5G-ROUTES is a 5G-PPP Phase 3 project whose aim is to validate through robust evidence the latest 5G features and 3GPP specifications (R.16 & R.17) of CAM under realistic conditions. In particular, it will conduct advanced large-scale field trials of most representative CAM applications to demonstrate seamless functionality across a prominent 5G cross-border corridor (Via Baltica-North), traversing Latvia, Estonia and Finland. This will help to boost confidence and accelerate the deployment of 5G-based interoperable CAM ecosystems and services throughout Europe. It also aims at validating 5G as a true enabler of innovative CAM services that cannot be realised by today’s technology. Specifically, 5G-ROUTES will provide: (a) validation of >150 network, business and service-level KPIs for 13 diverse CAM use cases that require 5G performance capabilities, covering several V2X scenarios in automated cooperative, awareness and sensing driving. 5G-ROUTES also focuses on uninterrupted infotainment passenger services on the go and multimodal services in the context of complete connectivity-enabled ecosystems around passengers and cargo over 3 different modes of transport (vehicles, rails and maritime); (b) innovative AIbased technological enablers for facilitating the execution of the field trials. Several scenarios will be considered for each use case covering cross-border, cross-telecom operators, cross telco-vendors, integrated cross terrestrial-satellite and cross-transport-mode settings. These will be incrementally validated, starting from lab trials, followed by localised large-scale trials at strategic cross-border locations (Valga city, Tallinn & Gulf of Finland) and finally in larger-scale trials covering significant portions of transport routes along the selected corridor. Our 22-partner consortium is driven by industry heavyweights and renowned organisations the majority of which participate in 30 out of 63 5G-PPP projects and in several 5G-PPP Working Groups.
New or reoccurring bacterial threats are a major challenge of this century, and a delayed response due to the lack of field-testing options risks human lives and causing an epidemic. Classical microbiology techniques are relatively slow, while cytometric methods allow the measurement of cell count, morphology etc. in an easy, reliable, and fast way. State of the art flow cytometers are high-throughput benchtop instruments that are neither portable nor cheap enough for field testing, causing logistic delays in bacterial testing in remote areas and conflict zones or where infrastructure is limited. The goal of this R&D activity is to create the proof of concept of and develop the methodology for low-cost, fully portable flow cytometers based on droplet microfluidics, which will not only allow field analysis of bacteria, but will have a single-cell resolution. Furthermore, through cognitive electronics, the system will be easy to use and fully automated from sample input to result output.
Worldwide, 2 million neural disease patients may benefit from functional electrical stimulation. Existing wearable assistive actuators (e.g. neuromuscular stimulators) lack context and situational awareness, and thus increase the patients’ safety risks and reduce their quality of life. We propose an innovative closed-loop wireless communication system that adds i) intelligent monitoring, ii) automated neuromuscular stimulation, iii) feedback from the actuator-to-coordinator for tuning and decision-making. We will: -investigate and select the suitable emerging wireless communication technology that meets the time-critical application requirements -propose novel coexistence strategies to avoid congestion and achieve higher throughput -develop task sharing and scheduling solutions to meet the time, energy, and reliability constraints -Implement, test and validate the developed solution on partially disabled neurodegenerative disease patients in cooperation with practicing clinicians.
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 analogto- 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 levelcrossing 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.