Md Hishamur Rahman

Enhancing Underutilized Bus Routes with Advance Reservations and Semiflexible Routing

We introduced a novel approach where bus riders provide advance notice of their stops, allowing buses to skip unrequested stops and take shortcuts. This method increases stop density, reduces walking distances to and from bus stops, and maintains operational efficiency. To design this system, we developed optimization models that maximize the number of stops while adhering to tour duration and arrival time constraints. A case study in Allegany County, Maryland, demonstrates significant enhancements for routes that were both underutilized and had layouts conducive to substantial shortcuts.

Paper: https://doi.org/10.1287/trsc.2024.0561

Linear regression coupled Wasserstein generative adversarial network for direct demand modeling of ride-hailing trips in Chicago and Austin

While modern machine learning techniques enhance the predictive accuracy of zone-to-zone direct demand models, they often lack inference ability due to complex structures and are limited by small sample sizes of fixed origin-destination (OD) pairs. To address these issues, a linear regression coupled Wasserstein generative adversarial network (LR-WGAN) is proposed, combining linear explanatory components with non-linear patterns to improve prediction accuracy by generating additional OD data. This model has shown significant improvement in predicting OD ride-hailing demand in Chicago and Austin and allows for inference on the relationship between demand and predictor variables.

Paper: https://doi.org/10.1080/19427867.2024.2372944

Integrating dial-a-ride with transportation network companies for cost efficiency: A Maryland case study

Funded by: National Science Foundation (#2055347 )

In this paper, we explored outsourcing outlier trips to transportation network companies (TNCs) in Dial-a-ride (DAR) operations, using a two-stage solution framework based on integer programming and improvement heuristic, which achieved cost reductions of 7%-13% for a medium-sized DAR operator in Maryland.

Paper: https://doi.org/10.1016/j.tre.2023.103140

Developing Multi-task Learning Models for Short-term Forecasting in Taxi and Ride-hailing System

Funded by: Miyan Research Institute, IUBAT

Ride-hailing companies require accurate spatio-temporal forecasting of both demand and supply-demand gap to reduce passenger waiting times, minimize driver search friction, and ensure efficient service management. However, such forecasting is challenging due to strong spatio-temporal dependencies and, in many cases, the lack of explicit spatial adjacency information arising from confidentiality and privacy constraints. Furthermore, designing spatio-temporal forecasting models separately in a task-wise and city-wise manner to forecast demand and supply-demand gap in a ride-hailing system poses a burden for the expanding transportation network companies. To address these issues, two complementary deep learning architectures are proposed. First, a spatio-temporal model integrating a feature importance layer, a one-dimensional convolutional neural network (CNN), and a zone-distributed independently recurrent neural network (IndRNN) is introduced to handle anonymized spatial data. Second, a multi-task learning framework, GESME-Net, is proposed to simultaneously predict demand and supply-demand gap across different tasks and cities. This framework employs a gated ensemble of spatio-temporal mixture of experts network integrating a convolutional recurrent neural network (CRNN), CNN, and recurrent neural network (RNN), as well as a task adaptation layer that reveals feature contributions while learning a joint representation for multi-task learning.

Paper 1: doi.org/10.1049/itr2.12073
Paper 2: doi.org/10.1016/j.multra.2024.100166

A Bivariate Ordered Choice Model for the Use of Motorcycle and Car Ridesourcing

Ridesourcing is becoming a popular mode of transportation in many countries around the world, including developing countries like Bangladesh. Previous studies have mostly focused on the behavioral choice models of car ridesourcing, while the factors affecting the choice between car and motorcycle ridesourcing services remains unexplored. To better understand the influence of socio-economic and demographic features on the joint frequency of using motorcycle and car ridesourcing, this research was conducted based on the data collected through questionnaire at key locations in Dhaka city, the capital of Bangladesh. A bivariate ordered probit model was developed for the usage of motorcycle and car ridesourcing to find their respective correlation with various socio-economic and demographic factors. The outcomes indicate that people with certain types of socio-demographic background prefer to use motorcycle over car for ride-sourcing and vice-versa. The result also shows that gender, household density, income, educational qualification, smart-phone usage have a positive impact on the frequent use of ride-services for both motorbikes and cars. The outcomes are expected to provide useful insights to the ride-sourcing service providers, transport agencies and policy makers of Bangladesh in understanding the choice behaviors from the ride-sourcing user perspectives.

Paper: https://doi.org/10.1016/j.trip.2021.100492

Understanding Pedestrian Bridge Usage considering Perception and Socio-demographic Characteristics of the Road Users in Dhaka City

Walking often involves crossing a road, where the chance of vehicle-pedestrian conflict increases. Footbridges are one of the engineering instruments that offer safety for pedestrians during road crossing avoiding any physical conflicts with pedestrians. However, the usage of pedestrian bridge is affected by several factors. This paper aims at finding the effect of socio-demographic factors and perception on the frequency of footbridge usage. Responses collected from 893 individuals at 10 footbridges in Dhaka are used to develop a Random Parameter Ordered Probit Model. Results suggest that people transitioning towards mid-age start using footbridge more, pursuing higher education helps to perceive the importance of footbridge and higher income and vehicle ownership cut footbridge usage significantly. From the perception of road users, when they acknowledge the safety and convenience of footbridge, they are more likely to use it frequently provided that safety enforcement is ensured. In contrast, road users perceive footbridge as a time inefficient infrastructure. Furthermore, road users in Bangladesh are found to be less prone towards bandwagon effect, indicating that the usage could be a habitual factor for them. The researchers suggest various policy implications in light of the outcomes, prior research and the current environment in and around the footbridges in Bangladesh. The results are expected to provide valuable insights to the transport agencies, policy makers and built environment experts in understanding footbridge usage in perspective of demography and psychology of the road users.

Paper: https://doi.org/10.1016/j.trip.2025.101384

Evaluation of Service Quality and Safety of Water Bus Services in Dhaka City from Commuters' Perspective

Water bus services can be considered as one of the means to avoid traffic congestion for cities surrounded by rivers/lakes. Bangladesh Inland Water Transport Corporation (BIWTC) recently launched a water bus service inside the capital Dhaka from Sadarghat to Gabtoli touching several locations through Buriganga and Turag rivers. However, the service is not yet frequently used due to several reasons related to service quality and safety issues, which is not explored by the concerned authority. Therefore, this study aims to evaluate the satisfaction level of the passengers on the service quality and safety of the water bus service in Dhaka city. A water bus service on Hatirjheel lake connecting several areas of Dhaka city is considered as the study area for this research. The satisfaction level on the service quality and safety is measured from the responses of a questionnaire survey conducted on 150 passengers using this route. Several multiple linear regression models are developed to correlate the respondents' socio-economic, demographic, travel characteristics and experiences with various aspects of service quality (i.e., cleanliness, comfort, punctuality & reliability, driver characteristics, and overall service quality) and safety issues (i.e., safety equipment, health facility, harassment, and overall safety). The findings of this study will help the BIWTC authority to take necessary measures for the successful implementation, continuation and expansion of water bus services.

Paper: link

A Comparative Analysis of Speed Variations among Different Lanes for Different Distances from the Point of Jaywalking Initiation

Jaywalking mostly occurs when a pedestrian crosses at the mid-block of the roads rather than designated crossing area. Oftentimes pedestrians start jaywalking even when the vehicles are not at safe distances from them. However, no study is apparently visible in the literature that focuses on the relationship among the initiation of jaywalking with speed differential of vehicles on different lanes and distances from the starting point of jaywalking. Therefore, this study aims to find whether there are differences of speed exists among vehicles on different lanes at a distance of 20m, 30m and 40m from the point of pedestrians initiate jaywalking. The study area is taken at a jaywalking location on Dhaka-Mymensingh highway, connecting the capital Dhaka city with a prime district Mymensingh. Required data is collected during peak and off-peak hours in weekdays and weekend. The variation of time and day of a week helps to identify whether the speed of the vehicles on different lanes and the initiation of jaywalking are affected by temporal phenomena. t-tests for both equal and unequal variances are utilized for finding the speed differences among vehicles on different lanes and different distances. Effect of the composition of vehicles on jaywalking is also investigated along with distance and lane position of the oncoming vehicles. The transportation engineers and policy makers associated with road safety will get an idea about the perception of the pedestrians' starting of jaywalking based on the differences of speed of the vehicles on different lanes along with consideration of distance, vehicle type, time and day of week. Based on these findings of this study they can fix different speed limit for different lanes, identify distance where to put road cautionary signs, and determine appropriate location of pedestrian-crossing to prevent pedestrians' jaywalking.

Paper: link

Spatial analysis of pedestrian crash risk exposure at the intersections of Dhaka city

Based on the comparison between observed and predicted pedestrian crashes, pedestrian risk exposures were quantified to identify vulnerable intersections for pedestrian crossing

Report abuse