Masfiqur Rahaman

Rickshaw pullers are one of the most underserved communities in Bangladesh. Due to extreme exposure to heat and air pollutants, they are much more vulnerable to diseases such as heat strokes, heat exhaustion, respiratory illness, etc. However, there is little focus in literature on how environmental conditions (e.g., heat and air quality) impact the health of rickshaw pullers. In this study, we explore how different environmental parameters(e.g., temperature, humidity, particulate matters in the air, CO₂, CO, NO_x, SO₂, LPG, and O₃) influence the health of rickshaw pullers during the drive. We assess different health parameters which include weight, height, body temperature, electrodermal conductivity of the body, heart rate, and oxygen saturation.
Poster

Crowd management during Hajj pilgrimage at Mecca in Saudi Arabia represents the most challenging problem of its kind. Massive crowds, heavy concentration, significant foreign presence, stress on rescue personnel and planners all contribute to complex challenges. In this project, we are trying to design a complete real-time solution for massive scale crowd mobility management to assist related bodies in Saudi Arabia to enhance pilgrim safety. Specific project tasks are: a) design a novel and innovative crowd simulator platform to realistically simulate and manage massive scale crowds exclusively for Hajj scenarios; b) provide digitally assisted mechanisms for planners and rescuers to assess and react earlier to massive scale crowds; c) design an intelligent crowd guidance system with universally understood digital displays; and d) evaluate project outcomes with real crowds.
Publications: Applied Soft Computing 2022, IEEE Access 2021
Funding source: Ministry of Education, Saudi Arabia.

Derailments frequently occur in developing countries which results in massive loss of property along with lethal consequences. Devising a real-time automated system having long-range and low-cost sensing for detecting uprooted or faulty rail blocks to prevent derailments is strenuous. This particularly holds over the developing countries considering their low-resource and insufficient network infrastructure in remote areas where trains frequently run. However, existing studies in this regard are yet to present a pragmatic solution that handles a long distance of sensing coverage. Therefore, we are trying to build a multi-sensor fusion network to detect an incoming train from a distance of 1500 m. In parallel, we are developing a low-cost, long-range, and highly reliable mobile multi-hop networking scheme to successfully transmit data sensed from rail tracks to an approaching train at a distance of around 2000 m.
Publications: ICTD 2022
Funding source: ICT Division, Government of Bangladesh.

Recent advancements in traffic signaling serve the purpose of signal optimization in developed countries where traffic is solely lane-based and homogenous. Since, in Dhaka city, traffic is non-lane-based and heterogeneous, existing traffic signal optimization methods are not directly applicable. Therefore, in this project, we are investigating a computer vision-based traffic signal optimization technique using limited computational resources to comply with the needs of Dhaka city. Our tasks in this project includes a) constructing a large-scale traffic image dataset of Dhaka city; b) estimate various traffic states such as vehicle type (motorized or non-motorized), direction of flow, and count of traffic; c) develop metaheuristic algorithms to optimize traffic signals in a junction of Dhaka city; d) evaluate the performance of our developed technique in real scenarios.
Publications: ICDM 2021
Awards: ICT Fellowship 2021, Government of Bangladesh.