Skip to content
View puja-urmi's full-sized avatar
:octocat:
:octocat:
2 followers · 0 following

Achievements

Achievement: Quickdraw

Achievements

Achievement: Quickdraw

Block or report puja-urmi

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
puja-urmi/README.md

👋 Hi there!

I am Puja Saha, M.A.Sc. candidate in Computer Engineering (CGPA: 3.93/4.00) at the University of Guelph, with a Bachelor’s degree in Biomedical Engineering (CGPA: 3.68/4.00). My research interests lie in model architecture adaptation, decentralized machine learning, optimization, and multimodal AI for diverse applications. Currently, I am doing research on decentralized AI for medical image analysis

I am actively seeking PhD/internship opportunities where I can apply my knowledge to contribute to advancing machine learning methodologies for impactful applications and grow.

🛠️ Skills & Tools

  • Programming: Python, MATLAB, C
  • Frameworks and Tools: PyTorch, NVFLARE, MONAI, PySpark, TensorFlow, Flower, LangChain, OpenCV, Scikit-learn, NiBabel
  • Technologies: Federated Learning, Cloud Computing (GCP, AWS, Compute Canada), Git
  • Operating Systems: Linux, macOS, Windows

🌟 Key Projects

  • Multiclass Semantic Segmentation:
    Developed a PyTorch-based solution for segmenting kidney and tumor regions in CT scans, achieving Dice scores of 91.03% (kidney) and 62.82% (tumor).
    GitHub Repository

  • Medical Chatbot:
    Built a retrieval-augmented generation-based chatbot trained on PubMed data, achieving high context precision and answer accuracy.
    GitHub Repository

  • Job Market Analysis and Salary Prediction:
    Conducted big data exploratory analysis and built a salary prediction model using PySpark, achieving a prediction RMSE of ~$10K.
    GitHub Repository

  • Human Pose Estimation:
    Designed a CNN-based regression model for human pose estimation, achieving an MSE of 0.0878.
    GitHub Repository

📫 Reach Out

Pinned Loading

  1. Job-Market-Analysis-PySpark Job-Market-Analysis-PySpark Public

    Explore this repo for a big data-driven project involves exploratory data analysis and salary prediction for the global job market from 2021 to 2023, encompassing over 1.6 million records. Using Py…

    Jupyter Notebook 1 1

  2. Medical-Chatbot-LLM-RAG Medical-Chatbot-LLM-RAG Public

    This repository contains the code for a chatbot that utilizes a large language model with retrieval-augmented generation (RAG), trained on reliable medical datasets from PubMed. The chatbot achieve…

    Jupyter Notebook 2 1

  3. Multiclass-Semantic-Segmentation-PyTorch Multiclass-Semantic-Segmentation-PyTorch Public

    This repository provides a PyTorch solution for multiclass semantic segmentation on the KiTS19 dataset, focusing on kidney and tumor segmentation. It includes notebooks for preprocessing, training,…

    Jupyter Notebook

  4. pariyaab/House_Prices_Regression_Models pariyaab/House_Prices_Regression_Models Public

    This repository contains code and resources for a machine learning project focused on predicting house prices. The project involves data preprocessing, model training using various algorithms, and …

    Python 2 1