Mechanical Engineering, Machine learning, Energy, Sustainability, Design
Hello!
Welcome to my website. I am a Lecturer at the Department of Mechanical, Aerospace, and Nuclear Engineering at Rensselaer Polytechnic Institute (RPI), Troy, NY. I received my PhD from the same institute in Mechanical Engineering supervised by Prof. Matthew Adam Oehlschlaeger.
I have worked as a Research Aide at the Data Science and Lea Division of Argonne National Laboratory under the mentorship of Dr. Aniket Tekawade. Broadly, I am interested in automated instrumentation and sensing systmes. I develop nearest neighbors, random forest, neural network and support vector machine based frameworks for supervised learning of patterns from measurements to make experiments automated. As part of my PhD research I developed machine learning based gas sensing methods from THz and IR spectra. My current research interests include Intelligent automated environmental monitoring, climate change management and mitigation, scientific and applied machine learning, design optimization, energy, sustainability, and combustion.
Previously, I obtained my Master's degree from at Indiana University Purdue University Indianapolis, supervised by Prof. Mohamed Razi Nalim. I earned my Bachelor of Science in Mechanical Engineering from BUET, Bangladesh.
PhD in Mechanical Engineering, 2023
Rensselaer Polytechnic Institute
MS in Mechanical Engineering, 2018
Purdue University
BSc (Hons.) in Mechanical Engineering, 2014
Bangladesh University of Engineering and Technology
In this project, A deep learning model is trained on simulated absorbance spectra to recognize infrared spectra of up to three component mixture in a broad 400-4000 1/cm wavenumber range. The proposed model is capable of highlighting important frequencies for multi-gas sensing and probable cause for misclassification within a user defined frequency range.
In this project, A deep learning model is trained on simulated absorbance spectra to recognize THz spectra of up to eight component mixture in 220-330 GHz frequency range. The workflow proposed is capable of highlighting important frequencies for multi-gas sensing and probable cause for misclassification by the model.
In this project, A deep learning 1D-CNN based classifier is trained on simulated absorbance spectra to recognize VOC THz spectra in 220-330 GHz frequency range.
In this ongoing project, ML classifiers are trained on simulated absorbance spectra to recognize IR spectra in a broad frequency range.
Software for intelligently guiding X-ray fluorescence scans to regions of interest using a suite of ML-based clustering algorithms..
This code trains on simulated absorbance spectra to recognize measured THz spectra in the 220-330 GHz frequency range using several machine learning methods.
Characterization of THz spectra of compounds.
In this project, I implemented a seal plate and a some data acquisition systems to measure ignition delay of hydrocarbon fuels by a traversing and chemically reactive hot turbulent jet issued from a rotating pre-chamber.