In terms of the calibre and variety of services offered to end users, smart city management is undergoing a dramatic transformation. The parties involved in delivering pervasive applications can now solve key issues in the big data value chain, including data gathering, analysis, and processing, storage, curation, and real-world data visualisation. This trend is being driven by Industry 4.0, which calls for the servitisation of data and products across all industries, including the field of smart cities, where people, sensors, and technology work closely together. In order to implement reactive services such as situational awareness, video surveillance, and geo-localisation while constantly preserving the safety and privacy of affected persons, the data generated by omnipresent devices needs to be processed fast. This paper proposes a modular architecture to (i) leverage cutting-edge technologies for data acquisition, management, and distribution (such as Apache Kafka and Apache NiFi); (ii) develop a multi-layer engineering solution for revealing valuable and hidden societal knowledge in the context of smart cities processing multi-modal, real-time, and heterogeneous data flows; and (iii) address the key challenges in tasks involving complex data flows and offer general guidelines to solve them. In order to create an effective system for the monitoring and servitisation of smart city assets with a scalable platform that proves its usefulness in numerous smart city use cases with various needs, we deduced some guidelines from an experimental setting performed in collaboration with leading industrial technical departments. Ultimately, when deployed in production, the proposed data platform will contribute toward the goal of revealing valuable and hidden societal knowledge in the context of smart cities.

Smart city management is going through a remarkable transition, in terms of quality and diversity of services provided to the end-users. The stakeholders that deliver pervasive applications are now able to address fundamental challenges in the big data value chain, from data acquisition, data analysis and processing, data storage and curation, and data visualisation in real scenarios. Industry 4.0 is pushing this trend forward, demanding for servitization of products and data, also for the smart cities sector where humans, sensors and devices are operating in strict collaboration. The data produced by the ubiquitous devices must be processed quickly to allow the implementation of reactive services such as situational awareness, video surveillance and geo-localization, while always ensuring the safety and privacy of involved citizens. This paper proposes a modular architecture to (i) leverage innovative technologies for data acquisition, management and distribution (such as Apache Kafka and Apache NiFi), (ii) develop a multi-layer engineering solution for revealing valuable and hidden societal knowledge in smart cities environment, and (iii) tackle the main issues in tasks involving complex data flows and provide general guidelines to solve them. We derived some guidelines from an experimental setting performed together with leading industrial technical departments to accomplish an efficient system for monitoring and servitization of smart city assets, with a scalable platform that confirms its usefulness in numerous smart city use cases with different needs.

The AI4Agriculture Grape Dataset is a collection of 250 images taken in a vineyard in Ribera de Duero. The grapefruits are from the Tempranillo variety. The images are annotated using bounding boxes. The goal of this dataset is to provide images and the associated annotations to train and validate object detection models. These models can be used in viticulture applications, such as yield estimation, fruit counting, and field robotics. The images were taken in twelve different parcels. Six areas were defined in each parcel. Each area contains several lines of plants (grapevines). For each line of plants, 4 picture samples have been taken (two on each side). The samples are from non-contiguous grapevines, so the pictures never overlap. The pictures were taken by a Xiaomi Redmi 8 (with resolution 4032x3024), Xiaomi Mi A3 (with resolution 3000x4000) and a Xiaomi Redmi 9 (with resolution 3264x2448). To avoid showing grapes from other rows, the pictures were taken at approximately half the height of the vine-tree rows. For each image, a .xml file was generated, with the Pascal VOC format, containing all the labeled items (with bounding boxes) in that image. Annotations in YOLO format are also provided (*.txt). The labeling methodology is described in this document. Some images have issues: i) reflections caused by the sun ii) group of grapes partially hidden by leaves or iii) hidden by other objects (e.g. irrigation pipes), iv) color and direction similar to a tree trunk v) dead grapes in the floor or vi) grapes from the plant behind the plant analyzed. The images were captured by SmartRural and annotated by ATOS, UPC, Deutsches Zentrum für Luft- und Raumfahrt, and National and Kapodistrian University of Athens in the framework of the AI4Agriculture pilot of the AI4EU project.

A Smart City based on data acquisition, handling and intelligent analysis requires efficient design and implementation of the respective AI technologies and the underlying infrastructure for seamlessly analyzing the large amounts of data in real-time. The EU project MARVEL will research solutions that can improve the integration of multiple data sources in a Smart City environment for harnessing the advantages rooted in multimodal perception of the surrounding environment.

The digitization of manufacturing industry has led to leaner and more efficient production, under the Industry 4.0 concept. Nowadays, datasets collected from shop floor assets and information technology (IT) systems are used in data-driven analytics efforts to support more informed business intelligence decisions. However, these results are currently only used in isolated and dispersed parts of the production process. At the same time, full integration of artificial intelligence (AI) in all parts of manufacturing systems is currently lacking. In this context, the goal of this manuscript is to present a more holistic integration of AI by promoting collaboration. To this end, collaboration is understood as a multi-dimensional conceptual term that covers all important enablers for AI adoption in manufacturing contexts and is promoted in terms of business intelligence optimization, human-in-the-loop and secure federation across manufacturing sites. To address these challenges, the proposed architectural approach builds on three technical pillars: (1) components that extend the functionality of the existing layers in the Reference Architectural Model for Industry 4.0; (2) definition of new layers for collaboration by means of human-in-the-loop and federation; (3) security concerns with AI-powered mechanisms. In addition, system implementation aspects are discussed and potential applications in industrial environments, as well as business impacts, are presented.

While several application domains are exploiting the added-value of analytics over various datasets to obtain actionable insights and drive decision making, the public policy management domain has not yet taken advantage of the full potential of the aforementioned analytics and data models. Diverse and heterogeneous datasets are being generated from various sources, which could be utilized across the complete policies lifecycle (i.e. modelling, creation, evaluation and optimization) to realize efficient policy management. To this end, in this paper we present an overall architecture of a cloud-based environment that facilitates data retrieval and analytics, as well as policy modelling, creation and optimization. The environment enables data collection from heterogeneous sources, linking and aggregation, complemented with data cleaning and interoperability techniques in order to make the data ready for use. An innovative approach for analytics as a service is introduced and linked with a policy development toolkit, which is an integrated web-based environment to fulfil the requirements of the public policy ecosystem stakeholders.

In the era of Big Data and AI, it is challenging to know all technical and business advantages of the emerging technologies. The goal of DataBench is to design a benchmarking process helping organizations developing Big Data Technologies (BDT) to reach for excellence and constantly improve their performance, by measuring their technology development activity against parameters of high business relevance. This paper focuses on the internals of the DataBench framework and presents our methodological workflow and framework architecture.

Big Data integration in European cities is of utmost importance for municipalities and companies to offer effective information services, enable e cient data-driven transportation and mobility, reduce CO2 emissions, assess the e ciency of infrastructure, as well as enhance the quality of life of citizens. At present this integration is substantially limited due to the following factors: 1) Urban Big Data is locked in isolated industrial and public sectors, and 2) The actual Big Data integration is an extremely hard technical problem due to the heterogeneity of data sources, variety of formats, sizes, quality as well as update rates, such that the integration requires signi cant human intervention.

In order to reduce the initial investments needed by small and medium enterprises (SMEs) to acquire the necessary expertise, hardware and software to run proper Big Data Analytics, TOREADOR proposes a Big Data Analytics framework which supports users in devising their own Big Data solutions by keeping the inherent costs at a minimum. Among the objectives of the TOREADOR framework is supporting developers in parallelizing and deploying their algorithms, in order to develop they own analytics solutions. This paper describes the Code-Based approach, developed by CINI and adopted within the TOREADOR framework to parallelize users' algorithms and deploy them on distributed platforms, with a focus on its integration with the web services and resources offered by ATOS for the actual deployment of the solution.

This document proposes an evaluation and monitoring approach for the DataBench framework based on the current ISO/IEC standards for system and software quality. The developed methodology adapts multiple quality factors implemented using technical metrics in order to assess the DataBench framework capabilities from different user perspectives. Furthermore, the approach is integrated in the existing DataBench workflow and modular architecture, and can be implemented using the technology frameworks applied in the Alpha release (deliverable D3.2) of the DataBench Toolbox. The resulting functionality can be seen as a set of interactive evaluation reports realized in the form of web dashboards depicting multiple technical metrics for the different user-roles in the DataBench framework. This document is the second deliverable in WP5 after D5.1 reporting the results from the activities in Task 5.2 related to the technical usability, relevance, scale, complexity and other quality metrics of the DataBench Framework. Ref. Ares(2019)4137114 30/06/2019 Deliverable D5.3 Assessment of Technical Usability, Relevance, Scale and Complexity

The European virtual physiological human initiative develops a platform, called VPH-Share, for understanding physiological processes in the human body in terms of anatomical structure and biophysical mechanisms. Besides storing, sharing, integrating and linking a wide variety of heterogeneous bio-medical datasets relevant to the VPH community, the project envisions the facilitation of a secure data infrastructure, as well as search and exploration facilities based on semantic technologies. The data infrastructure and management platform are built on top of a hybrid cloud environment. The data management platform offers tools that cover the whole life-cycle of datasets including integration, selection, semantic annotation and publishing datasets as a service. A comprehensive user interface enables end-users to search and to explore bio-medical data with support of semantic technologies, concealing the complexity of the underlying service environment. In this paper we describe the data infrastructure that has emerged in context of the project.

The standardisation of the architecture of electronic healthcare records is essential for two reasons: i) the records are being used to support shared care among clinicians with different specializations; ii) the standardisation process eases the introduction of mobile technologies within and among countries between people who provide and receive healthcare. It is a common problem previously addressed in the literature that already existing EHR approaches often present interoperability issues that restrain their effective application, since the different system components do not share a common nomenclature, data types, message syntax and encoding rules. Hospitals cannot share the clinical information of the patient. yourEHRM architecture implements standards that enable the exchange of desired medical information. The solution is based on generic information models that conform to openEHR/EN13606 archetypes associated with concepts of well-known terminologies such as SNOMED-CT. Besides it offers the possibility to exchange information with other Hospital Information Systems (HIS) using Health Level 7 (HL7) Clinical Data Architecture (CDA), Continuity of Care Record (CCR), Continuity of Care Document (CCD) or virtual Medical Record (vMR) as the payload. The architecture also permits the integration of data coming from heterogeneous and fragmented healthcare information systems and devices into the EHR.

The European VPH-Share project develops an integrated modular and generic framework for understanding physiological processes in the human body in terms of anatomical structure and biophysical mechanisms. One of the major challenges besides managing and sharing a wide variety of heterogeneous bio-medical data sources relevant to the VPH community is facilitating the search and exploration of these data using semantic technologies. The VPH-Share data infrastructure and management platform has been built on top of a Cloud-based service framework that can take advantage of both public and private IT resources. The data management platform offers tools that cover the whole life-cycle of data integration, selection, semantic annotation and publishing. A comprehensive user interface enables end users to search and explore bio-medical data with the support of semantic technologies, shielding them from the complexity of the underlying IT environment.

TaToo – Tagging tool based on a semantic discovery framework, a project funded by the European Commission provides a web-based solution for easy and accurate discovery as well as tagging of environmental resources. The novelty relies on a semantic framework integrating different domain ontologies in a multi-domain and multilingual context. The underlying ontology framework, comprises besides the different domain ontologies (e.g. related to climate change, agro-environmental and anthropogenic impact domains) also concepts and methods to establish a mapping between the domain ontologies and so-called minimal environmental resource model (MERM). Together this forms a suitable and usable bridge ontology allowing a cross-domain discovery by using aligned ontologies concepts from different domains. The clear advantage for the end-user is that he is now able to find relevant information stemming from other domains, (like from impact of pollutant, climate change or temperature on human health) that he would not have found before but would be even more important to him that the ones only from his domain of expertise. The TaToo semantic framework extends cross-domain search evolving towards the Linked Data initiative by providing a linking functionality. The cross-domain search can be extended including in the search results also linked resources.

Difficult to find, difficult to understand! Can we trust this information? How reliable are these data? Would these data or model serve my needs? Uncountable questions are now being raised by numerous end users, after the result of their search query returned some (or tons) of information on the web. TaToo tries to improve the success rate for reliable and understandable results on the web by a new and promising approach. TaToo is developing a semantic framework providing tools and services for information enrichment and discovery of environmental resources based on a service-oriented and semantically enhanced architecture. Having available semantic descriptions of environmental resources clearly facilitates the search and discovery of information, as semantics provide "meaning" to items, and allows the search engine to go beyond simple statistical searches, which often return unrelated hits. But this needs a lot of meta-information and semantic information someone would have to enter. The gap between the need for semantics and its general availability is what TaToo is addressing. TaToo facilitates the annotation of environmental resources by providing tagging tools and services so that related to the user's domain and expertise they could enter (tag, comment, rate, etc.) a specific item from the world wide information pool. At the same time TaToo offers discovery tools and services based on the previously entered semantic annotation, thus allowing to return to the user search results improved with quality, uncertainty and ranking information. TaToo relies on specially developed resource and semantic models, the Minimum Environmental Resource Model, called MERM, and the usage of bridge ontologies, in order to realize semantic interoperability between different environmental domains. Combined with several multilingual aspects TaToo will be able not only to cross-link information stemming from one language area but also from different ones. This paper describes the architecture and the ontology framework of TaToo, then it details how we address interoperability issues using the MERM model and bridge ontologies; finally it describes the user interaction with the TaToo framework, describing the TaToo portal as the TaToo entry point.