Drosophila melanogaster motion patterns correlated to end of life proximity

Published in The journals of gerontology. Series A, Biological sciences and medical sciences, 2025

Falls are a leading cause of disability and mortality, with risk factors spanning aging, neurodegenerative diseases, and sarcopenia. Using Drosophila melanogaster as a model organism, this project developed an automated machine learning pipeline to quantify falls in aged and physiologically stressed flies.

Recommended citation: Mattins F, Nagrath S, Fan Y, Manea TKD, Das S, Shankar A, Tower J. Machine learning scoring reveals increased frequency of falls proximal to death in Drosophila melanogaster. J Gerontol A Biol Sci Med Sci. 2025 Feb 15:glaf029. doi: 10.1093/gerona/glaf029. Epub ahead of print. PMID: 39953997.
Paper | Code

Glaucoma Severity Prediction Using RETFound

Published in , 2024

Glaucoma is a leading cause of irreversible blindness, necessitating early and precise detection for effective intervention. This project focuses on developing a scalable and clinically deployable ML model for predicting glaucoma severity, leveraging RETFound, a foundation model based on the Vision Transformer (ViT) architecture.

Fatigue Detection Using Biological Markers & Time-Series Analysis

Published in , 2022

Developed a machine learning framework to detect fatigue in subjects by analyzing measurable biological parameters and their quantifiable responses over time.

Download Code

Anomaly Detection in Multivariate Time-Series Data using GANs

Published in , 2022

Developed a robust anomaly detection framework for multivariate time-series data, leveraging Generative Adversarial Networks (GANs) and time-series forecasting. The objective was to enhance the security of Advanced Metering Infrastructure (AMI) by identifying False Data Injection Attacks (FDIA) in network traffic logs.

Download Code