Education
The George Washington University
Master of Science in Computer Science
August 2024 - May 2026
Washington, D.C.
PES University
Bachelor of Technology in Computer Science and Engineering
December 2020 - May 2024
Banglore, India
Experience
Research Assistant
PES University
Trained and developed a Vision-Language Model to generate metaphorical interpretations from images, combining CNNs for image feature extraction and Transformer-based NLP models, integrating both visual and textual feature representations to analyze visual metaphors for multimodal metaphor detection.
June 2023 - August 2023
Banglore, India
Skills
- Python
- R
- SQL
- NumPy
- Pandas
- Matplotlib
- PyTorch
- TensorFlow
- scikit-learn
- Keras
- OpenCV
- Apache Spark
- Power BI
- Tableau
- MongoDB
- PostgreSQL
- Neo4j
Projects
BiLSTM-CNN With Attention For Remaining Useful Life Prediction In Turbofan Engines
Created a hybrid deep learning model combining BiLSTM, Transformer, and CNN architectures to estimate Remaining Useful Life (RUL) of aircraft engines using NASA C-MAPSS dataset. Incorporated CBAM attention to enhance focus on key sensor features, positional encoding to preserve temporal structure of sensor sequences, residual dilated convolutions to capture long-range dependencies, and transformer blocks for contextual sequence modeling.
- TensorFlow
- scikit-learn
Anomaly Detection in Surveillance Videos
A novel Multiple Instance Learning (MIL) based model architecture to classify surveillance video segments as anomalous or normal. Utilized the I3D feature extraction model to extract RGB and motion flow features. Achieved an Area Under the Curve (AUC) of 0.9022, demonstrating high recall and precision, outperforming current state-of-the-art models on a subset of the UCF-Crime dataset by 2%.
- PyTorch
AI-Powered Diagnostic Support Tool
Retrieval-Augmented Generation (RAG) based diagnostic support tool using PubMed data and OpenAI API to suggest possible diseases based on patient symptoms, demographics, and medical history. Integrated Agentic AI to provide context-specific responses.
- Node.js
- React
Vehicle Detection and Classification
SSD-Mobilenet V1-based traffic monitoring system to detect, count, and classify vehicles in real-time, addressing need for efficient traffic control. Implemented vehicle color and speed prediction, storing images of detected vehicles, and logging detection data to a CSV file for analysis.
- TensorFlow
- OpenCV
Evaluating Traditional and Ensemble Learning Techniques for Churn Prediction
Built and evaluated multiple machine learning models to predict customer churn using a telecom dataset. Applied feature engineering and preprocessing, and benchmarked classifiers including Logistic Regression, SVM, Decision Trees, Random Forest, Gradient Boosting, and ensemble methods.
- pandas
- NumPy
- scikit-learn