At University of Petroleum & Energy Studies, I researched lithium-ion battery health prediction using the NASA B0005 EV dataset. I implemented LSTM and GRU models and engineered a hybrid LSTM-GRU architecture for State-of-Health forecasting.
In my brain tumor detection project, I evaluated FixMatch, Mean Teacher, and FlexMatch against a supervised ResNet-50 baseline using 10% labelled data. I also investigated a hybrid Mean Teacher and FixMatch approach.
I built an end-to-end machine learning pipeline to detect Parkinson's disease from speech biomarkers, including severity-stage classification. My other projects include a Python slang-translation CLI tool and a C++ Sierpiński Triangle renderer.
