with 921 respondents from Charlotte, North Carolina, and 906 from Washington, D.C. To better understand the factors affecting the path choices of ELs, an exploratory data analysis was carried out. These factors included individual-specific characteristics, such as age, income, and gender, as well as trip purpose and urgency, tolls, and journey times. These data sets were used to estimate a dynamic discrete choice model to assess sequential route choices under real time information, capturing the travelers’ state-dependency and forward-looking behavior, where individuals optimize intertemporal payoffs while choosing a route based on SP situations. The discrete choice model reveals that individuals often choose tolled routes for significant travel time savings. Individuals aged 25–60 years are less likely to select the tolled route than those over 60. High-income households prefer tolls in Charlotte, North Carolina; the opposite trend is seen in the Washington, D.C. region. The model results show that individual route selections are influenced by trip urgency and by the relative toll and journey duration values. The results could be applied to the design of congestion pricing, taking into consideration travelers’ sequential decision-making behavior.
- 7 May 2026
- Published by Elsevier in Journal of Transport & Health
- Vol. 49
Pedaling towards mental health: The role of biking in rural well-being
- 7 May 2026
- Published by Elsevier in Journal of Transport & Health
- Vol. 49
Pedaling towards mental health: The role of biking in rural well-being
- 24 February 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 316
Utility-informed neural networks for mode choice prediction: behaviorally constrained learning via utility gradients
- 24 February 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 316
Utility-informed neural networks for mode choice prediction: behaviorally constrained learning via utility gradients
- 1 January 2026
- Published by Canadian Science Publishing in Canadian Journal of Civil Engineering
- Vol. 53, 1-18
Factors affecting individuals’ travel mode choice in San Francisco Bay Area: a comparison between interpretable machine learning and econometric models
In this study, interpretable machine learning (ML) models and econometric models were compared to analyze individual travel mode choice behavior using data from the 2017 National Household Travel Survey in the San Francisco Bay Area. Two ML models, Random Forest (RF) and eXtreme Gradient Boosting (XGB), were implemented, along with three econometric models: Multinomial Logit, Nested Logit, and Cross-Nested Logit. Higher predictive accuracies of 0.853 for RF and 0.846 for XGB were achieved, particularly under class imbalance conditions. Model interpretability was ensured through the use of feature importance and Accumulated Local Effects plots. Promising temporal transferability was observed, as PM travel modes were accurately predicted using AM-trained models, with overall accuracies of 0.83 for RF and 0.83 for XGB, and balanced accuracies between 0.63 and 0.69. The findings indicate that the complementary strengths of ML and econometric approaches can enhance the understanding of travel behavior.
- 1 January 2026
- Published by Canadian Science Publishing in Canadian Journal of Civil Engineering
- Vol. 53, 1-18
Factors affecting individuals’ travel mode choice in San Francisco Bay Area: a comparison between interpretable machine learning and econometric models
In this study, interpretable machine learning (ML) models and econometric models were compared to analyze individual travel mode choice behavior using data from the 2017 National Household Travel Survey in the San Francisco Bay Area. Two ML models, Random Forest (RF) and eXtreme Gradient Boosting (XGB), were implemented, along with three econometric models: Multinomial Logit, Nested Logit, and Cross-Nested Logit. Higher predictive accuracies of 0.853 for RF and 0.846 for XGB were achieved, particularly under class imbalance conditions. Model interpretability was ensured through the use of feature importance and Accumulated Local Effects plots. Promising temporal transferability was observed, as PM travel modes were accurately predicted using AM-trained models, with overall accuracies of 0.83 for RF and 0.83 for XGB, and balanced accuracies between 0.63 and 0.69. The findings indicate that the complementary strengths of ML and econometric approaches can enhance the understanding of travel behavior.
- 1 January 2026
- Published by Canadian Science Publishing in Canadian Journal of Civil Engineering
- Vol. 53, 1-18
How did mobility choices evolve in the first year of the COVID-19 pandemic? Identifying the factors affecting mobility choices: a case study in New York City
This study aims to identify the factors affecting mobility choices (e.g., transit, car, and walk) during COVID-19 in New York City. Even though the COVID-19 pandemic evolved over time, most of the current studies heavily relied on cross-sectional datasets to understand individuals’ mobility choices. To address this gap, this study uses time-series and panel datasets and estimated aggregate and disaggregate level models to assess individuals’ mobility choices. The time-series model result reveals a negative correlation between public transit demand and grocery stores and residential activities during the pandemic. Also, walking demand increases with increased trips to transit stations, retail and recreational areas, and parks. The econometric model results show that employment status, reduced hours or pay cuts at the workplace, income, age, race, family size, and vehicle ownership are the factors that affect individuals’ mode-switching behavior during the pandemic. These models can be used for forecasting purposes in the post-pandemic era.
- 1 January 2026
- Published by Canadian Science Publishing in Canadian Journal of Civil Engineering
- Vol. 53, 1-18
How did mobility choices evolve in the first year of the COVID-19 pandemic? Identifying the factors affecting mobility choices: a case study in New York City
This study aims to identify the factors affecting mobility choices (e.g., transit, car, and walk) during COVID-19 in New York City. Even though the COVID-19 pandemic evolved over time, most of the current studies heavily relied on cross-sectional datasets to understand individuals’ mobility choices. To address this gap, this study uses time-series and panel datasets and estimated aggregate and disaggregate level models to assess individuals’ mobility choices. The time-series model result reveals a negative correlation between public transit demand and grocery stores and residential activities during the pandemic. Also, walking demand increases with increased trips to transit stations, retail and recreational areas, and parks. The econometric model results show that employment status, reduced hours or pay cuts at the workplace, income, age, race, family size, and vehicle ownership are the factors that affect individuals’ mode-switching behavior during the pandemic. These models can be used for forecasting purposes in the post-pandemic era.
- 10 December 2025
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2680 (8) , 523-541
Using Social Media to Model Community-Based Behavioral Response During Public Health Emergencies: A Case Study of the 2023 Canadian Wildfires
New York City (NYC) experienced severe air pollution from Canadian wildfires in June 2023, disrupting travel and daily activities. This study analyzed public reactions to evacuation, indoor activities, shopping, and recreation using geotagged X posts during the air pollution crisis. Geotagged posts were reverse geocoded to census blocks and spatially joined with socioeconomic and demographic data from the U.S. census and American Community Survey. The dataset initially comprised 0.59 million geotagged X posts from 66,858 unique users in NYC over a 1-week period. After relevance filtering, the final dataset included 10,258 posts from 10,258 unique users on wildfire-related travel and activity discussions. Public reactions were analyzed using a BERT-based natural language processing model, whereas a gender–race model inferred users’ gender and racial identities based on their first and last names. A multinomial logit model assessed how socioeconomic and demographic factors influenced activity discussions during the crisis. The findings revealed demographic differences in responses. For instance, females were less likely to discuss evacuation and essential trips, possibly owing to continued workplace operations despite hazardous conditions. Racial differences were also evident, with Asians more frequently mentioning evacuation and commuting, whereas African Americans showed lower engagement in discussions about social and recreational activities. Socioeconomic disparities further influenced response patterns, as lower-income and less-educated groups expressed fewer concerns about evacuation, highlighting potential barriers to crisis awareness and preparedness. These insights emphasize the need for targeted communication strategies and equitable health interventions to ensure that emergency responses effectively reach vulnerable populations during environmental crises.
- 10 December 2025
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2680 (8) , 523-541
Using Social Media to Model Community-Based Behavioral Response During Public Health Emergencies: A Case Study of the 2023 Canadian Wildfires
New York City (NYC) experienced severe air pollution from Canadian wildfires in June 2023, disrupting travel and daily activities. This study analyzed public reactions to evacuation, indoor activities, shopping, and recreation using geotagged X posts during the air pollution crisis. Geotagged posts were reverse geocoded to census blocks and spatially joined with socioeconomic and demographic data from the U.S. census and American Community Survey. The dataset initially comprised 0.59 million geotagged X posts from 66,858 unique users in NYC over a 1-week period. After relevance filtering, the final dataset included 10,258 posts from 10,258 unique users on wildfire-related travel and activity discussions. Public reactions were analyzed using a BERT-based natural language processing model, whereas a gender–race model inferred users’ gender and racial identities based on their first and last names. A multinomial logit model assessed how socioeconomic and demographic factors influenced activity discussions during the crisis. The findings revealed demographic differences in responses. For instance, females were less likely to discuss evacuation and essential trips, possibly owing to continued workplace operations despite hazardous conditions. Racial differences were also evident, with Asians more frequently mentioning evacuation and commuting, whereas African Americans showed lower engagement in discussions about social and recreational activities. Socioeconomic disparities further influenced response patterns, as lower-income and less-educated groups expressed fewer concerns about evacuation, highlighting potential barriers to crisis awareness and preparedness. These insights emphasize the need for targeted communication strategies and equitable health interventions to ensure that emergency responses effectively reach vulnerable populations during environmental crises.
- 4 October 2025
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2679 (12) , 549-577
Generative AI-based Adaptive Cruise Control Performance Evaluation in Car-Following Scenarios
This study introduces a novel generative AI-based adaptive cruise control (GenAI ACC) model for autonomous vehicles, utilizing a time generative adversarial networks (TimeGAN) framework to simulate car-following behavior. The model was developed and evaluated using OpenACC and Vanderbilt ACC datasets, comparing its performance against traditional PATH ACC and cooperative adaptive cruise control (CACC) systems across safety, flow stability, comfort, and emissions metrics. The GenAI ACC demonstrated significant improvements in several key areas, including safety, flow stability, comfort, and emissions. With regard to safety, it achieved reduced conflict durations and a 40% higher minimum time to collision in high oscillation scenarios compared with PATH ACC. The model maintained neutral flow stability (relative mean absolute deviation ≈ 1) across all scenarios, effectively minimizing speed disturbances. Concerning comfort, GenAI ACC limited jerk variations to ±2 m/s 3 , substantially outperforming PATH ACC’s 12 m/s 3 spikes in high oscillation scenarios. Most notably, it achieved 5–31% lower cumulative NO x emissions across all scenarios compared with both PATH ACC and PATH CACC. Although GenAI ACC has not yet matched the stability and comfort levels of PATH CACC, it offers a promising solution for autonomous vehicles by relying solely on onboard sensors, reducing vulnerability to cyberattacks and connectivity issues. This study highlights the potential of generative AI in bridging the gap between automated and connected automated systems, paving the way for safer, more efficient, and environmentally sustainable transportation.
- 4 October 2025
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2679 (12) , 549-577
Generative AI-based Adaptive Cruise Control Performance Evaluation in Car-Following Scenarios
This study introduces a novel generative AI-based adaptive cruise control (GenAI ACC) model for autonomous vehicles, utilizing a time generative adversarial networks (TimeGAN) framework to simulate car-following behavior. The model was developed and evaluated using OpenACC and Vanderbilt ACC datasets, comparing its performance against traditional PATH ACC and cooperative adaptive cruise control (CACC) systems across safety, flow stability, comfort, and emissions metrics. The GenAI ACC demonstrated significant improvements in several key areas, including safety, flow stability, comfort, and emissions. With regard to safety, it achieved reduced conflict durations and a 40% higher minimum time to collision in high oscillation scenarios compared with PATH ACC. The model maintained neutral flow stability (relative mean absolute deviation ≈ 1) across all scenarios, effectively minimizing speed disturbances. Concerning comfort, GenAI ACC limited jerk variations to ±2 m/s 3 , substantially outperforming PATH ACC’s 12 m/s 3 spikes in high oscillation scenarios. Most notably, it achieved 5–31% lower cumulative NO x emissions across all scenarios compared with both PATH ACC and PATH CACC. Although GenAI ACC has not yet matched the stability and comfort levels of PATH CACC, it offers a promising solution for autonomous vehicles by relying solely on onboard sensors, reducing vulnerability to cyberattacks and connectivity issues. This study highlights the potential of generative AI in bridging the gap between automated and connected automated systems, paving the way for safer, more efficient, and environmentally sustainable transportation.
- 14 September 2025
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2679 (12) , 340-354
Review of Mileage-Based User Fees for Sustainable Transportation Funding: Challenges, Opportunities, and Research Gaps
Decarbonization trends in the transportation sector through vehicle electrification, combined with the declining efficacy of the fuel tax, have necessitated sustainable transportation Funding solutions. One such solution is the mileage-based user fee (MBUF) or the vehicle miles traveled fee, which charges drivers based on distance traveled. Over the past decade, pilot programs and research reports have evaluated MBUF’s feasibility and benefits from diverse viewpoints. This paper provides a comprehensive review of the existing literature on MBUF, focusing on modeling and methodological aspects, incorporating empirical findings from technical reports and pilot programs, and comparing MBUF with other road pricing methods, particularly administrative costs, technological requirements, and interoperability across state boundaries and fee structures. Key areas of investigation include system-level impacts (such as revenue potential and rate setting) and individual-level impacts (such as equity and privacy). Equity considerations are further analyzed; that is, social (income- and demographic-based), geographic (rural versus urban), and modal equity. The review highlights the limited research on the long-term equity impacts of MBUF and the critical need to understand behavioral impacts under the evolving policy landscape. The challenges, opportunities, and research gaps associated with MBUF are discussed, emphasizing the need for data-driven behavioral models and a systematic approach to transportation Funding.
- 14 September 2025
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2679 (12) , 340-354
Review of Mileage-Based User Fees for Sustainable Transportation Funding: Challenges, Opportunities, and Research Gaps
Decarbonization trends in the transportation sector through vehicle electrification, combined with the declining efficacy of the fuel tax, have necessitated sustainable transportation Funding solutions. One such solution is the mileage-based user fee (MBUF) or the vehicle miles traveled fee, which charges drivers based on distance traveled. Over the past decade, pilot programs and research reports have evaluated MBUF’s feasibility and benefits from diverse viewpoints. This paper provides a comprehensive review of the existing literature on MBUF, focusing on modeling and methodological aspects, incorporating empirical findings from technical reports and pilot programs, and comparing MBUF with other road pricing methods, particularly administrative costs, technological requirements, and interoperability across state boundaries and fee structures. Key areas of investigation include system-level impacts (such as revenue potential and rate setting) and individual-level impacts (such as equity and privacy). Equity considerations are further analyzed; that is, social (income- and demographic-based), geographic (rural versus urban), and modal equity. The review highlights the limited research on the long-term equity impacts of MBUF and the critical need to understand behavioral impacts under the evolving policy landscape. The challenges, opportunities, and research gaps associated with MBUF are discussed, emphasizing the need for data-driven behavioral models and a systematic approach to transportation Funding.