🌐 Website • LinkedIn • Google Scholar • ResearchGate • ORCID
I build AI systems that identify people from physiological and behavioural signals — and deploy them on the hardware that actually exists in the field.
My PhD (Badji Mokhtar – Annaba University, 2025 — Very Honorable with Committee Praise) focused on combining ECG and voice in a multimodal biometric system using score-level fusion, achieving identification performance that consistently outperforms either modality alone. In parallel, I developed hardware-optimised CNN and GRU architectures that run directly on ESP32 and STM32 microcontrollers using TinyML — no cloud, no server, no GPU required.
10 journal articles · 6 conference papers
| Area | What I work on |
|---|---|
| Biometric identification | ECG, voice, handwritten signatures, multimodal fusion |
| Deep learning | CNNs, GRUs, LSTMs for time-series and signal data |
| Edge AI / TinyML | Model quantization, TFLite Micro, ESP32, STM32 deployment |
| Signal processing | EMD, Hilbert-Huang Transform, MFCC, spectrogram analysis |
| Medical AI | Healthcare-optimised embedded systems, blood typing datasets |
- Unifying heartbeats and vocal waves: An approach to multimodal biometric identification at the score level — Arabian Journal for Science and Engineering, 2025
- EMD based biometric identification system from electrocardiogram signals using GRU neural networks — Multimedia Tools and Applications (Q1), 2025
- Hardware-optimised CNN architecture for ECG biometric identification on embedded systems — IJSISE, 2025
- Healthcare Decision-Making with an ECG-Based Biometric System — IEEE DASA, 2023
- ABO-BTI: An Open-Source ABO Blood Typing Image Dataset for Medical AI Applications — Advances in EEE, 2025
→ Full list on Google Scholar and ResearchGate
languages = ["Python", "C", "C++", "MATLAB", "Assembly"]
frameworks = ["TensorFlow", "TFLite Micro", "Edge Impulse", "FreeRTOS"]
hardware = ["ESP32", "STM32", "Arduino", "Raspberry Pi"]
domains = ["Biometrics", "TinyML", "Signal Processing", "Embedded AI"]- 🔬 Research Fellow on AI-Enhanced PIV processing — Beijing Institute of Technology (collaborative project)
- 🎓 Open to postdoctoral positions in biometrics, edge AI, or related fields
- 📝 Peer reviewer — Scientific Reports · BMC Cardiovascular Disorders