About Me
Who I Am
I'm a dedicated and determined graduate student pursuing Masters in Computer Science at the University of California, Riverside, with a strong foundation in AI, Machine Learning, and Data Science. My academic journey has equipped me with both theoretical knowledge and practical skills in developing innovative solutions.
With experience in AI-driven security systems, computer vision applications, and machine learning research, I'm passionate about leveraging technology to solve real-world problems. My work spans from developing anomaly detection systems to optimizing deep learning models for various applications.
I'm constantly exploring new technologies and methodologies to enhance my skills and contribute meaningfully to the field of Computer Science.
Programming Languages
Skills
Tools/Frameworks
AI/ML Libraries
Concepts
Currently Learning
- Large Language Models
- Generative AI
- Reinforcement Learning
Education
University of California, Riverside
Master of Science - Computer Science
Vellore Institute of Technology
Bachelor of Technology - Computer Science and Engineering
Work Experience
Machine Learning Internship
National Institute of Technology
AI-Powered Insider Threat Detection
Developed an AI-driven Insider Threat Detection System using anomaly detection and predictive modeling, improving detection accuracy by 6% and reducing false positives by 12%.
Temporal Sequence Learning for Security Analytics
Designed and fine-tuned LSTM and Autoencoder to analyze security logs, capturing complex time‑dependent anomalies with a 15% improvement in predictive recall.
Scalable AI Data Pipelines
Engineered high‑performance ETL pipelines using Python, Pandas, and SQL, optimising preprocessing efficiency by 40%, ensuring real‑time data availability for AI‑driven security monitoring.
Summer Internship
Center for Development of Telematics (C‑DOT)
AI‑Driven Safety Mapping
Developed a real‑time Safety Sign Detection System using Computer Vision and Deep Learning, improving workplace safety by automating hazard identification with 92% accuracy.
Optimised Object Recognition
Designed a YOLO‑based deep learning model, achieving a 20% improvement in detection speed and 98% precision for identifying safety signs in dynamic indoor environments.
AI‑Powered Data Optimisation
Reduced data preprocessing and model training time by 30% by automating workflows with OpenCV, TensorFlow, and Pandas, enabling faster AI model iteration.
Projects
Spatio-Temporal Health Analytics and Visualization
Processing and analyzing large-scale health datasets from the CDC's National Center for Chronic Disease Prevention and Health Promotion using PySpark for distributed data processing, Geopandas for spatial data analysis, and Pandas-Profiling for exploratory data analysis and visualization.
Publications
Enhanced remote sensing and deep learning aided water quality detection in the Ganges River, India supporting monitoring of aquatic environments
Results in Engineering (RINENG), Elsevier Journal
Hierarchical Attention-Enhanced Multihead CNN and Level Sets Segmentation: A Proposed Approach to Enhance the Cyclone Intensity Estimation
Computers & Geosciences - Elsevier Journal
Parallelization of Molecular Dynamics Simulations
International Conference on MAchine inTelligence for Research Innovation (MAiTRI-2023 Summit)
Quantitative Nuclei Analysis for Accurate Detection of Breast Abnormalities through Machine Learning
IEEE Global Conference on Information Technologies and Communications