Semantic technologies for Big Data: Volume, Velocity, Variety and Veracity

Session supported by LAMBDA project, https://project-lambda.org/

With characteristics like Volume, Velocity, Variety and Veracity, Big Data throws challenges to the existing IT establishments. Researchers and professionals face challenges when exploring Big Data sets and when extracting value and knowledge from different data sources. 

Although various modelling approaches and schemes have been proposed by the Semantic Community that could contribute to standardization of the Big Data pipelines and development of Big Data applications, specific approaches for Big Data applications are required.

In this special session we seek to raise discussion on:

• How could Data Semantics principles be applied in Big Data technologies e.g. representing the entire pipeline of technologies connected to achieve a specific solution and make this representation shareable and verifiable in different cases?
• How could various analytical techniques including data mining, visualization, statistical analysis, and machine learning be applied in Big Data scenarios?
• What are the challenges raised by Big Data computing systems?
• What are the architectures, strategies and practices that are currently followed in Big Data computing?

Additional topics relevant to this session include — but are not limited to — the following:

• Artificial Intelligence / machine learning algorithms
• Knowledge graphs and NoSQL databases
• Centralized, federated, and distributed SPARQL query processing
• SPARQL Analytical Queries
• Security and privacy in querying the Web of Data
• Interoperability and Integration in different domains
• Analytics Services in Big Data applications (Geospatial Data Management, Renewable Energies,  Energy Efficiency, Healthcare, eGovernment, Sustainable and Smart Cities, IoT applications, etc)
• Big Data Analytics, Industry Analytics

This session is intended to be a meeting point for the research communities of semantic data management, analytics and Big Data. For providing a forum for sharing novel ideas, SemTech session welcomes a broad spectrum of contributions, including: Full research papers, position papers, case studies or evaluations. Authors are invited to submit original, unpublished contributions related to the aforementioned topics.

Co-chairs:

• Lehmann, Jens (jens.lehmann@cs.uni-bonn.de). Smart Data Analytics Group, University of Bonn, Bonn, Germany Enterprise Information Systems, Fraunhofer IAIS, , Germany
• Sallinger, Emanuel (emanuel.sallinger@cs.ox.ac.uk). Department of Computer Science, University of Oxford, , UK
• Janev, Valentina (valentina.janev@institutepupin.com). University of Belgrade, Institute Mihailo Pupin, Belgrade, Serbia

Artificial Intelligence-enabled Enterprise Information Systems

Capacity and capability to adapt has become a key factor of competitiveness in the industry today. It can be considered on both micro and macro levels and it encompasses range of circumstances, from the optimal operational response to disturbances at the shop floor level, to business decisions related to changing market trends. To some extent, the capacity to adapt is related to access to relevant data, owned by the enterprise or from external providers, while capability corresponds to the enterprise ability and skills to effectively interpret, understand and process this data and make best informed decisions on the industry’s operations and market environment trends. The former (capacity to adapt) is/will be achieved in so-called sensing enterprise, the enterprise which continuously listens to its internal and external environment, by using the technologies such as sensors, embedded electronics and multi-agent systems. The paradigms of Cyber-Physical Systems and Internet of Things are considered as critical enablers for the sensing enterprise development strategies. The latter (capability to adapt) is related to making sense of all this data and it is expected to be achieved in so-called AI-enabled enterprise.

Enterprise Information Systems (EIS) aim to solve common problems, such as lack of process automation, flexibility, responsiveness, scalability, traceability and integration in as less as possible intrusive way. However, they often fail to address those issues consistently and the typical reason for that is complexity of the process of EIS development and/or implementation in which different and diverse stakeholders fail to effectively communicate around the business objectives and key factors for their achievement. Complexity is multiplied with the factor of long duration of the software development lifecycle in which those objectives could easily become legacy. Emerging solution to this problem is Model-Driven Engineering (MDE) which facilitates near real-time system customization and efficient response to a change. However, MDE relies on the human perceptions of the realities of the enterprise which are sometimes incomplete or inaccurate. AI-enabled enterprise would effectively address this challenge by embedding machine-learned understanding of the enterprise realities represented by raw data, into the respective models. Furthermore, AI-enabled enterprise is capable to implement those models and to make decisions based on those models in a real-time.

The objective of this Special Track is to provide evidences on the maturity of the technologies which facilitate AI-enabled EIS, where this maturity may be considered at the levels of development, implementation and integration with existing EIS. Technologies that are commonly known as parts of AI stack are Machine Learning (including Deep Learning), Natural Language Processing (NLP) and knowledge representation and reasoning. Different industries would be taken into account, such as manufacturing, logistics, banking and finance, agriculture, healthcare and others. In those domains, SI seeks for the solutions to the common problems, such as process automation, process mining and discovery, security, compliance, decision making support, image recognition and processing, marketing automation, negotiation automation, etc.

The Special Track seeks for original contributions in using so-called AI technologies, namely data science and predictive analytics, Machine Learning (including Deep Learning), Natural Language Processing (NLP), knowledge representation and reasoning and similar, in the following topics and fields:

• Decision making support
• Process automation
• Process discovery and mining
• Marketing automation
• Smart Customer Relationship Management
• Smart Human Resources Management
• Facilitating AI models development lifecycle
• Cloud-based AI platforms and services
• AI-enabled software agents
• Business models for AI-enabled enterprises
• AI-enabled blockchain
• AI-enabled Cyber-Physical Systems
• AI-enabled Internet of Things
• Legal issues of AI-enabled enterprises
• Security issues of AI-enabled enterprises
• Maturity models for AI-enabled enterprises
• Applied AI-enabled EIS solutions in different domains
• Other relevant topics and fields

Co-chairs:

• Zdravković, Milan (milan.zdravkovic@gmail.com). Faculty of Mechanical Engineering, University of Niš, Niš, Serbia
• Panetto, Hervé (herve.panetto@univ-lorraine.fr). Research Center for Automatic Control of Nancy (CRAN), Université de Lorraine, Nancy, France

ICT for Automotive

The automotive is experiencing a drastic increase in use of ICT and IoT in the past few decades with the purpose of increasing driver safety and improving driver experience. With the introduction of autonomous vehicles, the importance and presence of ICT in the automotive field has become inevitable.  It is no doubt that autonomous vehicles will reduce road accidents and contribute to increased road safety, however there are a lot of questions that remain unanswered on how to get to full automation.

Within this track we would like to address different ICT challenges in automotive sector by inviting speakers from academia and industry to elaborate on the topic and present different points of view.

This track welcomes research in this field, especially in the (but not limited to) following topics:

• In-vehicle HCI
• Driver evaluation and human factor
• Autonomous / automated driving
• Connected vehicles

This track is supported by:

• University of Ljubljana, Faculty of Electrical Engineering, Slovenia
• Nervtech simulation technologies: Nervtech is a leading company in the field of promoting and improving driving safety.

Co-chairs:

• Sodnik, Jaka (jaka.sodnik@fe.uni-lj.si). Faculty of Electrical Engineering, University of Ljubljana, Slovenia, Ljubljana, Slovenia
• Stojmenova, Kristina (kristina.stojmenova@fe.uni-lj.si). Faculty of Electrical Engineering, University of Ljubljana, Slovenia, Ljubljana, Slovenia
• Dusparić, Ivana (ivana.dusparic@scss.tcd.ie). Trinity College Dublin, Dublin, Ireland
• Miljković, Nadica (nadica.miljkovic@etf.rs). University of Belgrade, Belgrade, Serbia
• Tement, Sara (sara.tement@um.si). University of Maribor, Maribor, Slovenia Department of Psychology, Faculty of Arts, University of Maribor, Maribor, Slovenia

ICT for health,aging and well-being

One of the greatest social challenges today is addressing many different concerns and issues related to healthcare, aging and well-being. These challenges include, but are not restricted to, improving the understanding of causes and mechanisms connected to health; ability to monitor, prevent, detect, and treat disease; personalize health and care delivery. For addressing such challenges, a new approach is needed, which will transform the health and care delivery. This approach is proactive rather than reactive. Healthcare should evolve mechanisms for early risk detection, shifting from the acute treatment to long-term health monitoring. Instead of focusing on single disease treatment, healthcare systems should become capable of handling multiple chronic conditions and comorbidities at the same time. Care delivery should become pervasive, not exclusively institutional. Finally, generic treatment approach should be abandoned, and care should become more personalized.

Advanced ICT technologies will play a crucial role in this transformation. Health-related data will grow and will have accurate and useful digital representations. Predictive computing, used by the care providers and customers, will use health-related data to facilitate early risk detection and self-management of health and disease. Health systems will become interoperable. Robotic systems, driven by artificial intelligence will enable assisted living, in smart, age-friendly homes. Biofeedback applications in healthcare, sport, recreation, and rehabilitation will enable easier and faster way to achieving the desired results. They will assist individuals, healthcare personnel, and trainers in many ways; from influencing the physiological processes in human body, to motor learning in sports and rehabilitation.

With this session, we aim to uncover the current research in the abovementioned topics and topics closely related to them. All relevant contributions are strongly welcomed.

Co-chairs:

• Trajanović, Miroslav (traja@masfak.ni.ac.rs). Faculty of Mechanical Engineering, University of Niš, Niš, Serbia
• Kos, Anton (anton.kos@fe.uni-lj.si). Faculty of Electrical Engineering, University of Ljubljana, Slovenia, Ljubljana, Slovenia
• Canciglieri Jr., Osiris (osiris.canciglieri@pucpr.br). Pontifical Catholic University of Parana – PUCPR / PPGEPS, Curitiba, Brasil