Porto, Portugal
Porto, Portugal

The Institute for Systems and Computer Engineering of Porto is a research & development institute located on the campus of the Faculty of Engineering of the University of Porto . INESC Porto is a private non-profit association, recognised as a Public Interest Institution and has been an Associate Laboratory since 2002. In 2011, the institute proposed a new broader structure for the Associate Laboratory, which was officially recognised by the Ministry of Science as INESC TEC .The purpose of INESC TEC is to act as an interface between the academic world, the world of industry and services and the public administration in Information Technologies, Telecommunications and Electronics . INESC TEC invests in Scientific Research and Technological Development, as well as in Advanced Training and Consulting, Technology Transfer and supports the Establishment of new Technology-based Companies.Present in 6 sites in the cities of Porto, Braga and Vila Real, INESC TEC incorporates 12 R&D Centres and one Associate Unit with complementary competences, always looking to the international market. INESC TEC brings together more than 800 researchers, of which around 300 have PhDs . Wikipedia.


Time filter

Source Type

Grant
Agency: European Commission | Branch: FP7 | Program: CP | Phase: ICT-2013.9.5 | Award Amount: 2.29M | Year: 2014

The need for machine learning (ML) and data mining (DM) is ever growing due to the increased pervasiveness of data analysis tasks in almost every area of life, including business, science and technology. Not only is the pervasiveness of data analysis tasks increasing, but so is their complexity. We are increasingly often facing predictive modelling tasks involving one or several of the following complexity aspects: (a)structured data as input or output of the prediction process, (b)very large/massive datasets, with many examples and/or many input/output dimensions, where data may be streaming at high rates, (c)incompletely/partially labelled data, and (d)data placed in a spatio-temporal or network context. Each of these is a major challenge to current ML/DM approaches and is the central topic of active research in areas such as structured-output prediction, mining data streams, semi-supervised learning, and mining network data. The simultaneous presence of several of them is a much harder, currently insurmountable, challenge and severely limits the applicability of ML/DM approaches.The proposed project will develop predictive modelling methods capable of simultaneously addressing several (ultimately all) of the above complexity aspects. In the most complex case, the methods would be able to address massive sets of network data incompletely labelled with structured outputs. We will develop the foundations (basic concepts and notions) for and the methodology (design and implementation of algorithms) of such approaches. We will demonstrate the potential and utility of the methods on showcase problems from a diverse set of application areas (molecular biology, sensor networks, mutimedia, and social networks). Some of these applications, such as relating the composition of microbiota to human health and the design of social media aggregators, have the potential of transformational impact on important aspects of society, such as personalized medicine and social media.


Grant
Agency: European Commission | Branch: FP7 | Program: CP | Phase: ICT-2013.2.2 | Award Amount: 6.28M | Year: 2013

Part handling during the assembly stages in the automotive industry is the only task with automation levels below 30% due to the variability of the production and to the diversity of suppliers and parts. The full automation of such task will not only have a huge impact in the automotive industry but will also act as a cornerstone in the development of advanced mobile robotic manipulators capable of dealing with unstructured environments, thus opening new possibilities in general for manufacturing SMEs. The STAMINA project will use a holistic approach by partnering with experts in each necessary key fields, thus building on previous R&D to develop a fleet of autonomous and mobile industrial robots with different sensory, planning and physical capabilities for jointly solving three logistic and handling tasks: De-palletizing, Bin-Picking and Kitting. The robot and orchestration systems will be developed in a lean manner using an iterative series of development and validation testes that will not only assess the performance and usability of the system but also allow goal-driven research. STAMINA will give special attention to the system integration promoting and assessing the development of a sustainable and scalable robotic system to ensure a clear path for the future exploitation of the developed technologies. In addition to the technological outcome, STAMINA will allow to give an impression on how a sharing of work and workspace between humans and robots could look in the future.


Grant
Agency: European Commission | Branch: FP7 | Program: CP | Phase: ICT-2013.1.2 | Award Amount: 6.53M | Year: 2013

Cloud data management, Big Data and the Internet of Things raise specific challenges with respect to scalable data management, both in real-time and offline. Big Data analytics puts the emphasis on large queries over big cloud data stores. The emerging Internet of Things applications also raise specific challenges with respect to real-time data management. Developing cloud applications at large scale is also complex due to the lack of coherence support.\n\nIn this landscape there is an increasing demand for efficiency and scalability that has resulted in the implementation and use of a wide diversity of different cloud data stores each one specialized and optimal for specific processing, thus leading to a no one size fits all situation. This trend has resulted in a large proliferation of APIs, a lack of a common programming framework and a lack of coherence across different cloud data managers for the corresponding different technologies (traditional environments provided full coherence that has been totally lost in the cloud landscape). CoherentPaaS addresses all these issues.\n\nCoherentPaaS will provide a rich PaaS with different one size data stores optimized for particular tasks, data, and workloads. CoherentPaaS will integrate NoSQL, SQL data stores, and complex event processing data management systems with holistic coherence and that will be accessed by means of a common query language. CoherentPaaS will thus enable the development of new cloud, BigData and IoT applications that exploit the performance and scalability of new cloud data management technologies, while hiding the complexity of the underlying technology under a unified query language and holistic coherence across data stores that will simplify application development.\n\nCoherentPaaS outcomes will enable application developers to program with a unified framework that will attain simplicity thanks to the common query language and holistic coherence, scalability guaranteed by each cloud data management technology, and efficiency by enabling to use different cloud data managers specialized for the required tasks.


Grant
Agency: European Commission | Branch: FP7 | Program: CP | Phase: ICT-2013.1.5 | Award Amount: 10.47M | Year: 2013

The traditional computing paradigm is experiencing a fundamental shift: organizations no longer completely control their own data, but instead hand it to external untrusted parties - cloud service providers, for processing and storage. There currently exist no satisfactory approach to protect data during computation from cloud providers and from other users of the cloud.\n\nPRACTICE has assembled the key experts throughout Europe and will provide privacy and confidentiality for computations in the cloud. PRACTICE will create a secure cloud framework that allows the realization of advanced and practical cryptographic technologies providing sophisticated security and privacy guarantees for all parties in cloud-computing scenarios. With PRACTICE users no longer need to trust their cloud providers for data confidentiality and integrity: Due to its computation on encrypted data, even insiders can no longer disclose secrets or disrupt the service. This opens new markets, increases their market share, and may allow conquering foreign markets where reach has been limited due to confidentiality and privacy concerns. PRACTICE enables European customers to safe cost by globally outsourcing to the cheapest providers while still maintaining guaranteed security and legal compliance.\n\nPRACTICE will deliver a Secure Platform for Enterprise Applications and Services (SPEAR) providing application servers and automatic tools enabling privacy-sensitive applications on the cloud. SPEAR protects user data from cloud providers and other users, supporting cloud-aided secure computations by mutually distrusting parties and will support the entire software product lifecycle. One goal of SPEAR is to support users in selecting the right approach and mechanisms to address their specific security needs. Our flexible architecture and tools that allow seamless migration from execution on unchanged clouds today towards new platforms while gradually adding levels of protection.\n\nPRACTICE is strongly industry-driven and will demonstrate its results on two end-user defined use cases in statistics and collaborative supply chain management. PRACTICE is based on real-life use cases underpinning the business interest of the partners. Our focus is on near-term and large-scale commercial exploitation of cutting-edge technology where project results are quickly transferred into novel products. PRACTICE is the first project to mitigate insider threats and data leakage for computations in the cloud while maintaining economies of scale. This goes beyond current approaches that can only protect data at rest within storage clouds once insiders may misbehave. Moreover, it will investigate economical and legal frameworks, quantify the economic aspects and return on security investment for SMC deployment as well as evaluate its legal aspects regarding private data processing and outsourcing.


Grant
Agency: European Commission | Branch: FP7 | Program: CP-CSA | Phase: ENERGY.2013.10.1.8 | Award Amount: 13.13M | Year: 2013

The ELECTRA Integrated Research Programme on Smart Grids (ELECTRA) brings together the partners of the EERA Joint Programme on Smart Grids (JP SG) to reinforce and accelerate Europes medium to long term research cooperation in this area and to drive a closer integration of the research programmes of the participating organisations and of the related national programmes. ELECTRAs joint research activity and collaborative support actions build on an established track record of collaboration and engagement. Together, the JP SG and ELECTRA will establish significant coherence across national research efforts critical to the stable operation of the EU power system of 2020\. The EU energy strategy sets ambitious goals for the energy systems of the future that foresees a substantial increase in the share of renewable electricity production. The whole-sale deployment of RES connected to the network at all voltage levels will require radically new approaches for real time control that can accommodate the coordinated operation of millions of devices, of various technologies, at many different scales and voltage levels, dispersed across EU grid. ELECTRA addresses this challenge, and will establish and validate proofs of concept that utilise flexibility from across traditional boundaries in a holistic fashion. In addition to the joint R&D activities, coordination work packages in ELECTRA build on existing efforts established through EERA and will significantly escalate these through the coordination and collaboration amongst EU leading research infrastructures, researcher exchange across EU and internationally, and actions on international cooperation. The support received at proposal stage from 16 national funding agencies, ENTSOE, EDSO4SG, ETP SG, as well as from a number of international organisations will be developed to leverage the research effort in ELECTRA and to strengthen its exploitation potential.


Grant
Agency: European Commission | Branch: FP7 | Program: CP-FP | Phase: HEALTH.2013.3.1-1 | Award Amount: 7.70M | Year: 2014

In 2010, 30 million Europeans were affected by depression and their number is still growing. Half of Europeans in need of mental care for depression do not have access to care services, do not always receive evidence-based treatments, are confronted with long waiting lists or high care expenditures. Internet-based treatment has the potential to addresses the drawbacks of standard care and keep depression treatment of high quality and affordable. E-COMPARED will conduct comparative effectiveness research in routine specialized mental care settings on the (cost-) effectiveness of internet-based treatment for depression in comparison with standard care. Health care systems, and -policies, existing ICT infrastructures and their uptake will be taken into account. E-COMPARED aims to 1)Evaluate EU mental health policies/guidelines for standard and internet-based care for depression in specialized care settings in countries with different health care systems and access levels of standard and internet-based care; 2)Compare clinical efficacy and cost-effectiveness of internet-based treatment and treatment as usual within controlled research settings, 3)Carry out pragmatic randomized controlled trials to study how internet-based depression treatment can be effectively implemented within routine specialized care settings, 4)Predict which patient groups could benefit from internet-based treatment vs. standard treatment by modeling patient characteristics; 5)Develop evidence based recommendations on how internet-based depression treatment can be cost-effectively integrated into routine specialized care systems for depression in EU mental health care systems, and develop a business case to ensure structural implementation of these services. E-COMPARED is multidisciplinary (psychology, HTA, ICT, care) and its members have a front runners position in internet-based treatment for common mental health disorders, e.g. through participating in FP7 projects (ICT4Depression, ROAMER).


Grant
Agency: European Commission | Branch: FP7 | Program: CP | Phase: ENERGY.2013.7.1.1 | Award Amount: 7.84M | Year: 2013

With the growing relevance of distributed renewable energy sources (DRES) in the generation mix and the increasingly pro-active demand for electricity, power systems and their mode of operation need to evolve. evolvDSO will define future roles of distribution system operators (DSOs) on the basis of scenarios which will be driven by different DRES penetration levels, various degrees of technological progress, and differing customer acceptance patterns. The evolvDSO consortium addresses the main research and technology gaps that need to be solved for DSOs to efficiently fulfil their emerging and future roles in the European electricity system. The new tools and methods will encompass a wide array of DSO activities related to planning, operational scheduling, real-time operations and maintenance. Selected methods and tools developed during the project will be validated in computer simulations and real-life testbeds to maximise their deployability, scalability and replicability. Beyond this holistic, top-down approach, evolvDSO is unique in that it brings together the key actors of the electricity value chain that are at the forefront of smart grid development, and with a clear common view on what is needed for further DRES integration in Europe. The consortium consists of 16 partners including DSOs, TSOs, renowned research institutions and new market players that provide unique expertise to achieve the stated objectives. evolvDSO will contribute to the transition to a more sustainable European energy system by maintaining and increasing the security and reliability of distribution grids facilitating the increased feed-in of DRES. The results of evolvDSO will drive the implementation of the EEGI roadmap and ultimately provide a significant impetus for reaching EU climate targets. The project will establish strong links to the realization of smart cities, thus contributing to the EC initiative Smart Cities and Communities


Grant
Agency: European Commission | Branch: FP7 | Program: CP-IP | Phase: SEC-2012.3.5-1 | Award Amount: 14.44M | Year: 2014

The SUNNY project aims to contribute to EUROSUR by defining a new tool for collecting real-time information in operational scenarios. SUNNY represents a step beyond existing research projects due to the following main features: A two-tier intelligent heterogeneous UAV sensor network will be considered in order to provide both large field and focused surveillance capabilities, where the first-tier sensors, carried by medium altitude, long-endurance autonomous UAVs, are used to patrol large border areas to detect suspicious targets and provide global situation awareness. Fed with the information collected by the first-tier sensors, the second-tier sensors will be deployed to provide more focused surveillance capability by tracking the targets and collecting further evidence for more accurate target recognition and threat evaluation. Novel algorithms will be developed to analyse the data collected by the sensors for robust and accurate target identification and event detection; Novel sensors and on-board processing generation, integrated on UAV system, will be focus on low weight, low cost, high resolution that can operate under variable conditions such as darkness, snow, and rain. In particular, SUNNY will develop sensors that generate both RGB image, Near Infrared (NIR) image and hyperspectral image and that use radar information to detect, discriminate and track objects of interest inside complex environment with focus on the sea borders. Alloying to couple sensor processing and preliminary detection results (on-board) with local UAV control, leading to innovative active sensing techniques, replacing low level sensor data communication by a higher abstraction level of information communication. The exploitation and adaptation of emerging standard wireless technologies and architectures as IEEE 802.11a/g/n, IEEE 802.11p, DVB-T2, Mobile WiMAX, LTE, and Wi-Fi@700MHz will be considered due to their low cost and advantageous features.


Grant
Agency: European Commission | Branch: FP7 | Program: CP-TP | Phase: NMP.2013.3.0-2 | Award Amount: 4.05M | Year: 2014

The forest-based value chains are one of the dominant contributors to the GDP in the rural regions of Europe. Besides the traditional value chains, novel ones are in the horizon, with significant impacts on the requirements for the raw material supply chains. A major roadblock for improving forest-based value chains is the lack of integrated control and planning mechanism. FOCUS will demonstrate how innovative sensor technologies and control methods can solve this problem, with case studies in Finland, Belgium, Switzerland,Germany,Austria, Portugal covering the main forest-based production processes in Europe biomass for bioenergy, timber and pulp wood, and cork transformation. The goal of FOCUS is to improve the individual value chain processes, and to remove the barriers for integrated planning and control for the whole value chain. The project brings together leading SMEs and organisations in the fields of environment and machine sensors, production machinery and control automation software development. The expertise is needed to address the key challenges: novel sensor development for environment, raw material and production machinery monitoring; new process specific control processes; plug-and-play composition of value chain wide control processes. The productivity and sustainability of the value chains will be enhanced by enabling the best use of the production resources, and by reducing harmful impacts like soil compaction by forest machines, and carbon footprint of the operations. Product marketability will be increased by traceability of raw material origin, and by controlling the quality of the raw material during the production process. The open source FOCUS platform will foster new business models by enabling several SMEs to jointly offer solutions. The project will be a paradigm for support of efficient and sustainable exploitation of existing and new forest-based value chains alike, and will enhance the economic development of European rural areas.


Grant
Agency: European Commission | Branch: FP7 | Program: CP | Phase: ICT-2013.4.2 | Award Amount: 6.15M | Year: 2014

LeanBigData aims at addressing three open challenges in big data analytics: 1) The cost, in terms of resources, of scaling big data analytics for streaming and static data sources; 2) The lack of integration of existing big data management technologies and their high response time; 3) The insufficient end-user support leading to extremely lengthy big data analysis cycles. LeanBigData will address these challenges by:Architecting and developing three resource-efficient Big Data management systems typically involved in Big Data processing: a novel transactional NoSQL key-value data store, a distributed complex event processing (CEP) system, and a distributed SQL query engine. We will achieve at least one order of magnitude in efficiency by removing overheads at all levels of the big-data analytics stack and we will take into account technology trends in multicore technologies and non-volatile memories. Providing an integrated big data platform with these three main technologies used for big data, NoSQL, SQL, and Streaming/CEP that will improve response time for unified analytics over multiple sources and large amounts of data avoiding the inefficiencies and delays introduced by existing extract-transfer-load approaches. To achieve this we will use fine-grain intra-query and intra-operator parallelism that will lead to sub-second response times.Supporting an end-to-end big data analytics solution removing the four main sources of delays in data analysis cycles by using: 1) automated discovery of anomalies and root cause analysis; 2) incremental visualization of long analytical queries; 3) drag-and-drop declarative composition of visualizations; and 4) efficient manipulation of visualizations through hand gestures over 3D/holographic views.Finally, LeanBigData will demonstrate these results in a cluster with 1,000 cores in four real industrial use cases with real data, paving the way for deployment in the context of realistic business processes.

Loading INESC Porto collaborators
Loading INESC Porto collaborators