Deep Learning (DL) algorithms are an extremely promising instrument in artificial intelligence, achieving very high performance in numerous recognition, identification, and classification tasks. To foster their pervasive adoption in a vast scope of new applications and markets, a step forward is needed towards the implementation of the on-line classification task (called inference) on low-power embedded systems, enabling a shift to the edge computing paradigm. Nevertheless, when DL is moved at the edge, severe performance requirements must coexist with tight constraints in terms of power/energy consumption, posing the need for parallel and energy-efficient heterogeneous computing platforms. Unfortunately, programming for this kind of architectures requires advanced skills and significant effort, also considering that DL algorithms are designed to improve precision, without considering the limitations of the device that will execute the inference. Thus, the deployment of DL algorithms on heterogeneous architectures is often unaffordable for SMEs and midcaps without adequate support from software development tools. The main goal of ALOHA is to facilitate implementation of DL on heterogeneous low-energy computing platforms. To this aim, the project will develop a software development tool flow, automating: • algorithm design and analysis; • porting of the inference tasks to heterogeneous embedded architectures, with optimized mapping and scheduling; • implementation of middleware and primitives controlling the target platform, to optimize power and energy savings. During the development of the ALOHA tool flow, several main features will be addressed, such as architecture-awareness (the features of the embedded architecture will be considered starting from the algorithm design), adaptivity, security, productivity, and extensibility. ALOHA will be assessed over three different use-cases, involving surveillance, smart industry automation, and medical application domains

Climate change and human history are closely linked. Paleoclimate studies are essential for improving climate models, particularly for the 60–12 ka period, characterized by glacial conditions and rapid millennial-scale climatic fluctuations. Investigating these oscillations is crucial for assessing modern global warming and its impact on extreme weather events and sea level rise. Conversely, the millennial-scale climate shifts after 12 ka drove mass migrations and economic transformations, leaving significant archaeological evidence. Paleoclimate studies and archaeology share methodologies like stratigraphic event definition and absolute dating, which are based mainly on 14C (up to 50 ka for organic materials) and luminescence techniques (up to 1 My for quartz and k-feldspar-rich samples). This study focuses on niche environments like islands and desert regions. The former preserve strong evidence of climate change and human activity, particularly in the Mediterranean, while the latter are considered modern analogues of past glacial arid conditions. Key sites include Sardinia, Crete, Cyprus, Balearic, Canaries islands and deserts in California, Texas and Argentina. DETECTOR builds on the IN-TIME project (IN-SITU INSTRUMENT FOR MARS AND EARTH DATING APPLICATIONS, G.A. 823934), which developed and validated a portable luminescence dating prototype (compared to lab analyses) through Alma Sistemi S.r.l. and the Luminescence Laboratory of the University of Sassari, Italy. Proposed studies will include field campaigns using updated portable instruments for in situ absolute dating. Measurements will be cross-verified with laboratory analyses to assess the instrument’s functionality, operational reliability, and performance, paving the way for a novel scientific instrumentation product. DETECTOR unite the expertise of partners from Italy, Spain, Cyprus, Greece, USA & Argentina.

The SHERLOCK project aims to boost innovation at European level by designing and implementing an original and advanced educational framework based on microcredentials for upskilling the workforce and lifelong learning. It will integrate and combine a multidisciplinary green and digital skills portfolio towards the cooperation and knowledge exchange flow across different stakeholders, bolstering job creations and supporting the ambitious target of mass energy building retrofitting. Fostering retrofitting in the building sector, which accounts for 40% of the EU primary energy consumption and 35% of the carbon emissions, is paramount to achieve the EU decarbonisation targets by 2050. This requires a skilled workforce able to navigate through the multidisciplinary dimensions of building energy retrofitting, encompassing both technical, financial, and societal aspects.SHERLOCK aims to tackle this challenge by creating a MOOC-based MicroMaster programme and a VET oriented short training course based on microcredentials and case study education, targeting students and professionals from both the building energy retrofitting and financial sectors. The project will help overcome the skills mismatch between financial operators and project developers. The programme will be codesigned with VET providers and stakeholders through the setup and deployment of the SHERLOCK Knowledge Centres, which will act as a reference point for exchanging ideas and as a lasting alliance between universities, businesses, VET providers and public institutions. SHERLOCK will define the learning objectives, design the programme content & materials, implement and monitor the acquisition of the green and digital skills required in the building energy renovation sector. Finally, it will develop guidelines for educators in higher education institutions and VET providers on how to co-design and implement innovative MicroMaster programmes to support lifelong learning and upskilling of the labour market.