Meet Myself

I am from Bangladesh, a country of six seasons in Asia. I received my UnderGrad degree from BUET. To make myself an expertise of Transportation Engineering, I joined UKy in Fall 17 to pursue my Masters.

Pastime

I really love to explore different places. I enjoy taking pictures of landscapes and posing in front of camera.You may call me narcissist, but I enjoy it

Presenting My Research at TRB 2018

The research titled 'Head-on crash probability estimation on two-lane undivided highway from vision-based classified trajectory'. It endeavors to to develop a model that estimates head-on crash probability from classified vehicle trajectory. The model formulation considered:drivers' overtaking decision (OD); and time-to-collision (TTC) on two-lane undivided highway. Drivers' overtaking decision was modeled using nonlinear random parameter multivariate binary logistic regression. It considered both traffic and drivers' characteristics (i.e. aggressiveness) variables. In contrast, TTC was determined using a new formulation adding vehicles' dynamic acceleration in consideration. Incorporation of overtaking importance factor (OIF) and crash frequency parameter (CFP) enabled the estimation of crash probability combining OD and TTC. Background subtraction technique along with Kalman filter was used to obtain vehicle trajectories from real-time video. Variable inputs required for calibrating the OD model were generated by constructing adjacency matrices among the vehicles. Exploiting these inputs, Metropolis-Hastings algorithm from Markov chain Monte Carlo (MCMC) method was applied to obtain calibrated parameters of the OD model for different types of vehicle. Calibration result showed that subject vehicle speed and the subject-opposing plays an important role in influencing the overtaking decision. Moreover, the study also found that bus has maximum crash probability.

On Going Research: Travel Time Reliability

Currently, I am involved with some projects on travel time reliability and congestion measure. The focus is to look at the reliability indices of Kentucky Road System as well as estimating minimum sample size for speed data to get a decent measure of congestion.