When you access EPFL websites, we may set cookies on your devices and process personal data about you in accordance with our privacy policy. You can block cookies by using your browser settings.
DIGIPREDICT proposes the first of its kind Edge AI Digital Twin, designed, developed and calibrated on experiments, based on the interaction between Digital Biomarkers, Organ-On-Chip (OoC) and Artificial Intelligence (AI) at Edge technologies, with the goal of identifying a specific dynamic digital fingerprint of the complex disease progression and building and assistive tools for medical doctors and patients. We will combine scientific and technical excellence in multiple disciplines and we aim at building a new interdisciplinary community in Europe centred on Digital Twins.
DIGIPREDICT proposes the first of its kind digital twin to predict the progression of disease and the need for early intervention in infectious and cardiovascular diseases. In the scope of this project, ESL contributes to the improvement of the energy efficiency and the privacy of the architecture by exploiting local computation at the Edge nodes. This task focuses on moving data analysis workloads closer to the sensors, providing simultaneous benefits on energy efficiency and data privacy. This involves the computing, memory, and energy profiling of the algorithms, the identification of the critical parts, and a distributed implementation between the available devices. The objective will be to extend the physiological sensors developed by project partners so that each one is capable of processing most of the captured data, and producing just the information required at a higher level for data fusion.