Projects

Projects Table of Contents Link to heading

Brain Tumor Classification Image

Developed a brain-tumor classifier using CNN and managed versioning and artifacts of model using MLFlow.
Automated training and retraining of model using Airflow DAG’s based on feedback received.
Deployed a scalable application developed using Streamlit leveraging Restful API endpoints on Kubernetes, based on the latest Docker image in the artifact registry, pushed by GitHub Actions on change thereby achieving CI/CD.
Monitored model for confidence and prediction distribution, data for drift and skew to increase lifecycle of model.

Body Composition Scanner Image

Used a pretrained Resnet model to extract silhouettes of front and left or right facing images of subjects.
Extracted features from silhouettes such as area, solidity of contour.
Established a linear relation between wrist size and neck circumference through a paper by Prof. John Verzani called “Human Proportions,” which was later used for other component calculations like fat percentage, lean mass, and more.

Penalty Analysis and Prediction Image

Created a new dataset with paramters such as isFansSide and established thaere exists a complex realtionship between them and direction of penalty for one test player Harry Kane
Applied various ML tecniques and settled on distance based KNN moedel which when tuned to 5 neighbours achieved an accuracy of 78%.
You can find a Google sheet of all the 1234 possible scenarios my model could face and the prediction in the read me of my GitHub repo.

Implemented classical machine learning algorithms (Linear Regression, Logistic Regression, and SVM) from scratch using Python, NumPy, and SciPy, demonstrating strong foundational understanding of model optimization, regularization, gradient descent.
Developed comprehensive evaluation metrics (Accuracy, RMSE, SSE, Precision, Recall) to assess model performance, improving the interpretability and robustness of predictions.

Health Centre Database Image

Designed and modeled a database to handle various aspects involved in a healthcare center.
Created a multidimensional model with several facts such as Consultation, Tests Conducted, and Operations performed to analyze health center metrics and identify potential hazards.
Implemented OLTP and OLAP databases using PostgreSQL and used Talend Jobs for ETL operations.

Improved user satisfaction by reducing load on bus by 30% with scheduling strategies derived based on a random forest model developed with MBTA Data Science team which achieved an accuracy of 84.8%.

European Football Database Image

Architected and implemented a scalable and robust database system for the European football/soccer league using MySQL and MongoDB.
Integrated MySQL database with Python using SQLAlchemy for data analysis.

Conducted timeseries analysis on human activity data, applying techniques such as ARIMA, LSTM, and Prophet models to forecast and understand patterns.

Formula1 Analysis Image

Extracted and integrated data from various sources and APIs, utilized Python for data wrangling, and created a comprehensive dashboard displaying the 2021 season insights using Tableau.
Used Exploratory Data Analysis techniques to uncover factors influencing the 2021 championship battle.