Wireless biomedical sensors should dramatically reduce the costs and risks associated with personal health care, while being more and more exploited by telemedicine and efficient e-health systems. However, because of the large power consumption of continuous wireless transmission, the battery life of the sensors is reduced for long-term use. Sub-nyquist continuous-time discrete-amplitude (CTDA) sampling approaches using level-crossing analog-to-digital converters (ADCs) have been developed to reduce the sampling rate and energy consumption of the sensors. However, traditional machine learning techniques and architectures are not compatible with the non-uniform sampled data obtained from level-crossing ADCs. This project aims to develop analog algorithms, circuits and systems for the implementation of machine learning techniques in CTDA sampled data in wireless biomedical sensors. This “near-sensor computing” approach, will help reduce the wireless transmission rate and therefore the power consumption of the sensor. The output rate of the CTDA is directly proportional to the activity of the analog signal at the input of the sensor. Therefore, artificial intelligence hardware that processes CTDA data should consume significantly less energy. For demonstration purposes, a prototype biomedical sensor for the detection and classification of sleep apnea will be developed using integrated circuit prototypes and a commercially available analog front-end interface. The sensor will acquire electrocardiogram and bioimpedance signals from the subject and will use data fusion techniques and machine learning techniques to achieve high accuracy.

Implantation of the embryo in a receptive uterus is critical for mammalian reproduction, yet remains poorly understood. This challenge is particularly significant in human health, as up to two-thirds of human pregnancies are lost due implantation failure. In the agricultural sector, particularly in sustainable milk and meat production, understanding and improving embryo implantation is equally crucial. High peri-implantation mortality rates in livestock lead to lower efficiency, profitability, and environmental sustainability. Much remains unknown about the molecular pathways and regulatory mechanisms of embryo-endometrial interactions in humans and livestock species. For ethical and practical reasons, implantation cannot be adequately studied in vivo in human, and it remains challenging in most animal models. IMPLANTEU is an international community of researchers whose objectives are: 1) To develop a molecular blueprint of human implantation in health and disease; 2) To improve implantation fitness for food production mammals and 3) To develop an advanced toolkit for implantation research. IMPLANTEU provides multi-species, multi-sector and multi-model molecular and system implantation research, integrating complementary expertise in reproductive and stem cells biology, medicine, physiology, ethics and law, and cutting-edge technologies such as stem cell-based embryo models, organoids, machine learning, and organ-on-chip. IMPLANTEU will train 13 doctoral candidates through research, innovation, secondments in academic and industrial environments, horizontal and focused courses, and interactions with stakeholders. The findings generated through IMPLANTEU will contribute to the profound understanding of the embryonic and endometrial contribution to reproductive success, innovations in infertility treatment, animal production efficiency and sustainability, tissue bioengineering, pathogen-host interaction, reproductive toxicology, and stem cell biology.

Coding theory is a cornerstone of the mathematics of communications. It an interdisciplinary field, lying at the intersection of mathematics, computer science and electrical engineering. It is a fundamental tool of every system of digital communications, with applications to error-correction, distributed storage, wireless communications, secure multi-party computation and post-quantum cryptography. The ENCODE doctoral network will focus on fundamentals and applications of coding theory to security, privacy and efficiency of distributed communication & computation. The DN will leverage the complementary expertise of 7 academic and 5 non-academic partners, to guide its 8 DCs to address and solve deep problems in coding theory and its applications. The DN will offer a superior supervisory experience for each DC, who will each benefit from the expertise of multiple advisors in academia and industry. The non-academic partners include 5 companies working at the cutting edge of cybersecurity, who will offer invaluable contributions to the training programme via hosting of DCs and input in advanced training sessions. DCs will be exposed to current technical challenges faced by industry and will have the opportunity to apply mathematics to tackle real-world problems during industrial secondments. ENCODE will create a unique training programme, designed to equip its DCs with the scientific tools and transferable skills required for them to become future leaders in the field, both in academia and in industry. The ENCODE programme will implement all EC Principles for Innovative Doctoral Training, adhere to best practice as outlined in the EU Charter & Code, the MSCA Green Charter, and ensure gender equality in all aspects of its activities, to create a lasting international, intersectoral, interdisciplinary doctoral network, dedicated to excellence in science, ethical standards & communications that will extend far beyond the DN.