Thanks to visit codestin.com
Credit goes to github.com

Skip to content
View MangaiS20's full-sized avatar

Block or report MangaiS20

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.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
MangaiS20/README.md

Hi, I'm Mangai

Data Science Graduate
Python | SQL | Data Analytics | Machine Learning | Clinical Data Validation

Tamil Nadu, India

About Me

I am a Data Science graduate with a background in Computer Science and hands-on experience in Data Analytics, Machine Learning, Clinical Data Validation, and Software Development through internships and academic projects.

I enjoy transforming data into meaningful insights, developing machine learning solutions, and continuously learning new technologies to solve real-world problems.

  • Interested in Data Analytics, Machine Learning, and AI
  • Python, SQL, Power BI
  • Clinical Data Validation (SDTM, Pinnacle21, Kwalify)
  • Continuously improving my Python, SQL, and Data Analytics skills
  • Open to Data Analyst, Data Science, Clinical Data Analyst, and Healthcare Analytics opportunities

Technical Skills

Programming

  • Python
  • SQL
  • R (Basic)

Machine Learning & AI

  • Scikit-learn
  • TensorFlow / Keras
  • CNN
  • BiLSTM
  • XGBoost

Data Analysis & Visualization

  • Pandas
  • NumPy
  • Matplotlib
  • Seaborn
  • Power BI
  • Microsoft Excel

Databases

  • MySQL
  • MongoDB
  • GraphDB

Web Technologies

  • Flask
  • HTML
  • CSS
  • JavaScript

Tools

  • Git
  • GitHub
  • Jupyter Notebook
  • Databricks (Basic)
  • Pinnacle21
  • Kwalify

Featured Projects

Human Activity Recognition using CNN-CBAM-BiLSTM

  • Developed a hybrid deep learning model for sensor-based human activity recognition.
  • Achieved 96.41% Accuracy and 0.9672 F1-score on the KU-HAR dataset.

Traditional Knowledge Archive System

  • Developed a Flask-based web application with multilingual OCR support.
  • Integrated Tesseract OCR, MySQL, and MongoDB for efficient manuscript management.

Stock Price Prediction using Machine Learning

  • Compared LSTM, Random Forest, and XGBoost models using historical Adani stock data.
  • Achieved an R² Score of 0.9299 using the LSTM model.

Certifications

  • IBM – Databases and SQL for Data Science (Coursera)
  • Deloitte Data Analytics Job Simulation (Forage)
  • Elements of AI
  • Cybersecurity Fundamentals
  • Full Stack Development

Connect with Me

Email: [email protected]

LinkedIn:
https://linkedin.com/in/mangais20

GitHub:
https://github.com/MangaiS20

Thank you for visiting my profile. Feel free to explore my repositories and connect with me.

Popular repositories Loading

  1. traditional_knowledge_app traditional_knowledge_app Public

    Flask-based Traditional Knowledge Archive System with multilingual OCR support using MySQL and MongoDB.

    HTML

  2. 2D--Transformations- 2D--Transformations- Public

    A Python toolkit for applying and visualizing 2D geometric transformations—featuring translation, rotation, scaling, shearing, reflection, affine, similarity, and projective techniques, all backed …

    Jupyter Notebook

  3. MangaiS20 MangaiS20 Public

    My GitHub Profile

  4. Human-Activity-Recognition-CNN-CBAM-BiLSTM Human-Activity-Recognition-CNN-CBAM-BiLSTM Public

    Deep Learning based Human Activity Recognition using CNN, CBAM and BiLSTM on sensor data

    Python

  5. stock-price-prediction-using-machine-learning stock-price-prediction-using-machine-learning Public

    Comparative stock price prediction using LSTM, Random Forest, and XGBoost on historical Adani stock market data.

    Jupyter Notebook