I'm building applied machine learning projects, including Pulmonary Diagnostics AI, a PyTorch DenseNet-121 pipeline for detecting COVID-19, Tuberculosis, and Viral Pneumonia from chest radiographs with 98% accuracy.
I improved the model with CLAHE image enhancement, torchvision augmentation, and Optuna hyperparameter optimization using stratified 3-fold cross-validation. I also built and deployed a Gradio interface on Hugging Face Spaces, using CLIP as a zero-shot validator for out-of-distribution images.
For Melbourne Rainfall Prediction, I developed Logistic Regression, Random Forest, and XGBoost models that achieved 84.6% accuracy and a 0.66 F1-score. I'm pursuing a BSc in Computer Science with a major in Machine Learning and Artificial Intelligence at the University of London.
