top of page
Education
From my deep interest in interdisciplinary research - I have completed my undergraduate in Electrical and Electronic Engineering from KUET and my Master of Science in Biomedical Engineering – Research from CMU.
Master of Science
Biomedical Engineering – Research from Carnegie Mellon University
-
BME Research Excellence Award
Coursework
Machine Learning | Signal Processing
Mathematical Foundations for Machine Learning
Embarking on the fascinating journey of Machine Learning (ML), I delved into its mathematical underpinnings with Professor Gordon's guidance. This foundational course was a revelation, transforming ad-hoc learning into structured discovery and empowering me to thrive in advanced ML spheres with confidence.
Computational Foundations for Machine Learning
Progressing through the ML continuum, I explored its computational aspects, transitioning from theory to practice. This course was instrumental in honing my skills to craft ML algorithms from the ground up, fortifying my technical prowess and algorithmic fluency.
Introduction to Machine Learning
This PhD-level exploration deepened my understanding of the mathematical choreography behind prevalent ML algorithms. It was not merely an academic endeavor but an intellectual one that taught me the artistry involved in the conception of new algorithmic paradigms.
Convex Optimization
Fueled by curiosity from my ML studies, I ventured into the mathematical landscape of optimization. CMU's course on Convex Optimization provided an intuitive grasp of the subject, enriching my perspective and proving invaluable in formulating the mathematical narrative of my research.
"Fun"-damentals of MRI and Neuroimaging Analysis
Venturing beyond the realm of deep learning in medical imagery, I immersed myself in the intricate world of MRI. Under Professor Sossena Wood's mentorship, I not only mastered the intricacies of MRI technology but also embarked on a hands-on project unraveling the neural correlates of simulated emotions.
Biomedical Optical Imaging
The exploration of Biomedical Optical Imaging's physical principles laid a concrete foundation for my thesis instrumentation development. It was a journey through the nuances of light and its biomedical applications, broadening my understanding of imaging technologies.
Introduction to Biomedical Imaging
This cornerstone BME course acted as a conduit to the multifaceted world of biomedical imaging modalities. It enriched my previous experiences with MRI, NIRS, and CT, providing a comprehensive perspective crucial for my interaction with diverse imaging technologies.
Biostatistics
At the intersection of biology, engineering, and statistics, I found a rigorous framework for data interpretation. The course illuminated various statistical methodologies, equipping me with the acumen for hypothesis testing, clustering, classification, and survival analysis in complex biological contexts.
Advanced Physiology
A serendipitous requirement, Advanced Physiology expanded my intellectual horizon beyond the cerebral focus. The culmination of this course left me with a profound appreciation of the human body's complexity and the intricate systems at play within it.
Introduction to Neural Engineering
With a backdrop of signal processing, this course provided a fresh lens to view the nervous system through the principles of engineering. It dovetailed with my core imaging courses, enhancing my grasp of neuroscience applications in my MS research.
Mathematical Foundations for Machine Learning
Embarking on the fascinating journey of Machine Learning (ML), I delved into its mathematical underpinnings with Professor Gordon's guidance. This foundational course was a revelation, transforming ad-hoc learning into structured discovery and empowering me to thrive in advanced ML spheres with confidence.
Computational Foundations for Machine Learning
Progressing through the ML continuum, I explored its computational aspects, transitioning from theory to practice. This course was instrumental in honing my skills to craft ML algorithms from the ground up, fortifying my technical prowess and algorithmic fluency.
Introduction to Machine Learning
This PhD-level exploration deepened my understanding of the mathematical choreography behind prevalent ML algorithms. It was not merely an academic endeavor but an intellectual one that taught me the artistry involved in the conception of new algorithmic paradigms.
Convex Optimization
Fueled by curiosity from my ML studies, I ventured into the mathematical landscape of optimization. CMU's course on Convex Optimization provided an intuitive grasp of the subject, enriching my perspective and proving invaluable in formulating the mathematical narrative of my research.
"Fun"-damentals of MRI and Neuroimaging Analysis
Venturing beyond the realm of deep learning in medical imagery, I immersed myself in the intricate world of MRI. Under Professor Sossena Wood's mentorship, I not only mastered the intricacies of MRI technology but also embarked on a hands-on project unraveling the neural correlates of simulated emotions.
Biomedical Optical Imaging
The exploration of Biomedical Optical Imaging's physical principles laid a concrete foundation for my thesis instrumentation development. It was a journey through the nuances of light and its biomedical applications, broadening my understanding of imaging technologies.
Introduction to Biomedical Imaging
This cornerstone BME course acted as a conduit to the multifaceted world of biomedical imaging modalities. It enriched my previous experiences with MRI, NIRS, and CT, providing a comprehensive perspective crucial for my interaction with diverse imaging technologies.
Biostatistics
At the intersection of biology, engineering, and statistics, I found a rigorous framework for data interpretation. The course illuminated various statistical methodologies, equipping me with the acumen for hypothesis testing, clustering, classification, and survival analysis in complex biological contexts.
Advanced Physiology
A serendipitous requirement, Advanced Physiology expanded my intellectual horizon beyond the cerebral focus. The culmination of this course left me with a profound appreciation of the human body's complexity and the intricate systems at play within it.
Introduction to Neural Engineering
With a backdrop of signal processing, this course provided a fresh lens to view the nervous system through the principles of engineering. It dovetailed with my core imaging courses, enhancing my grasp of neuroscience applications in my MS research.
Monte Carlo
simulation
I used Monte Carlo simulation with different levels of melanin to better understand how much influence melanin (a skin pigment) has on the Near Infrared Spectroscopy signal quality.
The simulation is also targeted in different metrics that NIRS measurements can offer.
This simulation paves the way to design the experiment with human data in NIRS.
The simulation is also targeted in different metrics that NIRS measurements can offer.
This simulation paves the way to design the experiment with human data in NIRS.
Hardware development
The air gap between the scalp and the optode is one of the most critical issues in NIRS. This gap differs with different hair types, causing a major problem and making the NIRS less accessible.
I worked with Alexis, a fantastic undergraduate student at CMU, to create several prototypes of this novel optode scalp interface that will make NIRS technology more accessible. The design is now in its final iteration.
I worked with Alexis, a fantastic undergraduate student at CMU, to create several prototypes of this novel optode scalp interface that will make NIRS technology more accessible. The design is now in its final iteration.
Signal processing
The majority of the research was devoted to analysing the data in order to better understand the bias in the signal - there were numerous questions to be answered, ranging from how do you define signal quality to whether the bias is wavelength dependent. I researched all of the questions for multiple metrics.
This analysis reveals which metrics have biases and which do not. This characterization work then paved the way for future work to reduce NIRS signal bias.
This analysis reveals which metrics have biases and which do not. This characterization work then paved the way for future work to reduce NIRS signal bias.
Grant writing and IRB documentation
This is one of the pillars of my MS journey here at CMU. Based on my research, we wrote a grant application to the Pennsylvania Infrastructure Technology Alliance (PITA) and were funded by them (along with the existing funding from Meta reality labs and CMU-Africa).
This project also paves the way for future grant work aimed at a broader intersection of bias in other modalities, such as pulse oximetry.
I worked on the IRB documentation in the same genre. This was essential for my experiment. The complexities of these writings taught me a new way to think about research - not just from a project standpoint - and how a research can be impactful and have overarching goals while adhering to strict protocol.
This project also paves the way for future grant work aimed at a broader intersection of bias in other modalities, such as pulse oximetry.
I worked on the IRB documentation in the same genre. This was essential for my experiment. The complexities of these writings taught me a new way to think about research - not just from a project standpoint - and how a research can be impactful and have overarching goals while adhering to strict protocol.
Bachelor of Science
Electrical and Electronic Engineering from Khulna University of Engineering and Technology
Coursework
Awards
Synergic Activities
Signal processing
Presentations
bottom of page