Vangelis Karkaletsis

National Center for Scientific Research Demokritos | ncsr · Insititute of Informatics and Telecommunications

Purpose: Disruptive technologies (AI, IoT, etc) unlock new frontiers of data-centric innovation. This increases the computational needs, pushing more and more companies into the HPC space. However, although HPC is a key tool for processing and analysing the constantly growing volume of data across numerous application areas many companies remain re...

This study is the first empirical strategic foresight research approach on the use of Generative Artificial Intelligence (Gen AI) in Greece, conducted by the National Centre for Social Research (EKKE) and the NCSR “Demokritos”, with the support of the Special Secretariat of Foresight. It systematically presents trends, opportunities, challenges, un...

The present study discusses the value of a direct interaction between Structural Health Monitoring applications utilizing active piezoelectric sensors and Machine Learning algorithms in order to develop well established Artificial Intelligence driven diagnostics’ tools for composite structures. More specifically, a high-fidelity Time Domain Spectra...

HPC is a key tool for processing and analyzing the constantly growing volume of data, from 64.2 zettabytes in 2020 to an expected 180 zettabytes in 2025 (1 zettabyte is equal to 1 trillion gigabytes). As such, HPC has a large number of application areas that range from climate change, monitoring and mitigating planning to the production of safer an...

This survey documents representation approaches for classification across different modalities, from purely content-based methods to techniques utilizing external sources of structured knowledge. We present studies related to three paradigms used for representation, namely a) low-level template-matching methods, b) aggregation-based approaches and...

The field of exploration of the values embraced by people and societies seems to be vast, as there are many different parameters of examination. The importance of values in the formation of human character and, by extension, in the formation of better societies is a key thematic area that to date, has attracted a lot of research interest across var...

Due to the wide range of timescales that are present in macromolecular systems, hierarchical multiscale strategies are necessary for their computational study. Coarse-graining (CG) allows to establish a link between different system resolutions and provides the backbone for the development of robust multiscale simulations and analyses. The CG mappi...

Coarse graining (CG) enables the investigation of molecular properties for larger systems and at longer timescales than the ones attainable at the atomistic resolution. Machine learning techniques have been recently proposed to learn CG particle interactions, i.e. develop CG force fields. Graph representations of molecules and supervised training o...

Coarse graining (CG) enables the investigation of molecular properties for larger systems and at longer timescales than the ones attainable at the atomistic resolution. Machine learning techniques have been recently proposed to learn CG particle interactions, i.e. develop CG force fields. Graph representations of molecules and supervised training o...

Due to the wide range of timescales that are present in macromolecular systems, hierarchical multiscale strategies are necessary for their computational study. Coarse-graining (CG) allows to establish a link between different system resolutions and provides the backbone for the development of robust multiscale simulations and analyses. The CG mappi...

HPC constitutes a strategic resource in the digital decade dominated by an increasing number of data-intensive applications and services and an ever increasing need to address our macroscopic and microscopic challenges for the benefit of citizens, businesses, researchers and public administrations around the world. Thus, increasing the usability of...

Unsupervised representation learning tends to produce generic and reusable latent representations. However, these representations can often miss high-level features or semantic information, since they only observe the implicit properties of the dataset. On the other hand, supervised learning frameworks learn task-oriented latent representations tha...

ExtremeEarth is a three-year H2020 ICT research and innovation project. Its main objective is to develop Artificial Intelligence and big data technologies that scale to the large volumes of big Copernicus data, information and knowledge, and apply these technologies in two of the European Space Agency (ESA) Thematic Exploitation Platforms (TEP): Fo...

In recent years, science has relied more than ever on large-scale data as well as on distributed computing and human resources. Scientists and research engineers in fields such as climate science and computational seismology, constantly strive to make good use of remote and largely heterogeneous computing resources (HPC, Cloud, institutional or loc...

Health care platforms rapidly shift toward the ICT-based solutions. In this context, a wide range of consumer electronics technologies come into play ranging from robotics, embedded systems, sensors, and communication infrastructures. Driven by such observations, the H2020 RADIO project set forward a service-oriented, easily expandable design parad...

Safe and efficient Human-Robot Collaboration (HRC) requires recognizing human collaborators intention. Hand pose kinematics early on an ongoing movement can provide information for predicting future human actions. Accurate state-of-the-art methods used for human hand pose estimation are either marker-based or make use of multiple cameras set around...

The recent breakthroughs in deep neural architectures across multiple machine learning fields have led to the widespread use of deep neural models. These learners are often applied as black-box models that ignore or insufficiently utilize a wealth of preexisting semantic information. In this study, we focus on the text classification task, investig...

This White Paper aims to set out the National AI Strategic Vision for Greece and to provide an initial plan of action on how to achieve this vision. It aims to accelerate the adoption and development of AI in both the private and public sectors in Greece and increase the relevant skills and the research and development (R&D) base through the provis...

This chapter describes the evolution of a real, multi-document, multilingual news summarization methodology and application, named NewSum, the research problems behind it, as well as the steps taken to solve these problems. The system uses the representation of n-gram graphs to perform sentence selection and redundancy removal towards summary gener...

The DARE platform has been designed to help research developers deliver user-facing applications and solutions over diverse underlying e-infrastructures, data and computational contexts. The platform is Cloud-ready, and relies on the exposure of APIs, which are suitable for raising the abstraction level and hiding complexity. At its core, the platf...

In this paper we introduce evidence transfer for clustering, a deep learning method that can incrementally manipulate the latent representations of an autoencoder, according to external categorical evidence, in order to improve a clustering outcome. It is deployed on a baseline solution to reduce the cross entropy between the external evidence and...

Evidence transfer for clustering is a deep learning method that manipulates the latent representations of an autoencoder according to external categorical evidence with the effect of improving a clustering outcome. Evidence transfer's application on clustering is designed to be robust when introduced with a low quality of evidence, while increasing...

Deep learning models, while effective and versatile, are becoming increasingly complex, often including multiple overlapping networks of arbitrary depths, multiple objectives and non-intuitive training methodologies. This makes it increasingly difficult for researchers and practitioners to design, train and understand them. In this paper we present...

Demographic and epidemiologic transitions have brought a new health care paradigm with the presence of both growing elderly population and chronic diseases. Life expectancy is increasing as well as the need for long-term care. Institutional care for the aged population faces economical struggles with low staffing ratios and consequent quality probl...

As smart interconnected sensing devices are becoming increasingly ubiquitous, more applications are becoming possible by re-arranging and re-connecting sensing and sensor signal analysis in different pipelines. Naturally, this is best facilitated by extremely thin services that expose minimal functionality and are extremely flexible regarding the w...

In this article, we present a taxonomy in Robot-Assisted Training; a growing body of research in Human–Robot Interaction which focuses on how robotic agents and devices can be used to enhance user’s performance during a cognitive or physical training task. Robot-Assisted Training systems have been successfully deployed to enhance the effects of a t...

The DARE e-science platform (http://project-dare.eu) is designed for efficient and traceable development of complex experiments and domain-specific services on the Cloud. DARE will be validated via two scientific pilots: Working with the ENES community for climate, the first will enhance part of the data-access and pre-processing procedures of the...

End Users of Climate data have nowadays to struggle with accessing the data they need for their research because of the rapid increase in data volumes. The whole climate data archive is expected to reach a volume of 30 Pb in 2018 and up to 2000 Pb in 2022 (estimated). On-demand data processing solutions as close as possible to the data storage are...

In this paper we introduce evidence transfer for clustering, a deep learning method that can incrementally manipulate the latent representations of an autoencoder, according to external categorical evidence, in order to improve a clustering outcome. It is deployed on a baseline solution to reduce the cross entropy between the external evidence and...

In this paper, we present a taxonomy in Robot-Assisted Training; a growing body of research in Human-Robot Interaction which focuses on how robotic agents and devices can be used to enhance user's performance during a cognitive or physical training task. The proposed taxonomy includes a set of parameters that characterize such systems, in order to...

Demographic and epidemiologic transitions have brought a new health care paradigm where life expectancy is increasing as well as the need for long-term care. To meet the resulting challenge, healthcare systems need to take full advantage of new opportunities offered by technical advancements in ICT. The RADIO project explores a novel approach to us...

Deep learning models, while effective and versatile, are becoming increasingly complex, often including multiple overlapping networks of arbitrary depths, multiple objectives and non-intuitive training methodologies. This makes it increasingly difficult for researchers and practitioners to design, train and understand them. In this paper we present...

Emergency response applications for nuclear or radiological events can be significantly improved via deep feature learning due to the hidden complexity of the data and models involved. In this paper we present a novel methodology for rapid source estimation during radiological releases based on deep feature extraction and weather clustering. Atmosp...

Speech music discrimination is a traditional task in audio analytics, useful for a wide range of applications (automatic speech recognition, radio broadcast monitoring, etc), that focuses on segmenting audio streams and classifying each segment as either speech or music. In this paper, we exploit the capabilities of convolu-tional neural networks (...

Emergencies that involve the release of hazardous substances into the atmosphere affects life and nature for several years. The timely and reliable estimation of the expected consequences on people and the environment facilitates informed decision making and timely response. Here, we demonstrate a tool that leverages Big Data and Semantic Web techn...

Dataset description vocabularies focus on provenance, ver-sioning, licensing, and similar metadata. VoID is a notable exception, providing some expressivity for describing subsets and their contents and can, to some extent, be used for discovering relevant resources and for optimizing querying. In this paper we describe the Sevod vocabulary, an ext...

Emergency response applications for nuclear or radiological events can be significantly improved via deep feature learning due to the hidden complexity of the data and models involved. In this paper we present a novel methodology for rapid source estimation during radiological releases based on deep feature extraction and weather clustering. Atmosp...

We present a method that recognizes exercising activities performed by a single human in the context of a real home environment. Towards this end, we combine sensorial information stemming from a smartphone accelerometer, with visual information from a simple web camera. Low-level features inspired from the audio analysis domain are used to represe...

The management and analysis of large-scale datasets – described with the term Big Data – involves the three classic dimensions volume, velocity and variety. While the former two are well supported by a plethora of software components, the variety dimension is still rather neglected. We present the BDE platform – an easy-to-deploy, easy-to-use and a...

This paper proposes a deep learning classification method for frame-wise recognition of human activities , using raw color (RGB) information. In particular, we present a Convolutional Neural Network (CNN) classification approach for recognising three basic motion activity classes, that cover the vast majority of human activities in the context of a...

In this paper, we present an interactive learning and adaptation framework that facilitates the adaptation of an interactive agent to a new user. We argue that Interactive Reinforcement Learning methods can be utilized and integrated to the adaptation mechanism, enabling the agent to refine its learned policy in order to cope with different users....

The rapidly increasing amount and variety of data coming from satellites and other sources is raising new issues such as the management and exploitation of extremely large and complex datasets (Big Data); the main challenge in the Space and Security domain is to improve the capacity to extract in a timely manner operational (i.e. useful and clear)...

As smart interconnected sensing devices are becoming increasingly ubiquitous, more applications are becoming possible by re-arranging and re-connecting sensing and sensor signal analysis in different pipelines. Naturally, this is best facilitated by extremely thin services that expose minimal functionality and are extremely flexible regarding the w...

The insights gained by the large-scale analysis of health-related data can have an enormous impact in public health and medical research, but access to such personal and sensitive data poses serious privacy implications for the data provider and a heavy data security and administrative burden on the data consumer. In this paper we present an archit...

In this paper, we present an interactive learning and adaptation framework. The framework combines Interactive Reinforcement Learning methods to effectively adapt and refine a learned policy to cope with new users. We argue that implicit feedback provided by the primary user and guidance from a secondary user can be integrated to the adaptation mec...

Demographic and epidemiologic transitions have brought forward a new health care paradigm with the presence of both growing elderly population and chronic diseases. Recent technological advances can support elderly people in their domestic environment assuming that several ethical and clinical requirements can be met. This paper presents an archite...

Argument extraction is the task of identifying arguments, along with their components in text. Arguments can be usually decomposed into a claim and one or more premises justifying it. Among the novel aspects of this work is the thematic domain itself which relates to Social Media, in contrast to traditional research in the area, which concentrates...

In this paper, we present a framework for physical rehabilitation , that uses a combination of video gaming and robotic technology to allow the monitoring and progress tracking of a person during physical therapy. The system, called MAGNI, uses the advanced control capabilities of the Bar-rett WAM Arm robot and a custom-made video game. The MAGNI s...

Integrating robotic platforms in smart home environments can improve the monitoring quality of daily activities. In this study, we explore a scenario where a robot provides a service to the users, which in our case is delivering a cup of coffee. The users place their order via an application, which at the same time captures a short video from their...

In this paper, we present an Adaptive Multimodal Dialogue System for Depressive and Anxiety Disorders Screening (DADS). The system interacts with the user through verbal and non-verbal communication to elicit the information needed to make referrals and recommendations for depressive and anxiety disorders while encouraging the user and keeping them...

A great deal of recent research has focused on social and assistive robots that can achieve a more natural and realistic interaction between the agent and its environment. Following this direction, this paper aims to establish a computational framework that can associate objects with their uses and their basic characteristics in an automated manner...

Demographic and epidemiologic transitions in Europe have brought a new health care paradigm where life expectancy is increasing as well as the need for long-term care. To meet the resulting challenge, European healthcare systems need to take full advantage of new opportunities offered by technical advancements in ICT. The RADIO project explores a n...

Dataset description vocabularies focus on provenance, versioning, licensing, and similar metadata. VoID is a notable exception, providing some expressivity for describing subsets and their contents and can, to some extent, be used for discovering relevant resources and for optimizing querying. In this poster we describe an extension of VoID that pr...

Reducing the possibility of ship accidents in the Aegean Sea is important to all economic, environmental, and cultural sectors of Greece. Despite the increased traffic and the related obvious risk, there are currently no national-level monitoring policies in Greece. To this end, we develop the AMINESS platform that will integrate information from m...

The NOMAD project (Policy Formulation and Validation through non Moderated Crowd-sourcing) is a project that supports policy making, by providing rich, actionable information related to how citizens perceive different policies. NOMAD automatically analyzes citizen contributions to the informal web (e.g. forums, social networks, blogs, newsgroups an...

Purpose – The purpose of this study is to develop a novel approach to e-participation, which is based on “passive crowdsourcing” by government agencies, exploiting the extensive political content continuously created in numerous Web 2.0 social media (e.g. political blogs and microblogs, news sharing sites and online forums) by citizens without gove...

Modern assistive environments have the ability to collect data from various distributed sources and the need to react swiftly to changes. As information flows, in the form of simple, source events, it becomes more and more difficult to quickly analyze the collected data in an automated way and transform them into operational knowledge. Event Recogn...

This chapter describes a real, multi-document, multilingual news summarization application, named NewSum, the research problems behind it, as well as the novel methods proposed and tested to solve these problems. The system uses the representation of n-gram graphs in a novel manner to perform sentence selection and redundancy removal for the summar...