DiTEC proposes an evolutionary approach to real-time monitoring of water networks that detects inconsistency between measured sensor data and the expected situation, and performs real-time model update without needing additional calibration. Deep learning will be applied to create a data-driven simulation of the system. In case of leaks, valve degradation or sensor faults, the model is adapted to the degraded network until the maintenance takes place, which can take a long time. We will analyse the effect on data readings of different malfunctions, and construct a mitigating mechanism that allows to continue using the data, albeit in a limited capacity.
DDTclean focuses on the development of future-facing wastewater treatment technologies. These novel technologies can provide intelligent wastewater governance, including collection and treatment, with the help of electrochemical-membrane technologies and scalable Artificial Intelligence enhanced distributed Digital Twin framework. This project addresses the existing dilemma of low treatment efficiency of decentralised wastewater, while facilitating the communication and coordination of multiple stakeholders, aiming to improve the environmental quality, especially in remote areas, and to contribute to system-wide optimal operations.
In the past years, the collection of data has increased significantly. Large scale data analysis requires a distributed server cluster where the data is divided among the available machines such that it can be processed in parallel, speeding up the analysis substantially. , Distributed data processing platforms such as Spark have become a de-facto standard in the world of large-scale data processing. The data processing pipelines for such platforms are composed during design time and then submitted to the central “master” component who then distributes the code among several worker nodes. However, in many situations, the application is not static and evolve over time: the developers add new processing steps, data scientists adjust parameters of their algorithm and quality assurance discovers new bugs. Currently, an update of the pipeline looks as follows: the developers patch their code, re-submit the updated version, and finally restart the entire pipeline.
However, restarting the processing pipeline safely is difficult: the intermediate state is lost and needs to be re-computed; some data needs to be reprocessed and, finally, the cost of restarting may not be trivial - especially for real-time streaming components that require 24x7 availability. In this project we investigate the possibility to support evolving data-intensive applications without the need for restarting them when the requirements change (e.g., new data sources or algorithms are available).
Industry 4.0 is focused on information systems bringing together data from a large variety of sources. These data are subject to analytics to become the high fidelity information that enables systems to become more intelligent and autonomous. In these digital processes, Artificial Intelligence (AI) plays a central role in creating the necessary autonomy.
In the Industrial transformation, there are frontrunners, followers and laggards among professionals, students and teachers. This AI-focused education project brings these groups together to accelerate the digital transformation.
Next to teaching new generations of students, professional education of technical workers and teachers is crucial because most of the current workforce has not received formal education in these digital technologies. This project will deliver state-of-the-art AI education using practical industry-relevant use cases to professionals and students in four countries, in co-operation with private companies.
My-TRAC project aims to deliver an innovative application for seamless transport and an ecosystem of models and algorithms for Public Transport – PT user choice simulation, data analytics and affective computing. My-TRAC stands out from other technologies due to three main reasons. First, My-TRAC fosters unprecedented involvement of users during, before and after a trip through a smart Human-Machine interface and numerous functionalities such as crowdsourcing, group recommendations, data exchange. Second, the application implements a vast array of technologies, such as affective computing, Artificial Intelligence and user choice simulation, that fuse expertise from multiple fields. Third, My-TRAC facilitates engagement of multiple stakeholders by seamlessly integrating services and creating connections between Rail operators, Mobility as a Service and other PT providers.
The project explored the market potential for a travel decision assistance e-tool, allowing users to obtain personalized ‘green’-multimodal recommendations for clean urban mobility choices in large and complex metropolitan areas; thus contributing to the transition towards more liveable, zerocarbon and resilient cities.
The following specific objectives were tackled: (1) Conduct an exploratory analysis of the market opportunities for implementing a travel decision assistance e-tool which promotes multimodality in a complex metropolitan context, and evaluate them from both demand side (travellers) and supply side (mobility services providers, ITS developers and city authorities). (2) Identify potential users in the market through the recognition of archetypal traveller profiles, as well as factors impacting their different behaviours. Evaluate the role of heterogeneity and attitudes towards risk and uncertainty in route choice decisions. (3) Identify potential investors in the mobility marketplace, interested in incorporating the etool to their business activities as part of Mobility as a Service (MaaS) strategies.
The protection of critical infrastructures increasingly demands solutions which support incident detection and management at the levels of individual CI, across CIs which are depending on each other, and across borders. An approach is required which really integrates functionalities across all these levels. Cooperation of privately operated CIs and public bodies (governments and EU) is difficult but mandatory. After about 10 years of analysis and research on partial effects in CIP and for individual infrastructure sectors, ECOSSIAN is supposed to be the first attempt to develop this holistic system in the sense portrayed above.
A prototype system will be developed which facilitates preventive functions like threat monitoring, early indicator and real threat detection, alerting, support of threat mitigation and disaster management. In the technical architecture with an operations centre and the interfaces to legacy systems (e.g., SCADA), advanced technologies need to be integrated, including fast data aggregation and fusion, visualization of the situation, planning and decision support, and flexible networks for information sharing and coordination support, and the connection of local operations centres. This system will only be successful, if the technical solutions will be complemented by an effective and agreed organizational concept and the implementation of novel rules and regulations. And finally, the large spectrum of economically intangible factors will have significant influence on the quality and acceptance of the system. These factors of societal perception and appreciation, the existing and required legal framework, questions of information security and implications on privacy will be analyzed, assessed and regarded in the concept. The system will be tested, demonstrated and evaluated in realistic use cases. They will be developed with the community of stakeholders and cover the sectors energy, transportation and finance, and the ubiquitous sector of ICT.
Making efficient use of energy in buildings is a paramount challenge to conserve energy and reduce greenhouse effects. GreenerBuildings will investigate how buildings can dynamically adapt their operations according to actual use, aiming at substantial energy savings.People spend a great deal of time in buildings, may these be offices, hospitals or commercial buildings. While active indoor, people desire to have comforting lighting and microclimate conditions that adapt to their activity and wishes. With GreenerBuildings we propose to realise an integrated solution that addresses the challenge of energy-aware adaptation from basic (energy harvesting) sensors and actuators, up to the embedded software for coordinating thousands of smart objects with the goals of energy saving and user support. Our vision is that buildings can respond to their actual use and changes in their environment; interact with their occupants through novel ubiquitous sensing and occupant behaviour inference techniques and that can transparently adapt a building’s function and operation. The project embraces the following key principles in order to achieve its goals: living lab experimentation/validation, agile consortium, a spiral development model, and a user centric approach. In particular, the validation will consider test cases with at least 1.000 devices deployed in different living lab buildings.The specific composition of the Consortium, consisting of top-class universities and research centres (TUE, RUG, CINI, UOR, ITRI), of leader industrial partners specialized in building automation and lighting (PRE) and of SMEs specialised in energy harvesting sensors and actuators (ENO), and of thermodynamics applications (FSA), guarantees a widespread dissemination and exploitation of the project results, based on well funded scientific and technological innovation.
Embedded systems are specialised computers used in larger systems or machines to control equipments such as automobiles, home appliances, communication, control and office machines. Such pervasivity is particularly evident in immersive realities, i.e. scenarios in which invisible embedded systems need to continuosly interact with human users, in order to provide continuous sensed information and to react to service requests from the users themselves. The SM4ALL project will investigate an innovative middleware platform for inter-working of smart embedded services in immersive and person-centric environments, through the use of composability and semantic techniques for dynamic service reconfiguration. By leveraging on P2P technologies, the platform is inherently scalable and able to resist to devices’ churn and failures, while preserving the privacy of its human users as well as the security of the whole environment. This is applied to the challenging scenario of private houses and home-care assistance in presence of users with different abilities and needs (e.g. young able bodied, aged and disabled).
The specific composition of the Consortium, consisting of top-class universities and research centers (UOR, TUW, RUG, KTH and FOI), of user partners specialized in domotics and home-care assistance (FSL and THFL) and a SME specialized in specific brain-computer interfaces (GTEC), and of leader companies in the embedded sector (TID and ED) guarantees a widespread dissemination and exploitation of the project results, coupled with a privileged position inside ARTEMIS and ARTEMISIA (due to the presence of UOR, TUW and ED in such bodies).