About Me
I received my B.S. degree from the Department of Mathematics and Computer Science, Ho Chi Minh City University of Science (VNUHCM), Vietnam, in 2018. I joined PRLab in March 2021. I received my M.S. degree from the Department of Artificial Intelligence Convergence at Chonnam National University, South Korea, in 2023. My research interests are machine learning, deep learning focusing on multimodal fusion, time-series analysis, affective computing, physiological signal processing, and AI applications in healthcare, human behavior analysis, and real-time industrial systems.
Here are a few technologies I’ve been working with recently:
- Python
- R
- SQL
- LaTex
- C/C++
- MATLAB
- MongoDB
- Maya
- Blender
- PyTorch
- Tensorflow
- PyQt
Experience
Teach undergraduate lectures in Machine Learning, Deep Learning, Computer Vision, etc.
Guide student projects on AI applications.
Develop lab exercises and custom datasets for practical coursework using tools such as Jupyter, Kaggle, RStudio.
Completed all required school certifications for academic teaching.
Propose and guide graduation thesis topics in AI-related fields, including healthcare, image processing, and video analysis.
Participate in faculty meetings and coordinated final-year thesis evaluations.
Pain Estimation: Experiment on the dataset from the Second Multimodal Sensing Grand Challenge for Next-Gen Pain Assessment 2025 (AI4pain 2025), which focuses on physiological signal-based pain classification.
Action Unit Detection: Experiment on the 8th Affective & Behavior Analysis in-the-Wild (ABAW8) dataset. We conducted experiments on action unit detection task.
Tech Stack: Python, R, SQL, Pytorch, Tensorflow, Kaggle, Jupyter, Google Colab, RStudio.
Data preparation: Collect and label data from the data generation step. Clean and check the data set for missing or incomplete before the training step.
Image enhancement: Convert X‑ray image from High Dynamic Range (32bit) to Low Dynamic Range (8bit) for display on the device.
Object detection: Using Image Processing and Deep Learning algorithms for detection of elements battery.
Deployment and improvement: Integrate and test model in real-time on the machine in the factory. Ongoing improvement to adapt to new data and conditions.
Write documents: Write user manuals and technical documentation for internal tools, covering training pipelines, model evaluation processes, and deployment workflows, etc. to support knowledge sharing within the team.
Tech Stack: Python, C#, Halcon, Jupyter, VSCode, Pytorch, Tensorflow, ONNX.
Mental Workload Estimation: Experiment with STEW dataset. We conducted experiments on classification and regression for Mental workload.
Stress Estimation: Experiment with Ulm-TSST dataset, We conducted experiments on Valence-Arousal estimation in Multimodal Emotional Stress Sub-challenge of Multimodal Sentiment Analysis Challenge (MuSe).
Valence-Arousal Estimation: Experiment on the Aff-Wild2 dataset. We achieved 3rd place in Task 1 - Valence-Arousal Estimation in Workshop and Competition on Affective Behavior Analysis in-the-wild.
Tech Stack: Python, Haskell, Flutter, Jupyter, Pytorch, Tensorflow, Git, Docker.
R&D automation scripts and tools inside and outside a 3D application to help the artist can be quickly worked on.
Providing technical support for artists, producers, and leads — including troubleshooting software, debugging tools, and writing scripts.
Supporting producers and team leaders in training for newbies.
Tech Stack: Python, Maya, Blender, 3DsMax, Unreal, MongoDB, Git, SVN, PyQt, Pytorch.
Prepare and teach exercises for Data Structure and Algorithms.
Support students with assigned exercises.
Research on document image analysis, focusing on table detection and number recognition for cell text.
Tech Stack: Python, C/C++, Ubuntu, Scikit-Learn, Tensorflow, Google Colab.
Research machine learning methods to feature extraction and object detection.
Use histograms of oriented gradients (HOG), local binary patterns (LBP) features and support vector machines (SVM) for motorcycle detection.
Tech Stack: Python, Ubuntu, SVN, Scikit-Learn.
Education
2021 - 2023
Master of Science in Artificial Intelligence
Chonnam National University, South Korea
GPA:
4.29/4.5
- Thesis title: Multi-space Fusion for Mental Workload Estimation based on Physiological Signal.
- Supervisor: Prof. Soo-Hyung Kim.
2014 - 2018
Bachelor of Science in Mathematics and Computer Science
Vietnam National University, Ho Chi Minh City - University of Science (HCMUS)
GPA:
8.0/10
- Thesis title: Face recognition based on partial face.
- Supervisor: Prof. Pham The Bao.
Projects
Python
Keras
Dash
Mental Workload Estimation
Mental workload (MWL) refers to brain activities, which are the number of resources in the human brain.
Python
Pytorch
Emotion Analysis
The 2D Valence and Arousal Space (VA-Space) is the most usual dimensional emotion representation; valence shows how positive or negative an emotional state is, whilst arousal shows how passive or active it is.
Python
Pytorch
Stress Estimation
Sentiment analysis is an aspect momentous for application in the future. Especially, emotional stress estimation helps improve our life.
Get in Touch
My inbox is always open. Whether you have a question or just want to say hi, I’ll try my best to get back to you!