A scientific paper entitled “Secure Edge Computing with Lightweight Control-Flow Property-based Attestation” has been co-authored by UBITECH and is presented at the 1st International Workshop on Cyber-Security Threats, Trust and Privacy Management in Software-defined and Virtualized Infrastructures (SecSoft), co-hosted at 5th IEEE International Conference on Network Softwarization (NetSoft 2019), between June 24-28, 2019 in Paris, France. In this paper, Sofianna Menesidou, Panagiotis Gouvas, and their co-authors propose a lightweight dynamic control-flow property-based attestation architecture (CFPA) that can be applied on both resource-constrained edge and cloud devices and services.
UBITECH is participating at the kick-off meeting, in Seville, Spain (June 4-5, 2019), of the SDN-microSENSE Innovation Action, officially started on May 1st, 2019. The project is funded by European Commission under Horizon 2020 Programme (Grant Agreement No. 833955) and spans on the period May 2019 – April 2022. The SDN-microSENSE project intends to provide a set of secure, privacy-enabled and resilient to cyberattacks tools, thus ensuring the normal operation of Electrical Power and Energy Systems (EPES) as well as the integrity and the confidentiality of communications.
In particular, adopting an SDN-based technology, SDN-microSENSE will develop a three-layer security architecture, by deploying and implementing risk assessment processes, self-healing capabilities, large-scale distributed detection and prevention mechanisms, as well as an overlay privacy protection framework. Firstly, the risk assessment framework will identify the risk level of each component of EPES, identifying the possible threats and vulnerabilities. Accordingly, in the context of self-healing, islanding schemes and energy management processes will be deployed, isolating the critical parts of the network in the case of emergency. Furthermore, collaborative intrusion detection tools will be capable of detecting and preventing possible threats and anomalies timely. Finally, the overlay privacy protection framework will focus on the privacy issues, including homomorphic encryption and anonymity processes.
A scientific paper entitled “Unveiling Trends and Predictions in Digital Factories” has been authored by UBITECH and is presented at the International Workshop on IoT Applications and Industry 4.0 (IoTI4 2019) that is part of the annual International Conference on Distributed Computing in Sensor Systems (DCOSS 2019), hosted between May 29-31, 2019 in Santorini, Greece. In this paper, Karagiorgou Sophia, Vafeiadis Georgios, Ntalaperas Dimitrios, Lykousas Nikolaos, Vergeti Danae and Alexandrou Dimitrios propose a failure prediction system for complex IT systems in the steel industry. The novelty of their work lies in the exploitation of Deep Learning techniques from streaming operational sensor data, enabling earlier failure predictions through a Neural Networks approach [in particular, through Long Short-Term Memory Networks (LSTM) that is a Recurrent Neural Network (RNN) architecture]. This predictive maintenance framework consists of three components: the Sense Module, the Detect Module and the Predict Module. To evaluate the proposed framework, real-life data are collected and analyzed based on daily operational and maintenance activities within the production line. They further demonstrate the framework’s potential by presenting some early results in modeling and predicting the complex and dynamic behavior in the manufacturing settings.
A scientific paper entitled “Personalised Monitoring and Recommendation Services for At-Risk Individuals Employing Machine-Learning and Decision Support” has been co-authored by UBITECH and is presented at the IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), the flagship conference of IEEE Engineering in Medicine and Biology Society (IEEE-EMBS) on the topics of informatics and computing in healthcare and life sciences, hosted between May 19-22, 2019 in Chicago, IL, USA. In this paper, Perakis Konstantinos, Pitsios Stamatis, Miltiadou Dimitrios, and their co-authors propose a technological solution, facilitating the provision of personalised health related services exploiting Big Data analytics, aiming to improve the everyday living and enhance the wellbeing of vulnerable individuals such as chronic disease patients, focusing mainly on patients suffering from COPD and/or CVD.
Sponsoring the 3-day technology conference DockerCon 2019(https://www.docker.com/dockercon/) that takes place from April 29 – May 2 at Moscone West in San Francisco, UBITECH has a dedicated exhibition booth at the Ecosystem Expo of the conference, for presenting and demonstrating the sophisticated MAESTRO platform that enables distributed applications composition and cloud services orchestration. The MAESTRO platform (themaestro.net) is an advanced developer framework for cloud orchestration and infrastructure automation, that gives you the power to design, deploy, and manage cloud-native containerized components in both public and private cloud environments. Built with IaaS (Infrastructure-as-a-Service) abstraction, the MAESTRO platform lets you create easy-to-manage, easy-to-scale workflows with Docker Compose applications. It comes with advanced off-the-shelf features to support extensive monitoring, security enforcement, elasticity management, and operational analytics.
Following a peer-review process, Sensors MDPI Journal has accepted to publish a scientific manuscript, co-authored by UBITECH’s Konstantinos Perakis and Stamatis Pitsios, entitled “IoT in Healthcare: Achieving Interoperability of High-Quality Data Acquired by IoT Medical Devices”. Konstantinos Perakis, Stamatis Pitsios and their co-editors from UPRC present a mechanism for effectively implementing a holistic approach for successfully achieving data interoperability between high-quality data that derive from heterogeneous devices. Through this mechanism, initially, the collection of the different devices’ datasets occurs, followed by the cleaning of them. In sequel, the produced cleaning results are used in order to capture the levels of the overall data quality of each dataset, in combination with the measurements of the availability of each device that produced each dataset, and the reliability of it. Consequently, only the high-quality data is kept and translated into a common format, being able to be used for further utilization. The proposed mechanism is evaluated through a specific scenario, producing reliable results, achieving data interoperability of 100% accuracy, and data quality of more than 90% accuracy.
UBITECH proudly supports (for the third year in a row) the Hellenic Cyber Security Team‘s efforts at the European Cyber Security Challenge (ECSC), organized by ENISA, between October 9 to October 11, in Bucharest, Romania. The 2019 ECSC challenge is aimed at identifying new talent – by having national teams compete in a Cyber Security Challenge. In particular, the top cyber talents from each country meet to network and collaborate and finally compete against each other to determine which country has the best cyber talents. To find out which country’s team is the best, contestants have to solve security related tasks from domains such as web security, mobile security, crypto puzzles, reverse engineering and forensics and collect points for solving them. The Greek team that will compete in the 2019 ECSC challenge grand finals is assembled after a qualification round, held on April 17-18, 2019, which determined the top 10 cyber security talents in Greece (aged between 14-25). The team will compete in the Challenge 2019 finals, in Bucharest, Romania.
A scientific paper entitled “Anonymizing Clinical and Genetic Data of Patients with Minimum Information Loss” has been authored by UBITECH and is presented at the 5th Collaborative European Research Conference (CERC 2019), hosted between March 29-30, 2019 in Darmstadt, Germany. In this paper, Dimitris Ntalaperas and Thanassis Bouras propose an approach for data anonymization to foster data exchange, which is based on disclosing a row based anonymized version of the original data set. The methodology is more versatile (than traditional data cubes -oriented approaches), while it also preserves the statistical characteristics of the original data set. We demonstrate this by considering an SVM predictor that tries to estimate the value of Breslow’s depth, based on the values of another clinical variable, namely Clark’s level, and the expression count of a skin cancer related gene (CDKN2A). The predictions are shown to have the same characteristics for both the original and the anonymized data sets.
UBITECH participated at the major H2020 project clustering event, organized by GHOST Project, on March 28, 2019 in Athens, wherein 25 EU funded projects participated and presented their objectives and results and share their implementation experiences. Very interesting round table sessions allowed the discussion between partners from different projects, and enacted future synergies and collaborations. Invited by the GHOST consortium, Konstantinos Theodosiou from UBITECH presented ANASTACIA H2020 project concept, objectives and achievements.
UBITECH showcases UPTIME results and their applicability in industrial use cases in the SMART INDUSTRIES track of the GLOBAL INDUSTRIE show, taken place in Lyon, France, from 5-8 March, 2019. GLOBAL INDUSTRIE brings together at EUREXPO, a) the entire industrial ecosystem, from start up to major customer, including subcontractors, equipment manufacturers and industrial solution providers, competitiveness clusters, research centers and incubators; b) the whole added value chain: R&D, design, production, maintenance, services, training; c) all the user industries: Transport and mobility, Energy and infrastructure, Food industry, Consumer goods, Chemicals, Cosmetics and Pharmaceuticals and Mechanical engineering. Welcomed by 96% of visitors and 88% of exhibitors at its launch, unparalleled in its extent, both in terms of its size and its scope, as well as its international reach, this event brings together four complementary shows, each of which is a leader in its field, whilst preserving their individual identities: MIDEST (international reference for subcontracting know-how), SMART Industries (for or the connected, collaborative and efficient smart factory), INDUSTRIE (for production technologies and equipment) and TOLEXPO (for working metal in sheets, coils, tubes and sections).