AI/ML Projects

Production-grade NLP microservice for real-time emotion classification with full-stack deployment

Built a complete AI application featuring a fine-tuned DistilRoBERTa Transformer for emotion classification, deployed as containerized microservices on Google Cloud Platform with automated CI/CD pipelines.

Key Features:

• Fine-tuned DistilRoBERTa Transformer for emotion classification
• FastAPI backend with async inference and performance caching
• React + Vite frontend with Tailwind CSS for real-time visualization
• Docker containerization with Cloud Run deployment
• Automated CI/CD via Firebase CLI and Google Cloud Build
• Environment-based CORS control and Pydantic validation

Technical Highlights:

• Low-latency, cloud-native AI product showcasing full-stack ML and MLOps
• Production-ready microservice architecture with scalable inference
• Integrated frontend-backend communication with real-time emotion outputs
• Complete DevOps pipeline from development to deployment

Tech Stack:

Deep learning model for automated tumor classification in medical imaging

Developed a convolutional neural network (CNN) model using TensorFlow and Keras for brain tumor classification in MRI scans, featuring data augmentation and Grad-CAM visualizations for medical interpretability.

Key Features:

• CNN architecture trained on brain MRI scans for tumor classification
• Data augmentation techniques for handling limited medical imaging datasets
• Grad-CAM visualizations for model interpretability in clinical settings
• Transfer learning implementation for improved performance
• Medical imaging preprocessing pipeline for DICOM format

Technical Highlights:

• Implemented custom data preprocessing for medical imaging data
• Applied regularization techniques to prevent overfitting
• Generated attention maps for clinical decision support
• Demonstrated potential for reducing diagnostic time in clinical workflows

Tech Stack:

Sequence-based classifier distinguishing enzymes from non-enzymes with high accuracy

Developed a bioinformatics machine learning pipeline using amino acid compositions and Biopython for protein sequence analysis, achieving 91% accuracy and 0.96 ROC-AUC score in enzyme classification.

Key Features:

• 91% classification accuracy with 0.96 ROC-AUC score
• Sequence-based classifier using amino acid compositions
• Biopython integration for protein sequence analysis
• Feature engineering from biological sequence properties
• Robust validation across different protein datasets

Technical Highlights:

• Advanced feature extraction from protein sequences
• Machine learning pipeline for biological data processing
• High-performance classification with excellent generalization
• Demonstrates expertise in computational biology applications

Tech Stack:

Natural Language Processing classifier to detect fake news using TF-IDF vectorization and Logistic Regression, with data leakage prevention techniques for improved model generalization.

Key Technologies:

Utilized clustering and dimensionality reduction techniques (PCA, K-Means, DBSCAN) to predict student performance and identify struggling students early for timely intervention.

Key Technologies:

End-to-end ML pipeline for diabetes risk prediction with class balancing techniques and hyperparameter tuning, transforming biomarkers into risk scores for early disease diagnosis.

Key Technologies: