Trieu Phat Luu
Senior Staff Data Scientist, Ph.D
- (+1)713-517-7819
- tpluu2207@gmail.com
- Google Scholar/tpluu
- Houston, TX
![image](assets/images/resume-profile.png)
A Senior Staff Data Scientist in Oil Field Services Digital of Baker Hughes. Served as Senior Research Associate at the Brain Machine Interface Lab, University of Houston, managed teams and delivered several projects with budgets exceeding $1M.
More than 10 years of experience in interdisiplinary areas of machine learning, AI, and robotics.
Proven ability to develop systems (hardware and software), and to communicate project's outcomes via scientific publications and oral presentations.
Education
![image](docs/images/stsmall507x507-pad600x600f8f8f8.u4.jpg)
Nanyang Technological University
Thesis: "Individual-specific Gait Pattern Planning and Locomotion Control Strategy for Robotic Gait Rehabilitation" . GPA: 4.84/5.0
![image](docs/images/1004px-Logo-hcmut.svg_-294x300.png)
Ho Chi Minh City University of Technology
Gradudated with the highest GPA in the Department (~700 students) and a gold medal.
Skills
- AWS Certified
- Machine Learning, Deep Learning
- Tensorflow, Keras
- Flask, HTML5, CSS, D3.js
- Robotics, ROS
- Computer Vision
- Digital signal processing
- Microcontroller Programming
- Labview, C/C++: Advanced
- Matlab, Python: Professional
- Git, CI/CD, Azure DevOps
- Strong work ethic
- Effective communication
- Technical & Scientific writing
Work Experiences
![image](docs/images/Baker-Hughes.jpg)
Baker Hughes
- Served as a Senior Staff Data Scientist in Oil Field Services Digital division of Baker Hughes, the largest business unit with $10B+ in revenue.
- Proposed efficient solutions to Chief Data Scientist based on the latest developments in AI technologies (e.g., representation learning, semantic segmentation, abnormality detection).
- Collaborated with the Drillbit team to develop models for bitwear prediction. The project was funded with ~ $1M and considered as foundations for drilling advisory and automation. Pull through revenue had potential of $100M drilling services.
- Key developer of an LSTM-VAE model to monitor bitwear in real-time. The recommendations from the AI model were validated during real-time drilling. It contributed to the extension of $300K funding from customers.
- Led R&D developments of AI-assisted borehole image segmentation. Developed tools to label training data using PyQt5 and OpenCV. Applied MaskRCNN using Tensorflow framework for instance segmentation of borehole images.
- Developed and launched software for detection of stable drilling zone using wavelet transform and change point detection algorithm.
- Presented works to customers and audiences at SPE conferences.
![image](docs/images/interlocking-uh.png)
University of Houston
- Key technical focal point for the development of a control architecture and network comminucation (CAN bus) for a pediatric exoskeleton. Results from this project were presented at several IEEE conferences and featured on Nature magazine.
- Developed a native app using Matlab GUI to calibrate a custom built torque sensor.
- Designed experimental protocol and developed a system to study EMG and EEG features during walking on developing children.
- Served as invited lecturer and delivered several presentations on "Robotics in healthcare” and "Brain-Machine interfaces"
- Managed a small team of three PhD students to develop a neural-machine interface for the control of a prosthetic leg. The project was funded by NSF with budgets excedding $1M.
- Developed software to visualize human walking data and segment into gait cycles
- Main author to develop software and algorithm to investigate electrocortical correlates of human walking across multiple terrains.
- Presented work at several IEEE conferences and high-impact journals (PlosOne, Scientific Data)
- Managed a diverse team of software engineer, undergraduate, master, and PhD students to study non-invasive decoding of walking from EEG brain signals. The project was funded by NIH with budgets excedding $1M.
- Led software development of a real-time EEG-based BCI to control a virtual walking avatar.
- Designed experimental protocol and directly engaged with data collections from 8 healthy individuals. The multimodal physiological sensor data (i.e., EEG, EOG, kinematics) were pre-processed and published on Nature/Scientific Data.
- The BCI-VR system showed its benefit in enhancing cortical involvement in human walking. It was also extended to several post-stroke individuals.
- Presented the research outcomes at multiple conferences (IEEE-ICVR, IEEE-SMC) and high-impact journals (J.Neural.Engineering, Nature/Scientific Reports, Frontiers)
![image](docs/images/sp.jpg)
Singapore Polytechnic
- Co-Principal Investigator of an R&D project to develop upper-limb exoskeleton for assisting the elderly in reaching and feeding tasks. The project was funded with ~700K SGD by MOE, Singapore.
- Key contributor to the development of a 6-DOF upper extremity assistive device. Conducted mechanical and electrical/electronic design and engaged with vendors for fabrication.
- Analyzed kinematics of reaching and grasping task on healthy adults using motion capture system and Matlab. Developed Labview program to control the robotic system
![image](docs/images/interlocking-uh.png)
University of Houston
- Designed a walking Avatar in Unity game engine. The control logic and UDP interface were implemented using C#
- Explored EEG-based brain-computer interface for the control of the walking Avatar
![image](docs/images/stsmall507x507-pad600x600f8f8f8.u4.jpg)
Nayang Technological University
- Developed a Natural and Tunable Rehabilitation Gait System (NaTUre-gaits) for neurorehabilitation in incomplete Spinal Cord Injury (iSCI) populations.
- Conducted experimental design, data collections, and data analytics to study kinematics of human walking on 70 healthy individuals.
- Developed a Neural Network Model to generate walking gait patterns from anthropometric data.
- Designed an Assist-As-Needed control algorithm for the robot to monitor the level of user's intents and adjust the supports accordingly. The controller was implemented using Labview and deployed on NI hardware
- Clinical trials on five iSCI patients at a local Tang Tock Seng hospital confirmed benefits of the system in walking assistance and reduction of manpower
- Presented work at numerous IEEE conferences, and multiple high-impact journals.
- Delivered three lab courses: “characteristic of industrial motors”, “vibration of four-cylinder engine”, and “control of vibration.”
- Served as mentor for 9 Final Year Project students
- Developed a wearable device to measure ground reaction force during human walking.
![image](docs/images/intel.png)
Intel Products Vietnam
Hornor and Distinctions
Finalists for the Best Paper Award and the Shimemura Young Author Award, Asisan Control Conference, ASCC 2011
Ph.D. research scholarship from Nanyang Technological University and National University of Singapore
Gold Medal for the Best Student graduated with the highest GPA in Department of Mechanical Engineering, Ho Chi Minh City University of Technology, Vietnam
Certificate for the Best Student in the Department of Mechanical Engineering, Ho Chi Minh City University of Technology
Bronze Medal, National Olympiads in Mechanical Elements, Vietnam
Bronze Medal, National Physics Olympiads, Vietnam
Gold Medal, Physics Olympiads, South of Vietnam
Presentations
Oral Presentations
Bi-directional LSTM-VAE for real-time bitwear estimation. SPE/IATMI Asia Pacific Oil & Gas Conference.
Locomotion-mode recognition via cortical dynamics from non-invasive EEG. Presented to graduate students from Baylor College of Medicine, Houston, TX.
Real-time EEG-based brain-computer interface to a virtual avatar enhances cortical involvement in human treadmill walking. Invited talk, Dept. of Health and Human Performance, University of Houston, TX.
Cortical features of locomotion-mode transitions via non-invasive EEG. IEEE International Conference on Systems, Man, and Cybernetics, Banff, Canada, Oct 2017.
A closed-loop brain computer interface to a virtual reality avatar: Gait adaptation to visual kinematic perturbations. International Conference on Virtual Rehabilitation, Valencia, Spain, Jun 2016
On the development of an over-ground gait rehabilitation system: NaTUre-gaits. IEEE Healthcare Innovation Conference, Houston, TX, 2012
Poster Presentations
Brain-Machine Interface for Automated Gait Intention Detection, IUCRC BRAIN Meeting
Development of a hybrid neural-machine interface for volitional control of a powered lower limb prosthesis. IUCRC BRAIN Meeting, Houston, TX.
Control architecture and network communication for a pediatric exoskeleton. International Symposium on Wearable & Rehabilitation Robotics, TIRR Memorial Hermann, Houston, TX.
Electroencephalography (EEG)-based Brain-Computer Interface to a virtual walking avatar engages cortical adaptation. Houston Methodist Neuroregeneration Symposium, TX.
Unscented Kalman filter for neural decoding of human treadmill walking from non-invasive electroencephalography. EMBC Conference, Orlando, FL.
Real-time closed-loop brain-computer interface to a virtual reality avatar. BRAIN meeting, Arizona State University, Tempe, AZ.
Study of ground reaction force and center of pressure with robotic gait trainer. IEEE Healthcare Innovation Conference, Houston, TX.
Publications
Selected Journal Articles
- HS Nguyen Luu, T. P.*, Tremor-Suppression Orthoses for the Upper Limb: Current Developments and Future Challenges. Frontiers in Human Neuroscience 15, 186 (2021)
- Sho Nakagome, Luu, T. P., Yongtian He, Akshay Sujatha Ravindran, Jose L Contreras-Vidal An empirical comparison of neural networks and machine learning algorithms for EEG gait decoding. Scientific Reports 10 (1), 1-17 (2020)
- Luu, T. P., Nakagome, S., He, Y. & Contreras-Vidal, J. L. Real-time EEG-based brain-computer interface to a virtual avatar enhances cortical involvement in human treadmill walking. Scientific reports 7, 8895 (2017).
- Luu, T. P., He, Y., Brown, S., Nakagome, S. & Contreras-Vidal, J. L Gait adaptation to visual kinematic perturbations using a real-time closed-loop brain–computer interface to a virtual reality avatar. 2016. Journal of Neural Engineering, 13, 036006.
- Luu, T. P., He, Y., Brown, S., Nakagome, S., Gorges, J. & Contreras-Vidal, J. L. Multi-trial Gait Adaptation of Healthy Individuals during Visual Kinematic Perturbations. 2017. Frontiers in Human Neuroscience, 11.
- Luu, T. P., Low, K. H., Qu, X., Lim, H. B. & Hoon, K. H An individual-specific gait pattern prediction model based on generalized regression neural networks 2014. Gait & Posture, 39, 443-448
Full List of Publications
Articles: 41
Citations: 904
h-index: 15
i10-index: 24
Academic Services
- Reviewer for journals such as Frontiers, Brain Topography, Gait & Posture, Nature/Scientific Report, Journal of Medical and Biological Engineering, Neural Networks, IEEE International Conference on Systems, Man, and Cybernetics.
- Co-chair at IEEE EMBC conference, BMI session, 2017.
- Editor at IEEE Journal of Translational Engineering in Health and Medicine, 2014.
Selected News Articles
- Nature: The mind-reading devices that can free paralysed muscles.
- MedicalXpress, EurekAlert, ECN, Science Newsline, Long Room, Health Medicinet: Use of brain-computer interface, virtual avatar could help people with gait disabilities
- True Viral News: Brain-Computer Interfaces & Virtual Avatar Offers New Hope to Patients with Gait Disabilities.
- Technology Networks: Gait Disabilities Overcome with Brain-Computer Interface and Avatar.
- National Science Foundation: Researchers map brain activity to improve prosthetic design.