Drexel University’s College of Computing & Informatics’ (CCI) Senior Project is a multi-term capstone experience involving in-depth study and application of computing and informatics. Students work in teams to develop a significant product requiring use of a development process that includes planning, specification, design, implementation, evaluation, and documentation. Projects are often conceived by external stakeholders who guide the requirements process and ultimately use the resulting application. Groups may be interdisciplinary with students from varied departments within Drexel’s College of Engineering and the Digital Media Program within the Westphal College of Media Arts & Design.
A competition was held on May 29 at 3675 Market Street, where CCI Senior Project teams gathered and presented their work to a judging panel comprised of CCI faculty, alumni and industry stakeholders.
The following teams and students were recognized as finalists for the 2023-24 academic year:
TEAM PROJECTS
1st Place
SecureHealth Penetration Test
Team Members: Neha Patel, Alexander Dragovits, Nickolas Kirtsos, Jared Pearlstein
Faculty Advisor: Thomas Heverin, PhD
Project Abstract: The purpose of this project is to identify potential vulnerabilities for a highly safe-guarded department at Drexel University. Additionally, we are looking to test the pre-existing safety measures to ensure that the sensitive data stored in this department is truly secure. Our intentions are to use a multitude of penetration tools and testing techniques to cover a large portion of the attack surface of this department.
Learn More
2nd Place
Botography
Team Members: Brandon Pero, Sully Jenkins, Richard Vo, Quan Ngo, Jack Hanes, Samprati Sinha
Faculty Advisor: Jeffrey Salvage
Project Abstract: With an estimated 55 percent of households actively gardening and the "cozy" genre of games growing in popularity, there are a small number of video games on the market catering to these combined interests. With Botography, players can explore a diverse world with obstacles to overcome. The game aims to give plant lovers the opportunity to explore this world at their own pace while facing challenges that require them to engage with their favorite hobby.
Learn More
3rd Place
Bloomberg ETF Data Capture
Team Members: Ryan Magilton, Kyle Steppe, Aaron Fuhrmann, Wei Ye, Alfredoni Saintclair, Hasham Tanveer
Faculty Advisor: Jeffrey Salvage
Project Abstract: Accurately collect additional data to help Bloomberg improve dividend forecasts, including specific company-level dividend policies and distribution schedule tables for ETFs.
Learn More
RESEARCH PROJECTS
1st Place
Comparative Analysis of the Vectorized Korn-Lambiotte and Stockham Fast Fourier Transforms: An Abstract Vector Machine Implementation
Team Members: Sultan Alsultan
Faculty Advisor: Jeremy Johnson, PhD
Project Abstract: Design efficient vectorized Stockham and Korn-Lambiotte FFTs for large vector length machines, implement them on an abstract vector machine, and compare their performance based on memory operations and vector arithmetic operations.
Learn More
2nd Place
Radiology Notes for Clinical Decision Support
Team Members: Xander Crawford
Faculty Advisor: Hegler Tissot, PhD
Project Abstract: In recent years the use of large language models (LLMs) in the clinical domain has enabled clinical decision support through the use of electronic medical records (EMRs). While these advancements have opened up the way for many complex tasks such as report coding, sentence classification, and summarization their impact on prediction tasks has been overshadowed. In this study, the ability of LLMs is evaluated with traditional processing techniques and models in binary prediction tasks of coronary atherosclerosis diagnosis and patient mortality using MIMIC IV radiology reports. It finds that XGBoost on a bag of words (BOW) dataset is competitive with a pre-trained RadBERT model.
Learn More
3rd Place
Estimating morphological parameter of galaxies
Team Members: Mathilda Nguyen
Faculty Advisor: Vasilis Gkatzelis, PhD
Project Abstract: In this thesis, we aim to filter out biases of Bayesian Neural Network trained on synthetically generated images of Low Surface Brightness Galaxies.
Learn More