I'm a Research Associate at the Interdisciplinary Center for Security, Reliability, and Trust (SnT) at the University of Luxembourg, focusing on applied machine learning approaches for satellite communications systems. My current research centers on developing efficient on-board satellite image classification methods and semantic knowledge distillation frameworks for Earth observation applications.
Previously, I was a Postdoctoral Fellow at the Biomedical Information Processing Laboratory at École de technologie supérieure (ETS), where I worked on machine learning approaches for biomedical informatics problems, particularly in pediatric intensive care settings. I've made contributions in areas like photoplethysmogram signal processing, clinical text classification, and artifact detection using transformer-based architectures.
I hold a Ph.D. in Electrical Engineering with a focus on Applied Artificial Intelligence from ETS, where I developed novel deep learning approaches for healthcare applications. I've received several prestigious awards including the merit doctoral scholarship from Le Fonds de Recherche du Quebec Nature et Technologies and the NSERC-PERSWADE fellowship. My research interests span applied machine learning, satellite communications, biomedical signal processing, and natural language processing in clinical settings.
Publications
Heart Rate and Body Temperature Relationship in Children Admitted to PICU - A Machine Learning Approach.
Emilie Lu, Thanh-Dung Le, P. Jouvet, R. Noumeir
IEEE transactions on bio-medical engineering 2025
Hybrid Deep Learning-Based Enhanced Occlusion Segmentation in PICU Patient Monitoring
Mario Francisco Munoz, Hoang Vu Huy, Thanh-Dung Le, P. Jouvet, R. Noumeir
IEEE Open Journal of Engineering in Medicine and Biology 2024
Semantic Knowledge Distillation for Onboard Satellite Earth Observation Image Classification
Thanh-Dung Le, Vu Nguyen Ha, T. Nguyen, G. Eappen, P. Thiruvasagam, Hong-Fu Chou, Duc-Dung Tran, L. M. Garcés-Socarrás, J. L. González-Rios, J. C. Merlano-Duncan, S. Chatzinotas
arXiv.org 2024
Cognitive Semantic Augmentation LEO Satellite Networks for Earth Observation
Hong-Fu Chou, Vu Nguyen Ha, P. Thiruvasagam, Thanh-Dung Le, G. Eappen, T. Nguyen, Duc-Dung Tran, Luis Manuel Garcés Socarrás, JUAN CARLOS MERLANO DUNCAN, S. Chatzinotas
arXiv.org 2024
On-Air Deep Learning Integrated Semantic Inference Models for Enhanced Earth Observation Satellite Networks
Hong-Fu Chou, Vu Nguyen Ha, P. Thiruvasagam, Thanh-Dung Le, G. Eappen, T. Nguyen, Luis Manuel Garcés Socarrás, Jorge Luis González Rios, JUAN CARLOS MERLANO DUNCAN, S. Chatzinotas
arXiv.org 2024
Onboard Satellite Image Classification for Earth Observation: A Comparative Study of ViT Models
Thanh-Dung Le, Vu Nguyen Ha, T. Nguyen, G. Eappen, P. Thiruvasagam, L. M. Garcés-Socarrás, Hong-Fu Chou, J. L. González-Rios, J. C. Merlano-Duncan, S. Chatzinotas
Mechanical properties of AlCoCrCuFeNi high-entropy alloys using molecular dynamics and machine learning
Hoang-Giang Nguyen, Thanh-Dung Le, Hong-Giang Nguyen, Te-Hua Fang
Materials Science and Engineering: R: Reports 2024
The Impact of LoRA Adapters for LLMs on Clinical NLP Classification Under Data Limitations
Thanh-Dung Le, T. Nguyen, Vu Nguyen Ha
arXiv.org 2024
Hybrid Deep Learning-Based for Enhanced Occlusion Segmentation in PICU Patient Monitoring
Mario Francisco Munoz, Hoang Vu Huy, Thanh-Dung Le
arXiv.org 2024
Multi-objective Representation for Numbers in Clinical Narratives: A CamemBERT-Bio-Based Alternative to Large-Scale LLMs
Boammani Aser Lompo, Thanh-Dung Le
Transformer Meets Gated Residual Networks To Enhance Photoplethysmogram Artifact Detection Informed by Mutual Information Neural Estimation
Thanh-Dung Le
Heart Rate and Body Temperature Relationship in Children Admitted to PICU -- A Machine Learning Approach
Emilie Lu, Thanh-Dung Le
Are Medium-Sized Transformers Models still Relevant for Medical Records Processing?
Boammani Aser Lompo, Thanh-Dung Le
Predictive Models based on Deep Learning Algorithms for Tensile Deformation of AlCoCuCrFeNi High-entropy alloy
Hoang-Giang Nguyen, Thanh-Dung Le
Boosting Transformer's Robustness and Efficacy in PPG Signal Artifact Detection with Self-Supervised Learning
Thanh-Dung Le
arXiv.org 2024
Label Propagation Techniques for Artifact Detection in Imbalanced Classes Using Photoplethysmogram Signals
Clara Macabiau, Thanh-Dung Le, Kevin Albert, Mana Shahriari, P. Jouvet, R. Noumeir
IEEE Access 2023
GRN-Transformer: Enhancing Motion Artifact Detection in PICU Photoplethysmogram Signals
Thanh-Dung Le
Improving Transformer Performance for French Clinical Notes Classification Using Mixture of Experts on a Limited Dataset
Thanh-Dung Le, P. Jouvet, R. Noumeir
Adaptation of Autoencoder for Sparsity Reduction From Clinical Notes Representation Learning
Thanh-Dung Le, R. Noumeir, J. Rambaud, Guillaume Sans, P. Jouvet
IEEE Journal of Translational Engineering in Health and Medicine 2022
Detecting of a Patient's Condition From Clinical Narratives Using Natural Language Representation
Thanh-Dung Le, R. Noumeir, J. Rambaud, Guillaume Sans, P. Jouvet
IEEE Open Journal of Engineering in Medicine and Biology 2021
Machine Learning Based on Natural Language Processing to Detect Cardiac Failure in Clinical Narratives
Thanh-Dung Le, R. Noumeir, J. Rambaud, Guillaume Sans, P. Jouvet
arXiv.org 2021
Reproducing AmbientGAN: Generative models from lossy measurements
Mehdi Ahmadi, T. Nest, M. Abdelnaim, Thanh-Dung Le
arXiv.org 2018
On-board Satellite Image Classification for Earth Observation: A Comparative Study of Pre-Trained Vision Transformer Models
Thanh-Dung Le, Vu Nguyen Ha, T. Nguyen, G. Eappen, P. Thiruvasagam, Luis Manuel Garcés Socarrás, Hong-Fu Chou, Jorge Luis González Rios, JUAN CARLOS MERLANO DUNCAN, S. Chatzinotas
arXiv.org 2024
A Novel Transformer-Based Self-Supervised Learning Method to Enhance Photoplethysmogram Signal Artifact Detection
Thanh-Dung Le, Clara Macabiau, Kevin Albert, P. Jouvet, R. Noumeir
IEEE Access 2024
Multi-objective Representation for Numbers in Clinical Narratives Using CamemBERT-bio
Boammani Aser Lompo, Thanh-Dung Le
arXiv.org 2024