Dự án nghiên cứu khoa học sinh viên HVNH 2024 - 2025

I built Sentiment Analysis models leveraging a deep learning approach utilizing the customer reviews of Amazon products. Since Long Short Term Memory Network (LSTM) is very effective in dealing with long sequence data and learning long-term dependencies, I used it for automatic sentiment classification of future product reviews.

Imbalanced classification with scikit-learn and PyTorch Lightning.

This project analyses the 2015 BRFSS health survey to identify key predictors of diabetes risk using data cleaning, statistical analysis, and machine‑learning models. BRFSS stands for Behavioral Risk Factor Surveillance System — a large, annual telephone‑based health survey run by the U.S. Centers for Disease Control and Prevention (CDC).

Effective deep learning approaches for animal classification.

deep learning model to classify x-ray

Multi-modal skin lesion classification on HAM10000 using ConvNeXt-Tiny + clinical metadata with fine-tuning and class balancing

Predicting liver cirrhosis outcomes using machine learning models based on clinical data.

Building a Convolutional Neural Network on a smaller sample of chest X-ray dataset

Adaptive Mix-Up for Highly Imbalanced Medical Image Classification