Research
Research
Focus
Focus
Embedded Files
On Going Research Projects
Complex System Modeling and Predictive Analytics
Overview:
Focused on understanding nonlinear dynamics in complex systems to develop predictive models for pathological processes.
Key Features:
Data-driven modeling of complex disease pathophysiological processes.
Multi-scale modeling using machine learning and statistical techniques.
Probabilistic models for scare event anomaly detection.
Impact:
Enhanced prediction of disease onset (e.g., obstructive sleep apnea, cardiovascular disease, neurodegenerative disorders).
Improved decision-making for preventive intervention and treatment optimization.
Outcomes:
Publications in leading journals on predictive modeling.
Application of models in both clinical and industrial domains.
Funding sources: NSF, NIH, and the University of South Florida
Related Publications
T. Nguyen, D. Kasperski, P. Huynh, T. Le, and T. B. Le. "Modal analysis of blood flows in saccular aneurysms." Physics of Fluids 37, no. 1 (2025). https://doi.org/10.1063/5.0243383
S. Ambardar, G. Binder, P. Huynh, D. Nguyen, H. Hrim, T. Le, D. Voronine. "Surface‐enhanced Raman imaging of intact cancer cell membrane on a rough aluminum substrate." Journal of Raman Spectroscopy 54, no. 9 (2023): 940-949. https://doi.org/10.1002/jrs.6562
P. Huynh, D. Nguyen, G. Binder, S. Ambardar, T. Le, D. Voronine. "Multifractality in Surface Potential for Cancer Diagnosis." Journal of Physical Chemistry B 127, no. 31 (2023): 6867-6877. https://pubs.acs.org/doi/abs/10.1021/acs.jpcb.3c01733
P. Huynh, A. Setty, T. Le, and T. Le. "A noise-robust Koopman spectral analysis of an intermittent dynamics method for complex systems: a case study in pathophysiological processes of obstructive sleep apnea." IISE Transactions on Healthcare Systems Engineering 13, no. 2 (2023): 101-116. https://doi.org/10.1080/24725579.2022.2141379
P. Huynh, A. Setty, Q. Tran, O. Yadav, N. Yodo, T. Le. "A Domain-knowledge Modeling of Hospital-acquired Infection Risk in Healthcare Personnel from Retrospective Observational Data: A Case Study for COVID-19." PLOS ONE 17, no. 11 (2022). https://doi.org/10.1371/journal.pone.0278345
P. Huynh, A. Setty, H. Phan, T. Le. "Probabilistic domain-knowledge modeling of disorder pathogenesis for personalized forecasting of acute onset." Artificial Intelligence in Medicine 121 (2021): 102056. https://doi.org/10.1016/j.artmed.2021.102056
Smart IoT Sensing System
Overview:
Designed IoT-based wearable systems for continuous monitoring and treatment of sleep disorders and related conditions like cardiovascular diseases, neurodegenerative disorders, and cancer.
Key Features:
Real-time biosignal monitoring and analysis.
Integration of predictive analytics for personalized therapy.
Scalable solutions for home and clinical use.
Impact:
Improved quality of life for patients with complex comorbid conditions.
Scalable telemedicine applications to underserved populations.
Notable Outcomes:
Successful deployment in head and neck cancer patient trials.
Multiple peer-reviewed articles on system design and performance.
Funding sources: NIH, ND-EPSCOR, University of South Florida
Related Publications
D. Nguyen, M. Le, P. Huynh, T. Le, C. Charles-Okezie, M.J. Diaz, C. Sabet, et al. "Deep Learning-based Integrated System for Intraoperative Blood Loss Quantification in Surgical Sponges." IEEE Journal of Biomedical and Health Informatics (2024). https://doi.org/10.1109/JBHI.2024.3499852
Nguyen, Q.H., Hore, S., Shah, A., Le, T., and Bastian, N.D. "FedNIDS: A Federated Learning Framework for Packet-based Network Intrusion Detection System." Digital Threats: Research and Practice (2023). https://doi.org/10.1145/3696012
A. Davila-Frias, N. Yodo, T. Le, O.P. Yadav. "A deep neural network and Bayesian method-based framework for all-terminal network reliability estimation considering degradation." Reliability Engineering & System Safety 229 (2023): 108881. https://doi.org/10.1016/j.ress.2022.108881
B. Richter, Z. Mace, M. Hays, S. Adhikari, H. Pham, R.J. Sclabassi, B. Kolber, S.S. Yerneni, P. Campbell, B. Cheng, N. Tomycz, D.M. Whiting, T. Le, T. Nelson, S. Averick. "Development and Characterization of Novel Conductive Sensing Fibers for in vivo Nerve Stimulation." Sensors 21, no. 22 (2021): 7581. https://doi.org/10.3390/s21227581
T. Le, C. Cheng, A. Sangasoongsong, W. Wongdhamma, S.T.S. Bukkapatnam. "Wireless Wearable Multisensory Suite and Real-Time Prediction of Sleep Apnea Episodes." IEEE Journal of Translational Engineering in Health and Medicine 1 (2013): 1-9. https://doi.org/10.1109/jtehm.2013.2273354
Validation of AI-Based Sensing Technology for Sleep Medicine
Overview:
Design and develop rigorous validation and verification studies of AI-driven wearable devices for sleep staging and other health metrics.
Key Features:
Comparative studies between wearable technology and gold-standard methods (e.g., polysomnography).
Development of metrics to assess accuracy and reliability for clinical use.
Impact:
Enabled consumer-grade wearables to meet clinical standards.
Improved access to affordable sleep health monitoring.
Notable Outcomes:
Collaboration with wearable tech companies for device optimization.
Published validation frameworks adopted by researchers globally.
Funding sources: Misfit-Fossil Wearable, ND-EPSCOR.
Related Publications
T. Le, P. Huynh, and L. Tomaselli. "Navigating the night: evaluating and accessing wearable sleep trackers for clinical use." Sleep (2024): zsad319. https://doi.org/10.1093/sleep/zsad319
A. Davila-Frias, N. Yodo, T. Le, OP Yadav “A deep neural network and Bayesian method-based framework for all-terminal network reliability estimation considering degradation”. Reliability Engineering & System Safety 229 (2023): 108881.https://doi.org/10.1016/j.ress.2022.108881
Q. Nguyen, Q. Huynh. H. Nguyen, A. Setty, T. Van, and T. Le, “Validation of Sleep Stage Scoring between Wearable Sleep Trackers and Polysomnography in Healthy Adults” Clocks & Sleep. 2021; 3(2):274-288. https://doi.org/10.3390/clockssleep3020017
Artificial Intelligence for Sustainable Energy Networks
Overview:
Applied machine learning and AI to optimize energy infrastructure for sustainability and resilience.
Key Features:
Multi-scale modeling of energy systems using AI.
Real-time optimization algorithms for reliability and energy efficiency.
Cross-disciplinary approach combining AI and engineering.
Impact:
Reduced energy downtime and enhanced reliability of infrastructure.
Contribution to sustainable development goals in energy.
Notable Outcomes:
Industry collaboration for deployment in real-world energy systems.
Develop methods for realtime health monitoring and risk quantification of cascading failures in energy network.
Funding sources: NSF, AI-Sustein (https://www.aisustein.com/)
Related Publications
L. Lemlem, C. Le, T. Le, O. Yadav, and T. Le. "Insights into the Interactions of Pipeline Risk Factors and Consequences Using Association Rule Mining." Journal of Performance of Constructed Facilities 39, no. 1 (2025): 04024059
R. Mishkatur, A. Akash, H. Pirim, C Le, T Le, and O. Yadav. "Enhancing Electrical Network Vulnerability Assessment with Machine Learning and Deep Learning Techniques." Northeast Journal of Complex Systems (NEJCS) 6, no. 1 (2024): 2.
P. Huynh, M. Rahman, O Yadav, T Le, and Chau Le. "Assessing Robustness and Vulnerability in Interdependent Network Infrastructure: A Multilayer Network Approach." In 2024 Annual Reliability and Maintainability Symposium (RAMS), pp. 1-7. IEEE, 2024.
P. Huynh, G. Singh, O. Yadav, T. Le, and C. Le. "Unsupervised Anomaly Detection in Electric Power Networks Using Multi-Layer Auto-Encoders." In 2024 Annual Reliability and Maintainability Symposium (RAMS), pp. 1-6. IEEE, 2024. (William A. Golomski Award Best Paper Award)
P. Huynh , A. Alqarni, OP. Yadav, T. Le “A Physics-informed Latent Variables of Corrosion Growth in Oil and Gas Pipeline”. In 2023 IEEE Annual Reliability and Maintainability Symposium (RAMS), Orlando, USA, 2023. (SRE Doug Ogden Best Paper Award and William A. Golomski Award Best Paper Award)
Contact Us
Sensing and Predictive Analytics for Computational HEalthcare Systems (SPACHES) LaboratoryDepartment of Industrial and Management System EngineeringUniversity of South Florida4202 East Fowler AveTampa, FL 33620-0001 USAEmail: tqle@usf.eduWebsite: www.spaches.org
Sensing and Predictive Analytics for Computational HEalthcare Systems (SPACHES) LaboratoryDepartment of Industrial and Management System EngineeringUniversity of South Florida4202 East Fowler AveTampa, FL 33620-0001 USAEmail: tqle@usf.eduWebsite: www.spaches.org
Page updated
Google Sites
Report abuse