MSCA

Coordinated by Prof. Frank Leferink, the NEPIT project brings together world leading experts from Enschede, Magdeburg, Wrocław, Ancona, Dresden and Eindhoven to create a training Network of highly skilled engineers through an integrated doctoral training program based on research in Evaluation of Propagation and Interference that underpins all future technological developments. Specific innovations expected to be achieved are novel test methodologies, novel modelling strategies, suitable simulation techniques and greater accuracy in EM prediction.
The NEPIT doctoral training objectives are, in line with the needs as stated by the EU10 (Triple-I: international,inter-sectoral and interdisciplinary):
Create the European network for a doctoral School for Evaluation of Propagation and Interference, managed by leading scientists with state-of-the-art infrastructure and covering a wide range of interdisciplinary approaches.Develop a structural doctoral programme in NEPIT by five leading research groups at renowned universities,in close collaboration with industry, and going beyond the usual boundaries such as including standardisation.Strengthen and structure the initial training of researchers in NEPIT at European level.Provide trained researchers with the necessary skills to work and excel in industry.Improve career perspectives by broad skills development.Build a durable consortium in research and training. Therefore exchange of research and doctoral-level education material will continue after the NEPIT project.Already now most of the NEPIT beneficiaries contribute to workshops at the key conferences, and this will continue after NEPIT; but then with the 10 DC. Furthermore several NEPIT beneficiaries already collaborate in standardization working groups, NEPIT will strengthen this collaboration such that also after NEPIT this collaboration continues.
The NEPIT scientific objectives are to develop novel methods to model, simulate, design, evaluate, implement, measure and monitor cost-effective, reliable, and efficient methodologies, including design guidelines in the field of EM propagation and interference, with a particular focus on electrically large (w.r.t. wavelength) and complex systems. These objectives can be achieved by
Modelling the impact of the random EM environment where systems are deployed, and simulating the EM wave propagation characteristics in semi-enclosed environments.Developing new models and simulation methods for the electromagnetic coupling into and out of complex, distributed systems considering the stochastic behaviour of such coupling mechanisms.Developing advanced measurement techniques for EM propagation and interference which allows for greater repeatability and reproducibility.Developing a full experimental evaluation and characterisation method of electrically large systems.Providing industry with novel test methodologies for reliable in-situ EMC measurements and embedding this inworld-wide accepted standards.Providing a robust and reliable measurement uncertainty for measurements performed using reverberation chambers in a standard, as well as in a non-standard fashion.Providing techniques for appropriate and representative emulation of specific, real-life, electromagnetic environments in the laboratory.
The NEPIT societal objectives are the implementation of the newly developed and acquired knowledge into standards and validated methods by close collaboration with industry via secondments, training schools and case studies and thus actually contribute to the Horizon Europe ambition. The inter/multi-disciplinary characteristics are guaranteed by the presence of five academic beneficiaries and one industrial beneficiary (Lumiloop, spin-off company from the Technical University of Dresden) from four countries (the Netherlands, Germany, Poland and Italy) having top class expertise in electromagnetic interference, electronic control, wireless systems, antennas, and propagation. Furthermore, the inter-sectoral characteristic is guaranteed by the support of a series of industrial entities, such as Philips Healthcare, Rohde&Schwarz, EVEKTOR, Fokker, TIM, PIT, THALES, CANON, Kawasaki Heavy Industries, etc., forming a fully interrelated, integrated, and international consortium. The mix of industrial associated partners shows the widespread interest from many sectors, like automotive, security, medical, printing, satellite and professional electronics. The industrial supporters will collaborate by making facilities available for the researchers, present needs and research results at the Training Schools, provide actual case studies, provide practical training during secondments at industry, and being members of the Supervisory Board.

Description: Oil spills rapidly spread on sea surfaces covering wide areas, assuming different appearances and thicknesses. Due to currents and winds, continuous slicks break into smaller fragments which can reach coastal ecosystems and lead to adverse environmental and socio-economic impacts. The faster the actions to detect, stop, and contain the released oil from spreading, the higher the Oil Spill Response (OSR) success rate. Clean-up effectiveness is higher over thicker oil layers, referred to as "actionable oil". Detecting these regions is crucial to guide response vessels allowing a better deployment of barriers and skimmers, enhancing mechanical oil recovery efficiency, in situ burning tasks, as well as aerial-based dispersant application.
Under this scenario, "Searching for Oil Spills on Sea Surfaces" (SOSeas) will employ the latest generation of deep learning methods for semantic segmentation to develop an artificial intelligence (AI) based system to identify relative oil thicknesses by using Synthetic Aperture Radars (SAR). Oil slick characterization is a new, promising and highly innovative research area with great perspectives owing to the availability of free and open Earth Observation products, and to the effectiveness of machine learning algorithms combined with high-performance computing infrastructure based on graphical processing units (GPUs).
A team of scientists and key stakeholders from diverse research institutes, governmental agencies, and private companies are composing the project's advisory panel. This multidisciplinary and intersectoral panel merges complementary skills and expertise within academic and operational scenarios, consolidating an important research network. It is expected that a deep learning architecture well-trained on large-scale datasets to recognize oil thickness variations has the potential to indicate the location of recoverable oil, thereby improving situational awareness, decision-making, and clean-up effectiveness.

Description:  Traffic safety is the fundamental criterion for vehicular environments and many artificial intelligence-based systems like self-driving cars. There are places, e.g., intersections and shared spaces, in the urban environment with high risks where vehicles and vulnerable road users (VRUs) such as pedestrians and cyclists directly interact with each other. By advancing state-of-the-art artificial intelligence methodologies, this project aims to build a privacy-aware deep learning framework to learn road users’ behaviour in various mixed traffic situations for the safety of vehicles and VRUs.
VeVuSafety proposes a 3D environment model based on a 3D point cloud for privacy protection — private information like license plates and faces is anonymized. Then, within this environment model, an end-to-end deep learning framework using camera data will be built for multimodal trajectory prediction, anomaly detection, and potential risk classification based on deep generative models such as the Variational Auto-Encoder.  Besides road user safety and privacy, VeVuSafety can help traffic engineers and city planners to better estimate the design of traffic facilities in order to achieve a road-user-friendly urban traffic environment.
Fig. 1 project profile and work packages
Partners: Leibniz University Hannover, Nara Institute of Science and Technology (NAIST), VISCODA GmbH