Hello! This is Hisham! I am from Bangladesh, a beautiful country from South Asia, famous for its hospitality. I am a PhD student at Kahlert School of Computing, University of Utah. I am currently working in Dr. Shireen Elhabian's lab on image analysis, being co-advised by Dr. Edward DiBella on image reconstruction project in MRI. My focus is on MRI faster image acquisition and reconstruction.
I completed my undergraduation from Bangladesh University of Engineering and Technology with a BSc in Computer Science and Engineering. I worked at Optimizely, as a Software Engineer. Additionally, I was also an adjunct lecturer of CSE, BUET. Parallel to this, I have a keen interest in Applications in Deep Learning in Medical Imaging. Due to my outgoing personality and previous research experiences, I am also interested in Human-Computer Interaction.
As part of my undergrad thesis, I worked with Dr. Atif Hasan Rahman, Associate Professor, CSE, BUET, in the field of Deep Learning applications in Computation Biology. We explored the Gene Panel Design problem as a Machine Learning Feature Selection problem. In addition, I worked on two Exploratory Data Analysis-based research projects with Dr. Sriram Chellappan, Professor, Department of Computer Science and Engineering, University of South Florida and Dr. A.B.M. Alim Al Islam, Professor, CSE, BUET.
Here goes my departmental webpage. To view my publications, please visit my Google Scholar profile. Aside from my academic pursuits, travelling, running, and dancing has always been a great passion of mine. Additionally, I enjoy exploring new places and getting acquainted with diverse cultures.CGPA: 3.79/4.00
Last two semesters: 3.90
GPA: 5.00/5.00
GPA: 5.00/5.00
Coronavirus (COVID-19) pandemic has been the defining global health crisis. New policies need to be forged by policy-makers for various sectors such as trading, banking, education, etc., to lessen losses and to heal quickly. For efficient policy-making, in turn, some prerequisites needed are historical trend analysis on the pandemic spread, future forecasting, the correlation between the spread of the disease and various socio-economic and environmental factors, etc. Besides, all of these need to be presented in an integrated manner in real-time to facilitate efficient policy-making. Therefore, in this work, we developed a web-based integrated real-time operational dashboard as a one-stop decision support system for COVID-19. In our study, we conducted a detailed data-driven analysis based on available data from multiple authenticated sources to predict the upcoming consequences of the pandemic through rigorous modeling and statistical analyses. We also explored the correlations between disease spread and diverse socio-economic as well as environmental factors. Furthermore, we presented how the outcomes of our work can facilitate both contemporary and future policy-making.
Write your contributions in this para.
Methods: Mathematical Computing, Statistical AnalysisConference: COMPASS '22: ACM SIGCAS/SIGCHI Conference on Computing and Sustainable Societies (COMPASS)
A fundamental limitation of the emerging single-cell spatial transcriptomics (sc-ST) technologies is their panel size. Being based on fluorescence in situ hybridization, an sc-ST dataset can profile only a pre-determined panel of a few hundred genes. This often forces biologists to build panels from only the marker genes of different cell types and forgo other genes of interest, e.g., genes encoding ligand-receptor complexes or genes in specific pathways. We propose scGIST– a deep neural network that designs sc-ST panels through constrained feature selection. On four datasets, scGIST outperformed alternative methods in terms of cell type detection accuracy. Moreover, unlike other methods, scGIST allows genes of interest to be prioritized for inclusion in the panel while staying within the its size constraint. We demonstrate through diverse use cases that scGIST includes large fractions of prioritized genes without compromising cell type prediction efficacy making it a valuable addition to sc-ST’s algorithmic toolbox.
Methods: Feature Selection, Custom Loss Function Current state:
awaiting review addressing reviewer's comments (Venue: Genome Biology)
The details of individual feelings and how they change on social media before and during the epidemic are explored in our study. We thoroughly investigate the currently available libraries and their potential combinations in order to create a method that is more efficient than the frequently inadequate out-of-the-box sentiment-analyzing libraries for text posts for analyzing sentiments in Twitter text posts relevant to the pandemic. In addition to word posts, we also undertake a longitudinal bimodal exploratory data analysis utilizing image postings.
Methods: Sentiment Analysis, Bimodal CorrelationCurrent state: Submitted (Technological Forecasting and Social Change Journal)
Current state: Work in Progress (Supervised by s2e-lab, University Of Notre Dame)
I have got extended training on Git, Microservice, Docker, Basic AWS, Node, React, Clean Code Practises, etc. Currently, I have worked on a project of Angular to React Migration, in which me along with my team are converting the entire system's legacy Angular code base to React. Currently, I work in the Platform team where we define the coding policy of the system, address the system's old tech debts, and resolve any unattended bugs.
I used Cypress to write end-to-end Automated Tests for IEIMS that is going to be utilized by Secondary and Higher Secondary students all over Bangladesh through this endpoint.
My main role was to analyze the Android and iOS games' data followed by interpreting and spotting patterns, trends, and correlations in the data. I used Tableau and Google Data Studio for fetching and analyzing the data from their database.