As a Biomedical Data Engineer/Scientist with the U.S. Air Force and a Ph.D. candidate at the University of North Dakota, my professional and academic journey has been deeply rooted in the intersection of data science, bioinformatics, and physics. Since March 2023, my role with the U.S. Air Force has revolved around advancing the field of human biodynamics through the development of innovative analytical tools and methodologies. My expertise lies in kinematic analysis, sensor data interpretation, and the design of data structures optimized for machine learning (ML) and experimental analysis.
One of my key contributions in this role has been the development of a specialized MATLAB script for calculating kinematic parameters from human biodynamics data. This tool stands out for its high-precision analytics capabilities, making a significant impact in the field. Furthermore, I created another MATLAB script for comparative sensor analysis, which has been pivotal in evaluating sensor accuracy and reliability by comparing sensor-generated data with theoretical kinematic values.
My work also involves extensive data manipulation and feature extraction, where I utilize Python libraries such as Pandas and NumPy for efficient data handling. In addition, I have a strong proficiency in data analysis and visualization, employing tools and libraries like Matplotlib and Seaborn to generate comprehensive visual reports and dashboards. These visualizations play a crucial role in interpreting complex biomedical data, facilitating better decision-making processes.
In the realm of machine learning, I have developed a Python-based predictive model for NiJ values, a critical tool for real-time analytics that has the potential to revolutionize our understanding of human biodynamics.
Parallel to my role in the U.S. Air Force, I have been pursuing my Ph.D. remotely at the University of North Dakota since March 2020. My research primarily focuses on analyzing the tumor microenvironment using histopathological images and epigenetic data. This involves collaborative work with Columbia University, where I am developing novel machine learning-based models using Python. My research achievements include computer vision-based identification and grading of diabetic retinopathy and analyzing the epigenetic mechanisms of SARS-CoV-2 and GFP+CSC-H460 tumor cells.
My work has also led to the creation of a new model for identifying cardiac abnormalities in 12-lead ECG recordings, significantly advancing the field of medical diagnostics. My academic and professional experiences demonstrate a strong commitment to leveraging data science and machine learning in the pursuit of groundbreaking discoveries in biomedicine and human health.