PhysioSense: Embedded AI for Personalized Predictive Diagnosis through Multimodal Physiological Sensor Fusion

Descriptif du sujet
Title :

PhysioSense: Embedded AI for Personalized Predictive Diagnosis through Multimodal Physiological Sensor Fusion

Brief description :

The PhysioSense PhD project aims to develop an embedded AI system for personalized predictive diagnosis using multimodal physiological sensor fusion. By integrating data from sensors such as heart rate, ECG, SpO₂, temperature, and skin conductance, the system will provide real-time, non-invasive, and context-aware health assessment directly on wearable or medical devices. It will employ lightweight deep learning models (TinyML, MobileNet) and advanced fusion methods (attention-based or Bayesian approaches) to detect early anomalies like cardiac, respiratory, or stress-related disorders. Designed for low-power edge hardware, the solution ensures privacy, speed, and offline functionality, while explainable AI modules enhance transparency and clinical trust. This project contributes to interpretable biomedical AI and supports accessible, preventive, and personalized healthcare for all.

Research environment :

Candidates are expected to carry out their research full-time within the structures of EUROMED University.

PhD student’s responsibilities :

 

  • Design and implement algorithms for multimodal physiological signal preprocessing and fusion.
  • Develop and train lightweight deep learning models for real-time health anomaly detection on embedded systems.
  • Integrate the models into wearable or medical devices using edge AI frameworks such as TensorFlow Lite or Edge Impulse.
  • Implement explainable AI techniques to visualize sensor contributions and improve clinical interpretability.
  • Conduct experimental validation using real or simulated physiological datasets.
  • Contribute to scientific publications, conference presentations, and potential prototype demonstrations

 

Candidate profile :

Master’s degree in Embedded Systems, Biomedical Engineering, or AI, with experience in physiological signal processing and edge-AI deployment. Interest in real-time health diagnostics and wearable technologies is highly recommended.

The application file must include the following documents :

CV, a cover letter, the PhD project, diplomas, and academic transcripts.

Submission of the application file :

The application file must be sent to the Doctoral Studies Center (CEDoc) of the Euro-Mediterranean University of Fes by email no later than October 26, 2025, to the following contacts:

Administrative Affairs Officer of the CEDoc: Mrs. Boutaina Jai Mansouri : : b.jai-mansouri@emadu.ueuromed.org)

Director of Research and of the CEDoc: Prof. Abdelghafour Marfak : : a.marfak@euromed.org)

Thesis supervisor :

• Pr. Sara BAKKALI (s.bakkali@insa.ueuromed.org)