Co-authored a Springer Nature book chapter on multimodal machine learning integrating text and image representations for classification tasks. Designed a hybrid architecture combining transformer-based NLP models and CNN-based image models using feature-level fusion. Implemented and evaluated models using multiple performance metrics including accuracy, precision, recall, and F1-score.

Conducting research on AI-driven biosensor frameworks for environmental toxin detection using synthetic data generation and hybrid machine learning models. Developing simulation-based training pipelines to address data scarcity and improve model generalization.