Quentin Mascret obtained the master’s degree in electrical and Application Eng. from Ecole Nationale Supérieure de l'Electronique et ses Application of Paris (France) in 2017, then he obtained his Ms.C in Electrical Eng, from Laval University of Québec in 2018. He is currently a doctoral candidate in Electrical and Computer Engineering at Benoit Gosselin's laboratory
Project : The Internet of Medical Objects (IoMT) applied to people with epilepsy: prevention, detections and intelligent closed-loop alerts.
The project consists of creating a smart textile incorporating a multitude of interconnected star sensors that acquire various physiological measures (ECG, sEMG, respiratory and visual) and inertial measurements (motion detection). The EEG will be an additional module outside the intelligent textile that will take the form of glasses (e-Glass ) or in the form of an electrode strip. The module can evolve according to the technological advances. The set of sensors will communicate by Bluetooth 5 protocol with AES 128-bit encryption to ensure the confidentiality of medical data to a receiving station (cell or base station depending on whether the patient is traveling or home). The data will be processed in real time on the base station when the patient is at home. Conversely, when the patient is traveling, these tasks will be performed by the main node (mother sensor). He will then forward the cellular / base station alerts to alert the patient and the nearest health services for a quick response. In addition, an innovative principle based on the Blockchain will be integrated. It's about protecting sensitive patient data by sharing it encrypted to multiple computers to prevent falsification and hacking. Finally, machine and deep learning layers will be used to make models of artificial intelligence. These will prevent and anticipate epileptic seizures. The objective is to propose a prediction with quantification on the time that the patient has before his next crisis. This time will become more and more precise following the trainings resulting from pre-ictal and ictal patient collections.