Asif Raihan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Asif Raihan has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Md Hadiuzzaman
Department of Civil Engineering, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh
9 shared publications - Moinul Hossain
Department of Civil and Environmental Engineering, Islamic University of Technology, Gazipur, Bangladesh
4 shared publications - Nazmul Haque
Accident Research Institute Bangladesh University of Engineering and Technology 1000 Dhaka Bangladesh
4 shared publications - A. F. S. Ahad Rahman Khan2 shared publications
- Faria Afrin Prova
Ahsanullah University of Science and Technology, Faculty of Engineering, Department of Civil Engineering, Dhaka, Bangladesh
2 shared publications - Muhtashim Shahrier2 shared publications
Latest Publications
- 29 October 2026
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
Novel Deep Learning Architecture for Modeling Crash Severity Using Satellite Imagery Considering Land Use and Geometry
Crash severity prediction has been significantly enhanced by deep learning (DL) techniques, which overcome the limitations of traditional statistical and machine learning models that rely on manually engineered features and fixed relationships. These conventional approaches often fail to account for the complex spatial and structural factors influencing crash severity. In contrast, convolutional neural networks (CNNs) can automatically extract hierarchical features from high-dimensional data, such as satellite imagery, allowing for more scalable and accurate analysis. However, most existing deep-learning-based models use a single-input architecture, which restricts the integration of multiple interacting factors. To address this limitation, this study introduces ArroNet42, a novel dual-branch CNN designed to classify crash severity into four categories—no crash, simple collision, injury crash, and fatal crash—by concurrently processing land use and road geometry imagery. The model demonstrates superior performance, achieving a validation accuracy of 80.8%, outperforming established architectures such as GoogleNet (73.3%), ResNet-50 (72.9%), EfficientNet-B0 (72.8%), and DarkNet-53 (72.2%), which were limited to single-input land use imagery. An extended model, ArroNet43, which integrates roadway curvature as an auxiliary numerical input, achieved a slightly lower validation accuracy (79.3%), suggesting that curvature-related spatial features are already implicitly learned from the imagery inputs. These results underscore the advantage of multi-branch DL architectures in capturing complex crash-related factors. ArroNet42 provides a robust framework for proactive safety analysis and supports data-driven interventions by reducing dependence on historical crash records.
- 29 October 2026
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
Novel Deep Learning Architecture for Modeling Crash Severity Using Satellite Imagery Considering Land Use and Geometry
Crash severity prediction has been significantly enhanced by deep learning (DL) techniques, which overcome the limitations of traditional statistical and machine learning models that rely on manually engineered features and fixed relationships. These conventional approaches often fail to account for the complex spatial and structural factors influencing crash severity. In contrast, convolutional neural networks (CNNs) can automatically extract hierarchical features from high-dimensional data, such as satellite imagery, allowing for more scalable and accurate analysis. However, most existing deep-learning-based models use a single-input architecture, which restricts the integration of multiple interacting factors. To address this limitation, this study introduces ArroNet42, a novel dual-branch CNN designed to classify crash severity into four categories—no crash, simple collision, injury crash, and fatal crash—by concurrently processing land use and road geometry imagery. The model demonstrates superior performance, achieving a validation accuracy of 80.8%, outperforming established architectures such as GoogleNet (73.3%), ResNet-50 (72.9%), EfficientNet-B0 (72.8%), and DarkNet-53 (72.2%), which were limited to single-input land use imagery. An extended model, ArroNet43, which integrates roadway curvature as an auxiliary numerical input, achieved a slightly lower validation accuracy (79.3%), suggesting that curvature-related spatial features are already implicitly learned from the imagery inputs. These results underscore the advantage of multi-branch DL architectures in capturing complex crash-related factors. ArroNet42 provides a robust framework for proactive safety analysis and supports data-driven interventions by reducing dependence on historical crash records.
- Open Access
- 30 March 2026
- Published by Politechnika Warszawska - Warsaw University of Technology in Archives of Transport
- Vol. 77 (1) , 131-146
Are paratransit users really different from active mode travelers for first and last mile connectivity: lesson learned from MRT users
Dhaka’s first mass rapid transit (MRT) system has marked a critical shift in the city’s public transport landscape, aiming to provide high-capacity, and reliable mobility. However, the effectiveness of this transportation mode depends on seamless first and last mile (FLM) connectivity. This study examines whether paratransit users differ meaningfully from active mode travelers in FLM connectivity for MRT system where paratransit like rickshaw is predominant. Using 1,513 valid home-interview responses, the research applies Principal Component Analysis (PCA) to extract three latent constructs, i.e., Travel Utility Perception, Travel Time & Cost Impact, and Socio-Demographic Profile. Structural Equation Modeling (SEM) is used to assess distinct models for walking and rickshaw as FLM modes. The findings reveal that the behavioral factors influencing paratransit use are closely aligned with those of active transport users, implying that in compact urban settings, paratransit may function as a substitute for active travel, potentially due to the lack of adequate walking and cycling infrastructure. Two models are then combined, referring to active FLM modes to investigate how their trip making behavior interact with each other. Key findings indicate that trip distance, fare sensitivity, time savings, and socio-economic status significantly influence FLM mode choice. The combined model of active travel yielded the best fit (RMSEA = 0.102; CFI = 0.848; TLI = 0.875), suggesting rickshaws function as pragmatic extensions of active travel rather than discrete modes. These results emphasize a continuum-based strategy for FLM planning that integrates rickshaw-friendly and walkable infrastructure to maximize accessibility and inclusivity along MRT corridors in built-up areas.
- 30 March 2026
- Published by Politechnika Warszawska - Warsaw University of Technology in Archives of Transport
- Vol. 77 (1) , 131-146
Open AccessAre paratransit users really different from active mode travelers for first and last mile connectivity: lesson learned from MRT users
Dhaka’s first mass rapid transit (MRT) system has marked a critical shift in the city’s public transport landscape, aiming to provide high-capacity, and reliable mobility. However, the effectiveness of this transportation mode depends on seamless first and last mile (FLM) connectivity. This study examines whether paratransit users differ meaningfully from active mode travelers in FLM connectivity for MRT system where paratransit like rickshaw is predominant. Using 1,513 valid home-interview responses, the research applies Principal Component Analysis (PCA) to extract three latent constructs, i.e., Travel Utility Perception, Travel Time & Cost Impact, and Socio-Demographic Profile. Structural Equation Modeling (SEM) is used to assess distinct models for walking and rickshaw as FLM modes. The findings reveal that the behavioral factors influencing paratransit use are closely aligned with those of active transport users, implying that in compact urban settings, paratransit may function as a substitute for active travel, potentially due to the lack of adequate walking and cycling infrastructure. Two models are then combined, referring to active FLM modes to investigate how their trip making behavior interact with each other. Key findings indicate that trip distance, fare sensitivity, time savings, and socio-economic status significantly influence FLM mode choice. The combined model of active travel yielded the best fit (RMSEA = 0.102; CFI = 0.848; TLI = 0.875), suggesting rickshaws function as pragmatic extensions of active travel rather than discrete modes. These results emphasize a continuum-based strategy for FLM planning that integrates rickshaw-friendly and walkable infrastructure to maximize accessibility and inclusivity along MRT corridors in built-up areas.
- 24 March 2026
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2680 (11) , 829-845
Public Transport and Harassment of Women: Synopsis
Harassment while using public transportation is an unpleasant but common occurrence for women who use public transport as their means of mobility. Despite the prevalence of harassment, the issue has not received sufficient attention in transportation planning and policy. In this research, we synthesize the existing literature on women’s harassment in public transportation, analyze key factors contributing to harassment, and propose policy recommendations to improve the current situation. This study also highlights how harassment remains a persistent issue in modern society, despite growing calls for equality and inclusivity. The findings emphasize the importance of addressing this challenge to support sustainable development and create safer, more equitable environments for all. Such factors as insufficient lighting, overcrowded transit, poorly organized bus stops, and difficulties during boarding and alighting are identified as significant contributors to harassment. Furthermore, the study highlights that victims often feel unsafe reporting incidents, owing to a lack of trust in authorities and social stigma. Fear of harassment negatively affects women’s mental, social, and personal well-being, limiting their mobility and participation in society. The paper concludes with the proposal of a 6Rs policy framework aimed at ensuring safe, secure, and efficient transportation for women, contributing to sustainable societal development.
- 24 March 2026
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2680 (11) , 829-845
Public Transport and Harassment of Women: Synopsis
Harassment while using public transportation is an unpleasant but common occurrence for women who use public transport as their means of mobility. Despite the prevalence of harassment, the issue has not received sufficient attention in transportation planning and policy. In this research, we synthesize the existing literature on women’s harassment in public transportation, analyze key factors contributing to harassment, and propose policy recommendations to improve the current situation. This study also highlights how harassment remains a persistent issue in modern society, despite growing calls for equality and inclusivity. The findings emphasize the importance of addressing this challenge to support sustainable development and create safer, more equitable environments for all. Such factors as insufficient lighting, overcrowded transit, poorly organized bus stops, and difficulties during boarding and alighting are identified as significant contributors to harassment. Furthermore, the study highlights that victims often feel unsafe reporting incidents, owing to a lack of trust in authorities and social stigma. Fear of harassment negatively affects women’s mental, social, and personal well-being, limiting their mobility and participation in society. The paper concludes with the proposal of a 6Rs policy framework aimed at ensuring safe, secure, and efficient transportation for women, contributing to sustainable societal development.
- 17 January 2026
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2680 (10) , 36-53
Do Riding Behavior, Speeding, and Law Adherence Differ between Professional and Nonprofessional Riders?
Bangladesh has experienced a rapid rise in motorcycle use in recent years. The surge in nonprofessional and professional riders is as a result of demand, ride-sharing opportunities, self-employment, and affordability. Although riding behavior is identified as one of the most influential precursors of motorcycle safety, there is little research comparing the riding behaviors of professional and nonprofessional riders. This study, therefore, aims to differentiate professional and nonprofessional riders based on their distinct riding behavior. Data from 624 motorcycle riders were collected via online and face-to-face questionnaire surveys in Dhaka. Following the feature selection through mean decrease accuracy and mean decrease Gini, this study developed a random forest (RF) model to delve deeper into riders’ behavior. Furthermore, the SHapley Additive exPlanations-based feature was employed to determine the differential factors like overtaking vehicles from the wrong side, carrying passengers without helmets, no speed reduction at intersections, and riding without proper fitness. In addition, this study focused on finding differences in the two rider groups’ law adherence, alertness, and speed behaviors. Consequently, this enables policymakers to design data-driven targeted safety measures that more effectively address the unique risks the two rider groups pose. The findings suggest targeted educational interventions, awareness campaigns, and effective and strict enforcement of the Road Transportation Act of 2018 to improve safety practices. It also recommends purpose-built technology-based solutions, such as the use of wearable smart glasses and AI-integrated speed cameras, as well as engineering-based solutions, such as separating traffic moving at varying speeds and separate lanes for motorcycles.
- 17 January 2026
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2680 (10) , 36-53
Do Riding Behavior, Speeding, and Law Adherence Differ between Professional and Nonprofessional Riders?
Bangladesh has experienced a rapid rise in motorcycle use in recent years. The surge in nonprofessional and professional riders is as a result of demand, ride-sharing opportunities, self-employment, and affordability. Although riding behavior is identified as one of the most influential precursors of motorcycle safety, there is little research comparing the riding behaviors of professional and nonprofessional riders. This study, therefore, aims to differentiate professional and nonprofessional riders based on their distinct riding behavior. Data from 624 motorcycle riders were collected via online and face-to-face questionnaire surveys in Dhaka. Following the feature selection through mean decrease accuracy and mean decrease Gini, this study developed a random forest (RF) model to delve deeper into riders’ behavior. Furthermore, the SHapley Additive exPlanations-based feature was employed to determine the differential factors like overtaking vehicles from the wrong side, carrying passengers without helmets, no speed reduction at intersections, and riding without proper fitness. In addition, this study focused on finding differences in the two rider groups’ law adherence, alertness, and speed behaviors. Consequently, this enables policymakers to design data-driven targeted safety measures that more effectively address the unique risks the two rider groups pose. The findings suggest targeted educational interventions, awareness campaigns, and effective and strict enforcement of the Road Transportation Act of 2018 to improve safety practices. It also recommends purpose-built technology-based solutions, such as the use of wearable smart glasses and AI-integrated speed cameras, as well as engineering-based solutions, such as separating traffic moving at varying speeds and separate lanes for motorcycles.
- Open Access
- 31 December 2025
- Published by Acadlore Publishing Services Limited in International Journal of Transport Development and Integration
- Vol. 9 (4) , 886-901
Assessing Quality of Boarding/Alighting Facility and Metro Stations Accessibility Incorporating Hybrid Cost Function
Mass Rapid Transit (MRT) systems play a critical role in promoting sustainable development, particularly in megacities. This study assesses the quality of boarding/alighting facilities along with accessibility of MRT, as integrated system components which is vital for maintaining a safe, efficient and user-friendly transit system, in the context of built-up cities. A robust questionnaire form is designed using 29 selected variables derived from pilot survey which was administerd to 1,397 respondents across nine operational stations of MRT in Dhaka, a developing megacity of Southeast Asia. Using the collected data, Gini Index and ANOVA are employed for variable prioritization. Machine Learning Algorithms, i.e., Random Forest (RF) Classifier, Support Vector Machine (SVM) and Classification and Regression Trees (CART), are compared to assess predictive performance where RF demonstrated better performance based on accuracy. Additionally, feature selection identified critical factors related to MRT trip performance, such as switching cost comparison, feeder service cost, inclusive service performance, customer loyalty, lighting near stations, overall comfort, security. This study, further, incorporates two most crucial factor, switching cost comparison and feeder service cost to a hybrid function, assessing system components and user transferability, utilizing a novel matrix-based approach. The study's conclusions provide insights into boarding/alighting facility and accessibility as system components incorporating hybrid cost function (HCF) to enhance the efficiency of MRT services in built-up cities across the world.
- 31 December 2025
- Published by Acadlore Publishing Services Limited in International Journal of Transport Development and Integration
- Vol. 9 (4) , 886-901
Open AccessAssessing Quality of Boarding/Alighting Facility and Metro Stations Accessibility Incorporating Hybrid Cost Function
Mass Rapid Transit (MRT) systems play a critical role in promoting sustainable development, particularly in megacities. This study assesses the quality of boarding/alighting facilities along with accessibility of MRT, as integrated system components which is vital for maintaining a safe, efficient and user-friendly transit system, in the context of built-up cities. A robust questionnaire form is designed using 29 selected variables derived from pilot survey which was administerd to 1,397 respondents across nine operational stations of MRT in Dhaka, a developing megacity of Southeast Asia. Using the collected data, Gini Index and ANOVA are employed for variable prioritization. Machine Learning Algorithms, i.e., Random Forest (RF) Classifier, Support Vector Machine (SVM) and Classification and Regression Trees (CART), are compared to assess predictive performance where RF demonstrated better performance based on accuracy. Additionally, feature selection identified critical factors related to MRT trip performance, such as switching cost comparison, feeder service cost, inclusive service performance, customer loyalty, lighting near stations, overall comfort, security. This study, further, incorporates two most crucial factor, switching cost comparison and feeder service cost to a hybrid function, assessing system components and user transferability, utilizing a novel matrix-based approach. The study's conclusions provide insights into boarding/alighting facility and accessibility as system components incorporating hybrid cost function (HCF) to enhance the efficiency of MRT services in built-up cities across the world.
- Open Access
CNN-Based Framework for Pedestrian Age and Gender Classification Using Far-View Surveillance in Mixed-Traffic Intersections
Pedestrian safety remains a pressing concern in congested urban intersections, particularly in low- and middle-income countries where traffic is multimodal, and infrastructure often lacks formal control. Demographic factors like age and gender significantly influence pedestrian vulnerability, yet real-time monitoring systems rarely capture this information. To address this gap, this study proposes a deep learning framework that classifies pedestrian age group and gender from far-view intersection footage using convolutional neural networks (CNNs), without relying on facial recognition or high-resolution imagery. The classification is structured as a unified six-class problem, distinguishing adult, teenager, and child pedestrians for both males and females, based on full-body visual cues. Video data was collected from three high-risk intersections in Dhaka, Bangladesh. Two CNN architectures were implemented: ResNet50, a deep convolutional neural network pretrained on ImageNet, and a custom lightweight CNN optimized for computational efficiency. Eight model variants explored combinations of pooling strategies and optimizers. ResNet50 with Max Pooling and SGD achieved the highest accuracy (86.19%), while the custom CNN performed comparably (84.15%) with fewer parameters and faster training. The model's efficient design enables real-time inference on standard surveillance feeds. For practitioners, this system provides a scalable, cost-effective tool to monitor pedestrian demographics at intersections using existing camera infrastructure. Its outputs can shape intersection design, optimize signal timing, and enable targeted safety interventions for vulnerable groups such as children or the elderly. By offering demographic insights often missing in conventional traffic data, the framework supports more inclusive, data-driven planning in mixed-traffic environments.
Open AccessCNN-Based Framework for Pedestrian Age and Gender Classification Using Far-View Surveillance in Mixed-Traffic Intersections
Pedestrian safety remains a pressing concern in congested urban intersections, particularly in low- and middle-income countries where traffic is multimodal, and infrastructure often lacks formal control. Demographic factors like age and gender significantly influence pedestrian vulnerability, yet real-time monitoring systems rarely capture this information. To address this gap, this study proposes a deep learning framework that classifies pedestrian age group and gender from far-view intersection footage using convolutional neural networks (CNNs), without relying on facial recognition or high-resolution imagery. The classification is structured as a unified six-class problem, distinguishing adult, teenager, and child pedestrians for both males and females, based on full-body visual cues. Video data was collected from three high-risk intersections in Dhaka, Bangladesh. Two CNN architectures were implemented: ResNet50, a deep convolutional neural network pretrained on ImageNet, and a custom lightweight CNN optimized for computational efficiency. Eight model variants explored combinations of pooling strategies and optimizers. ResNet50 with Max Pooling and SGD achieved the highest accuracy (86.19%), while the custom CNN performed comparably (84.15%) with fewer parameters and faster training. The model's efficient design enables real-time inference on standard surveillance feeds. For practitioners, this system provides a scalable, cost-effective tool to monitor pedestrian demographics at intersections using existing camera infrastructure. Its outputs can shape intersection design, optimize signal timing, and enable targeted safety interventions for vulnerable groups such as children or the elderly. By offering demographic insights often missing in conventional traffic data, the framework supports more inclusive, data-driven planning in mixed-traffic environments.
- Open Access
Modeling Chaotic Pedestrian Behavior Using Chaos Indicators and Supervised Learning
As cities around the world aim to improve walkability and safety, understanding the irregular and unpredictable nature of pedestrian behavior has become increasingly important. This study introduces a data-driven framework for modeling chaotic pedestrian movement using empirically observed trajectory data and supervised learning. Videos were recorded during both daytime and nighttime conditions to capture pedestrian dynamics under varying ambient and traffic contexts. Pedestrian trajectories were extracted through computer vision techniques, and behavioral chaos was quantified using four chaos metrics: Approximate Entropy and Lyapunov Exponent, each computed for both velocity and direction change. A Principal Component Analysis (PCA) was then applied to consolidate these indicators into a unified chaos score. A comprehensive set of individual, group-level, and contextual traffic features was engineered and used to train Random Forest and CatBoost regression models. CatBoost models consistently achieved superior performance. The best daytime PCA-based CatBoost model reached an R^2 of 0.8319, while the nighttime PCA-based CatBoost model attained an R^2 of 0.8574. SHAP analysis highlighted that features such as distance travel, movement duration, and speed variability were robust contributors to chaotic behavior. The proposed framework enables practitioners to quantify and anticipate behavioral instability in real-world settings. Planners and engineers can use chaos scores to identify high-risk pedestrian zones, apprise infrastructure improvements, and calibrate realistic microsimulation models. The approach also supports adaptive risk assessment in automated vehicle systems by capturing short-term motion unpredictability grounded in observable, interpretable features.
Open AccessModeling Chaotic Pedestrian Behavior Using Chaos Indicators and Supervised Learning
As cities around the world aim to improve walkability and safety, understanding the irregular and unpredictable nature of pedestrian behavior has become increasingly important. This study introduces a data-driven framework for modeling chaotic pedestrian movement using empirically observed trajectory data and supervised learning. Videos were recorded during both daytime and nighttime conditions to capture pedestrian dynamics under varying ambient and traffic contexts. Pedestrian trajectories were extracted through computer vision techniques, and behavioral chaos was quantified using four chaos metrics: Approximate Entropy and Lyapunov Exponent, each computed for both velocity and direction change. A Principal Component Analysis (PCA) was then applied to consolidate these indicators into a unified chaos score. A comprehensive set of individual, group-level, and contextual traffic features was engineered and used to train Random Forest and CatBoost regression models. CatBoost models consistently achieved superior performance. The best daytime PCA-based CatBoost model reached an R^2 of 0.8319, while the nighttime PCA-based CatBoost model attained an R^2 of 0.8574. SHAP analysis highlighted that features such as distance travel, movement duration, and speed variability were robust contributors to chaotic behavior. The proposed framework enables practitioners to quantify and anticipate behavioral instability in real-world settings. Planners and engineers can use chaos scores to identify high-risk pedestrian zones, apprise infrastructure improvements, and calibrate realistic microsimulation models. The approach also supports adaptive risk assessment in automated vehicle systems by capturing short-term motion unpredictability grounded in observable, interpretable features.
- Open Access
How does the Performance of the Data-driven Traffic Flow Forecasting Models deteriorate with Increasing Forecasting Horizon? An Extensive Approach Considering Statistical, Machine Learning and Deep Learning Models
With rapid urbanization in recent decades, traffic congestion has intensified due to increased movement of people and goods. As planning shifts from demand-based to supply-oriented strategies, Intelligent Transportation Systems (ITS) have become essential for managing traffic within existing infrastructure. A core ITS function is traffic forecasting, enabling proactive measures like ramp metering, signal control, and dynamic routing through platforms such as Google Maps. This study assesses the performance of statistical, machine learning (ML), and deep learning (DL) models in forecasting traffic speed and flow using real-world data from California's Harbor Freeway, sourced from the Caltrans Performance Measurement System (PeMS). Each model was evaluated over 20 forecasting windows (up to 1 hour 40 minutes) using RMSE, MAE, and R-Square metrics. Results show ANFIS-GP performs best at early windows with RMSE of 0.038, MAE of 0.0276, and R-Square of 0.9983, while Bi-LSTM is more robust for medium-term prediction due to its capacity to model long-range temporal dependencies, achieving RMSE of 0.1863, MAE of 0.0833, and R-Square of 0.987 at a forecasting of 20. The degradation in model performance was quantified using logarithmic transformation, with slope values used to measure robustness. Among DL models, Bi-LSTM had the flattest slope (0.0454 RMSE, 0.0545 MAE for flow), whereas ANFIS-GP had 0.1058 for RMSE and 0.1037 for flow MAE. The study concludes by identifying hybrid models as a promising future direction.
Open AccessHow does the Performance of the Data-driven Traffic Flow Forecasting Models deteriorate with Increasing Forecasting Horizon? An Extensive Approach Considering Statistical, Machine Learning and Deep Learning Models
With rapid urbanization in recent decades, traffic congestion has intensified due to increased movement of people and goods. As planning shifts from demand-based to supply-oriented strategies, Intelligent Transportation Systems (ITS) have become essential for managing traffic within existing infrastructure. A core ITS function is traffic forecasting, enabling proactive measures like ramp metering, signal control, and dynamic routing through platforms such as Google Maps. This study assesses the performance of statistical, machine learning (ML), and deep learning (DL) models in forecasting traffic speed and flow using real-world data from California's Harbor Freeway, sourced from the Caltrans Performance Measurement System (PeMS). Each model was evaluated over 20 forecasting windows (up to 1 hour 40 minutes) using RMSE, MAE, and R-Square metrics. Results show ANFIS-GP performs best at early windows with RMSE of 0.038, MAE of 0.0276, and R-Square of 0.9983, while Bi-LSTM is more robust for medium-term prediction due to its capacity to model long-range temporal dependencies, achieving RMSE of 0.1863, MAE of 0.0833, and R-Square of 0.987 at a forecasting of 20. The degradation in model performance was quantified using logarithmic transformation, with slope values used to measure robustness. Among DL models, Bi-LSTM had the flattest slope (0.0454 RMSE, 0.0545 MAE for flow), whereas ANFIS-GP had 0.1058 for RMSE and 0.1037 for flow MAE. The study concludes by identifying hybrid models as a promising future direction.
- Open Access
Trajectory-based real-time pedestrian crash prediction at intersections: A novel non-linear link function for block maxima led Bayesian GEV framework addressing heterogeneous traffic condition
This study develops a real-time framework for estimating pedestrian crash risk at signalized intersections under heterogeneous, non-lane-based traffic. Existing approaches often assume linear relationships between covariates and parameters, oversimplifying the complex, non-monotonic interactions among different road users. To overcome this, the framework introduces a non-linear link function within a Bayesian generalized extreme value (GEV) structure to capture traffic variability more accurately. The framework applies extreme value theory through the block maxima approach using post-encroachment time as a surrogate safety measure. A hierarchical Bayesian model incorporating both linear and non-linear link functions into GEV parameters is estimated using Markov Chain Monte Carlo simulation. It also introduces a behavior-normalized Modified Crash Risk (MRC) formula to account for pedestrians' habitual risk-taking behavior. Seven Bayesian hierarchical models were developed and compared using deviance information criterion. Models employing non-linear link functions for the location and scale parameters significantly outperformed their linear counterparts. The results revealed that pedestrian speed has a negative relationship with crash risk, while flow and speed of motorized vehicles, pedestrian flow, and non-motorized vehicles conflicting speed contribute positively. The MRC formulation reduced overestimation and provided crash predictions with 93% confidence. The integration of non-linear link functions enhances model flexibility, capturing the non-linear nature of traffic extremes. The proposed MRC metric aligns crash risk estimates with real-world pedestrian behavior in mixed-traffic environments. This framework offers a practical analytical tool for traffic engineers and planners to design adaptive signal control and pedestrian safety interventions before crashes occur.
Open AccessTrajectory-based real-time pedestrian crash prediction at intersections: A novel non-linear link function for block maxima led Bayesian GEV framework addressing heterogeneous traffic condition
This study develops a real-time framework for estimating pedestrian crash risk at signalized intersections under heterogeneous, non-lane-based traffic. Existing approaches often assume linear relationships between covariates and parameters, oversimplifying the complex, non-monotonic interactions among different road users. To overcome this, the framework introduces a non-linear link function within a Bayesian generalized extreme value (GEV) structure to capture traffic variability more accurately. The framework applies extreme value theory through the block maxima approach using post-encroachment time as a surrogate safety measure. A hierarchical Bayesian model incorporating both linear and non-linear link functions into GEV parameters is estimated using Markov Chain Monte Carlo simulation. It also introduces a behavior-normalized Modified Crash Risk (MRC) formula to account for pedestrians' habitual risk-taking behavior. Seven Bayesian hierarchical models were developed and compared using deviance information criterion. Models employing non-linear link functions for the location and scale parameters significantly outperformed their linear counterparts. The results revealed that pedestrian speed has a negative relationship with crash risk, while flow and speed of motorized vehicles, pedestrian flow, and non-motorized vehicles conflicting speed contribute positively. The MRC formulation reduced overestimation and provided crash predictions with 93% confidence. The integration of non-linear link functions enhances model flexibility, capturing the non-linear nature of traffic extremes. The proposed MRC metric aligns crash risk estimates with real-world pedestrian behavior in mixed-traffic environments. This framework offers a practical analytical tool for traffic engineers and planners to design adaptive signal control and pedestrian safety interventions before crashes occur.