Engaging children with ASC (Autism Spectrum Conditions) in communication centred activities during educational therapy is one of the cardinal challenges by ASC and contributes to its poor outcome. To this end, therapists recently started using humanoid robots (e.g., NAO) as assistive tools. However, this technology lacks the ability to autonomously engage with children, which is the key for improving the therapy and, thus, learning opportunities. Existing approaches typically use machine learning algorithms to estimate the engagement of children with ASC from their head-pose or eye-gaze inferred from face-videos. These approaches are rather limited for modeling atypical behavioral displays of engagement of children with ASC, which can vary considerably across the children. The first objective of EngageME is to bring novel machine learning models that can for the first time effectively leverage multi-modal behavioural cues, including facial expressions, head pose, vocal and physiological cues, to realize fully automated context-sensitive estimation of engagement levels of children with ASC. These models build upon dynamic graph models for multi-modal ordinal data, based on state-of-the-art machine learning approaches to sequence classification and domain adaptation, which can adapt to each child, while still being able to generalize across children and cultures. To realize this, the second objective of EngageME is to provide the candidate with the cutting-edge training aimed at expanding his current expertise in visual processing with expertise in wearable/physiological, and audio technologies, from leading experts in these fields. EngageME is expected to bring novel technology/models for endowing assistive robots with ability to accurately ‘sense’ engagement levels of children with ASC during robot-assisted therapy, while providing the candidate with a set of skills needed to become one of the frontiers in the emerging field of affect-sensitive assistive technology.

The objective of INTERLACE is to use the Abstract State Interaction Machines framework (CoreASIM) open source output of the FP7 FET project BIOMICS to develop a decentralized transactional and ledger architecture demonstrator for B2B mutual credit. INTERLACE will add to the work already started by its coordinator, Sardex s.r.l., to develop this architecture. SARDEX will use the Open Transaction protocol (OTX) as an intermediate solution between fully centralized and distributed architectures. OTX involves a pool of Auditor nodes to validate the transactions executed by each Notary node. In INTERLACE there will be only one central Notary, as a first step from the current centralized server towards a more distributed architecture. The persistence layer will be implemented as a private blockchain stored on the central server to create a sparse 160-bit address space implemented as a binary hash tree. This approach achieves continuity with the existing solution while also enabling scalability to multiple circuits (multiple Notaries) under the same mathematical and computational framework. SARDEX has been operating successfully an electronic, B2B, zero-interest mutual credit system on the island of Sardinia since 2009. The Sardex system (also known as Circuito di Credito Commerciale) enables local economic actors (SMEs in particular) to trade with each other in a trustful and circular fashion with a unique digital trade credit unit. It does this by monetizing the spare capacity of the local economy in the form of mutual, and taxable, credit between participating companies, at zero interest, on a strong basis of trust, solidarity, and local cultural identity. Therefore, INTERLACE will address very effectively the Workprogramme objective to generate socio-economic impact from EU-funded research. INTERLACE is uniquely positioned to integrate the very advanced results of BIOMICS directly in a deeply innovative, transformative, and successful fintech platform for B2B trade.

SEMIoTICS aims to develop a pattern-driven framework, built upon existing IoT platforms, to enable and guarantee secure and dependable actuation and semi-autonomic behaviour in IoT/IIoT applications. Patterns will encode proven dependencies between security, privacy, dependability and interoperability (SPDI) properties of individual smart objects and corresponding properties of orchestrations involving them. The SEMIoTICS framework will support cross-layer intelligent dynamic adaptation, including heterogeneous smart objects, networks and clouds, addressing effective adaptation and autonomic behaviour at field (edge) and infrastructure (backend) layers based on intelligent analysis and learning. To address the complexity and scalability needs within horizontal and vertical domains, SEMIoTICS will develop and integrate smart programmable networking and semantic interoperability mechanisms. The practicality of the above approach will be validated using three diverse usage scenarios in the areas of renewable energy (addressing IIoT), healthcare (focusing on human-centric IoT), and smart sensing (covering both IIoT and IoT); and will be offered through an open API. SEMIoTICS consortium consists of strong European industry (Siemens, Engineering, STMicroelectronics), innovative SMEs (Sphynx, Iquadrat, BlueSoft) and academic partners (FORTH, Uni Passau, CTTC) covering the whole value chain of IoT, local embedded analytics and their programmable connectivity to the cloud IoT platforms with associated security and privacy. The consortium is striving for a common vision of creating EU’s technological capability of innovative IoT landscape both at European and international level.