For future, novel closely coupled airframe-engine architectures with BLI concepts, current testing technology struggles to accurately assess the inlet flow distortion levels that influence the engine stability due to the low spatial and temporal resolution of current experimental methods. New concepts will require support of numerical means, ground facilities as well as in-flight testing. Non-intrusive, laser-based solutions such as PIV or DGV require the inlet flow to be seeded, which comes with a number of caveats including the requirement of uniform seeding distribution across the measurement plane and the installation of seeding rakes within the intake sub-system. This is notably challenging in airborne measurements. A promising laser-based measuring technology is the seedless Filtered Rayleigh Scattering (FRS) which would be ideal for in-flight measurements. Due to its potential to offer spatial and temporal resolution similar to other laser methods, it allows even highly dynamic flow distortions generated by the geometry of the complex intakes to be clearly understood. SINATRA plans to further mature the FRS technology and provide the necessary outlook by achieving the following: a) Develop and validate up to TRL4 an FRS measuring system prototype, using a CW laser, for time averaged distortion measurements b) upgrade the above prototype, to demonstrate an FRS measuring system working with a pulsed laser thus showing the capability of the technology to measure instantaneous distortions on a unsteady flow up to TRL3, c) provide a ground test inlet distortion facility that will be available to the whole European aeronautical, industrial & scientific community enabling a wide range of non-intrusive flow measurements representative of future architectures to be explored simultaneously and d) use the distortion data from the FRS measurements to characterise the distorted flows that are pertinent to advanced propulsion systems by means of distortion descriptors.

WASTE2FUELS aims to develop next generation biofuel technologies capable of converting agrofood waste (AFW) streams into high quality biobutanol. Butanol is one of the most promising biofuels due to its superior fuel properties compared to current main biofuels, bioethanol and biodiesel. In addition to its ability to reduce carbon emissions, its higher energy content (almost 30% more than ethanol), its ability to blend with both gasoline and diesel, its lower risk of separation and corrosion, its resistance to water absorption, allowing it to be transported in pipes and carriers used by gasoline, it offers a very exciting advantage for adoption as engines require almost no modifications to use it. The main WASTE2FUELS innovations include: • Development of novel pretreatment methods for converting AFW to an appropriate feedstock for biobutanol production thus dramatically enlarging current available biomass for biofuels production • Genetically modified microorganisms for enhancing conversion efficiencies of the biobutanol fermentation process • Coupled recovery and biofilm reactor systems for enhancing conversion efficiencies of Acetone-Butanol-Ethanol fermentation • Development of new routes for biobutanol production via ethanol catalytic conversion • Biobutanol engine tests and ecotoxicological assessment of the produced biobutanol • Valorisation of the process by-products • Development of an integrated model to optimise the waste-to-biofuel conversion and facilitate the industrial scale-up • Process fingerprint analysis by environmental and techno-economic assessment • Biomass supply chain study and design of a waste management strategy for rural development By valorising 50% of the unavoidable and undervalorised AFW as feedstock for biobutanol production, WASTE2FUELS could divert up to 45 M tonnes of food waste from EU landfills, preventing 18 M tonnes of GHG and saving almost 0.5 billion litres of fossil fuels.

In the EU, treating patients with prostate (PCa) and kidney cancer (KC) costs more than €6.6 billion annually. Yet, PCa and KC are often managed inadequately, which is associated with high costs and negative consequences such as hospitalisation, psychosocial stress and poorer chances of survival. Diagnostic and therapeutic effectiveness depends on multimodal information, including cancer type, stage, and location as well as the patient’s age and health. Current clinical methods do not effectively use the large amount of mostly unstructured data. The main challenge in developing multimodal models is the lack of access to data sources and missing joint validation of data through collaboration between clinicians and computer scientists. A strength of our consortium is access to multiple sources of medical data, including the largest expert-annotated database for PCa and KC to date. Our overall goal is to develop and deploy marketable data-driven multimodal decision support systems to improve clinical prognosis, patient stratification and individual therapy for patients suffering from PCa or KC, defining a new state-of-the-art for the development of multimodal medical AI applications. We will develop AI models for PCa and KC that incorporate multimodal data, e.g., image data, unstructured medical text notes, laboratory information and biomarkers, and perform a prospective validation of the models in a large prospective multicentric international study. At the same time, we will assess the trust of healthcare professionals and patients in such AI tools and explore how this trust can be increased. By providing improved, personalised diagnosis and prognosis assessment, the multimodal models will ultimately contribute to better patient outcomes and quality of life. The models developed in this study can be used as basis for any use case where imaging and electronic medical records are relevant, as they are easily adaptable and can help combat different types of cancer.

Health inequities have been increasing in Europe, particularly in a context of an ageing society and economic crisis. In countries with different levels of infrastructures and health system preparedness, inequities create significant policy challenges. The main goal of this project is to advance knowledge of policies that have the highest potential to enhance health and health equity across European regions with particular focus on metropolitan areas. To achieve this goal, the project will develop tools – based on a population health index – to evaluate the health and wellbeing of European population. This index will be informed by evidence on the relationship between multiple determinants (e.g. demographic, social, economic, environmental, lifestyle, and health care) and health outcomes in the past 15 years. It will be constructed using a multicriteria model structure, following a socio-technical approach: integrating the technical elements of a multicriteria value model and the social elements of interdisciplinary and participatory processes. The index will be applied to evaluate the population’s health in 273 NUTS 2 European regions and 9 selected pilot metropolitan areas (covering populations of 28 EU countries). The space-time analysis and comparison of the population health index will be enabled by a user-friendly web-based Geographic Information System. The population health index will be used to foresee and discuss the impact of multilevel policies and combinations of policies in population health and health equity across European regions, thus providing a basis for policy dialogue. Multicriteria resource allocation models, conflict analyses, analysis of policies’ feasibility, and scenario analyses will then assist in providing evidence on which policies have the highest potential to improve health and reduce health inequities at different geographical levels, and in suggesting alternative policy options for health policy development and regulation.

The primary goal of each retailer is to “understand your customers”. Our interviews with retailers show a primary demand from the retail industry for predicting a customer's next demand. Surprisingly , even a complete record of past purchases (and returns) is not sufficient to understand how items in a company's catalog do or do not connect with the customer's general tastes, lifestyle and aspirations. Moverover, from a business perspective, any efficiency gains in the logistics of supplier management, shipping and handling are rather minor, compared to the gains one could obtain from a better understanding of the customers’ personalities and habits. Given that the customer demands trigger proactive stocking and fashion production, this appears as a logical consequence. In this project, we want to consolidate and extend existing European technologies in the area of database management, data mining, machine learning, image processing, information retrieval, and crowdsourcing to strengthen the positions of European fashion retailers among their world-wide competitors. Our choice for the fashion sector is a concise one: i) as a multi-billion euro industry, the fashion sector is extremely important for the European economy; ii) Europe already has a solid position in the world fashion stage, however, to maintain its position and keep up with the competitors, European fashion industry needs the help of advanced technology; and iii) European fashion industry provides an excellent exercise for new technologies, because it is a multi-sectorial by itself (i.e., imposes challenging data integration issues), it has a short life-cycle (i.e., requires timely reaction to the current events) and it involves diverse languages and cultures. The main outcome of the FashionBrain project is the improvement of the fashion industry value chain obtained thanks to the creation of novel on-line shopping experiences, the detection of influencers, and the prediction of upcoming fashion trends. Tangible outcomes will include software, demonstrators, and novel algorithms for a data-driven fashion industry.