Embedded Files
Hamdi Altaheri
About
About
AI Researcher specializing in deep learning and foundation models, with 10+ years of R&D experience. Currently a Postdoctoral Fellow at the University of Waterloo, leading research on integrating large language models (LLMs) with brain signals. Previously served as an AI Researcher at King Saud University’s Center of Smart Robotics Research (2019–2024) and as an Adjunct Lecturer (2022–2024), contributing to the development of AI solutions for health tech, brain–computer interfaces, computer vision, speech forensics, and robotics.
AI Researcher specializing in deep learning and foundation models, with 10+ years of R&D experience. Currently a Postdoctoral Fellow at the University of Waterloo, leading research on integrating large language models (LLMs) with brain signals. Previously served as an AI Researcher at King Saud University’s Center of Smart Robotics Research (2019–2024) and as an Adjunct Lecturer (2022–2024), contributing to the development of AI solutions for health tech, brain–computer interfaces, computer vision, speech forensics, and robotics.
Published 21 peer-reviewed articles in international journals and conferences, including IEEE Transactions on Industrial Informatics and the IEEE Internet of Things Journal, with two papers listed as “Highly Cited” by Web of Science. Holds two U.S. patents in robotics and artificial intelligence. Developed deep learning models for EEG-based brain decoding, released as open-source projects and integrated into research toolkits such as TorchEEG and Braindecode. Recognized with multiple awards, including the President of the Republic of Yemen Prize for Youth in Applied Sciences.
Published 21 peer-reviewed articles in international journals and conferences, including IEEE Transactions on Industrial Informatics and the IEEE Internet of Things Journal, with two papers listed as “Highly Cited” by Web of Science. Holds two U.S. patents in robotics and artificial intelligence. Developed deep learning models for EEG-based brain decoding, released as open-source projects and integrated into research toolkits such as TorchEEG and Braindecode. Recognized with multiple awards, including the President of the Republic of Yemen Prize for Youth in Applied Sciences.
Currently, focused on bridging brain signals with foundation models and generative AI through self-supervised multimodal learning. Open to roles that translate advanced research into scalable, real-world AI applications.
Currently, focused on bridging brain signals with foundation models and generative AI through self-supervised multimodal learning. Open to roles that translate advanced research into scalable, real-world AI applications.
Projects
Projects
Bridging Brain with Foundation Models through Self-Supervised Learning (Current)
Bridging Brain with Foundation Models through Self-Supervised Learning (Current)
This project investigates self-supervised learning on large-scale EEG datasets to develop a large brain foundation model, aiming to enhance the accuracy, generalization, and robustness of brain–computer interface (BCI) systems.
🎯Current outputs:
Nature SR paper (GitHub), Review paper arXiv (GitHub)
Attention-based deep learning techniques for EEG brain signal decoding
Attention-based deep learning techniques for EEG brain signal decoding
This project aims to develop a deep learning model that automatically focuses on the most relevant temporal, spatial, and spectral features of EEG signals to improve MI decoding accuracy.
🎯Main outputs:
ATCNet IEEE TII 2023🔥Highly Cited-WoS (poster: 1 2), D-ATCNet IEEE IoT-J 2023 (poster), DL-EEG Survey Neural Co. App. 2023🔥Highly Cited-WoS, AI-LSTM IEEE TII 2022, REH-MI EEG dataset IEEE DataPort 2025.
🎓 PhD Thesis: 📄 Thesis manuscript 📊 Slides ⚙️ Github
🏅 The project has been distinguished with four awards and recognitions: ⭐ university award 2022, ⭐ college award 2023, ⭐ university award 2024, and ⭐ university recognition 2024.
Survey: Deep learning for EEG signal decoding
Survey: Deep learning for EEG signal decoding
🔥Highly Cited-WoS
Vision System for Date Harvesting Robot
Vision System for Date Harvesting Robot
This project aims to develop intelligent systems for date fruits in an orchard environment, including fruit detection and segmentation, classification, maturity analysis, and visual yield estimation.
🎯Main outputs:
IEEE paper 2019 (poster), DiB paper 2019, Date Fruit dataset, IEEE DataPort 2019
https://sites.google.com/view/daterobotic
🎓 Master Thesis: 📄 Thesis manuscript 📊 Slides 🌐 Website
Universal Control and Security System UCSS
Universal Control and Security System UCSS
UCSS is an integrated system (electronic device and computer-based software) designed as a universal and scalable system for control and security applications.
🏅 This project has been awarded several prizes, including the 12th annual prize of the President of the Republic of Yemen in engineering sciences, 2010. (national award)
The Electronic Unit
The Electronic Unit
The electronic device is an embedded system consisting of a microprocessor (Rabbit 2000 microprocessor) and a set of separate electronic cards that can be inserted according to the requirements of the application.
The electronic unit has different communication capabilities allowing the building to be monitored and controlled from anywhere, anytime, using current wireless data technologies such as GSM, SMS, and GPRS. In addition to computer networks (Ethernet, Wi-Fi) and internet (HTTP, FTP).
The Software Unit (3D-Eye system)
The Software Unit (3D-Eye system)
The 3D-Eye system is network-based computer software with a 3D graphical user interface used to control and monitor smart buildings. Using the 3D interface, the system can monitor and control the building devices such as elevators, escalators, laser detectors, air conditioning, etc. The system also provides various tools and options to display and store videos from the monitoring cameras.
Test Environment (Building model)
Test Environment (Building model)
In order to test the UCSS system from the early development stages, we designed a building model equivalent to the real operating environment. The model has:
Elevator & escalator systems (3 Floors).
Automatic doors.
Security system by laser and monitoring cameras.
Fire alarm system.
Lighting system.
Page updated
Google Sites
Report abuse