SU THET MIN HTET
A dedicated Computer Science Student specializing in Big Data with a strong foundation in machine learning, data analysis, and programming. Completed hands-on projects, including building machine learning models and deploying web apps. Looking to leverage my knowledge and experience into a role in Data Science.
View My Resume
View My LinkedIn Profile
Portfolio
My Data Science, Machine Learning, and NLP projects
American Sign Language (ASL) Real-Time Recognition
This project demonstrates a real-time American Sign Language (ASL) recognition system using TensorFlow/Keras and OpenCV.
Using the ASL Alphabet Dataset, I trained a CNN model to recognize 29 different ASL gestures (A–Z and special signs).
The system integrates MediaPipe for hand detection and cropping, and OpenCV for streaming and displaying predictions in real time.
View Kaggle Notebook
View on GitHub
Sentiment Analysis on Tweets
Sentiment analysis helps analyze the emotions behind tweets and other text data. This project uses XLM-RoBERTa, a multilingual transformer model, to classify tweets into positive, negative, or neutral sentiments. By fine-tuning the model with Hugging Face Transformers, I leveraged transfer learning for improved accuracy in sentiment classification.
Analyzing Food and Drug Adverse Event Reports
This project analyzes the CAERS dataset to identify patterns in food and drug-related adverse events. By applying data analysis and visualization techniques, I explored trends and insights that could help in understanding the risks associated with different food products.The analysis is made interactive with Streamlit, allowing users to explore trends dynamically.
Predicting Gestational Diabetes Risk
Gestational diabetes can have significant health implications for both the mother and baby. In this project, I developed three machine learning models that predicts gestational diabetes risk based on various clinical and demographic factors. The model aims to assist healthcare professionals in early detection and intervention. Moreover, a simple interactive UI was built using ipywidgets in Google Colab, allowing users to input feature values and obtain predictions from the trained models.
Predicting Critical Temperature in Superconductors
This project focuses on predicting the critical temperature of superconducting materials using regression models built with two different libraries: SparkMLlib and Scikit-Learn. By analyzing material compositions and properties, the model provides insights into superconducting behavior.
Predicting Abalone Age Using Machine Learning
This project aims to predict the age of abalones based on physical attributes such as shell size and weight. Using machine learning regression models, I implemented Linear Regression, Decision Tree, and Random Forest to estimate abalone age. The model is deployed as a web application for easy access and use.
Website: https://abalone-age-prediction-wtct.onrender.com
Traffic Bottleneck Identification on Road Networks
This was my Final Year Project (FYP), where I led a team to develop a traffic bottleneck identification system. The project focused on optimizing road networks by detecting congestion points and suggesting efficient alternative routes.
Website: https://flowx.onrender.com