Grammatikis, Panagiotis Radoglou; Sarigiannidis, Panagiotis; Iturbe, Eider; Rios, Erkuden; Martinez, Saturnino; Sarigiannidis, Antonios; Efstathopoulos, Georgios; Spyridis, Yannis; Sesis, Achilleas; Vakakis, Nikolaos; Tzovaras, Dimitrios; Kafetzakis, Emmanouil; Giannoulakis, Ioannis; Tzifas, Michalis; Giannakoulias, Alkiviadis; Angelopoulos, Michail; Ramos, Francisco
In: Computer Networks, 2021.
The technological leap of smart technologies has brought the conventional electrical grid in a new digital era called Smart Grid (SG), providing multiple benefits, such as two-way communication, pervasive control and self-healing. However, this new reality generates significant cybersecurity risks due to the heterogeneous and insecure nature of SG. In particular, SG relies on legacy communication protocols that have not been implemented having cybersecurity in mind. Moreover, the advent of the Internet of Things (IoT) creates severe cybersecurity challenges. The Security Information and Event Management (SIEM) systems constitute an emerging technology in the cybersecurity area, having the capability to detect, normalise and correlate a vast amount of security events. They can orchestrate the entire security of a smart ecosystem, such as SG. Nevertheless, the current SIEM systems do not take into account the unique SG peculiarities and characteristics like the legacy communication protocols. In this paper, we present the Secure and PrivatE smArt gRid (SPEAR) SIEM, which focuses on SG. The main contribution of our work is the design and implementation of a SIEM system capable of detecting, normalising and correlating cyberattacks and anomalies against a plethora of SG application-layer protocols. It is noteworthy that the detection performance of the SPEAR SIEM is demonstrated with real data originating from four real SG use case (a) hydropower plant, (b) substation, (c) power plant and (d) smart home.
Grammatikis, Panagiotis Radoglou; Sarigiannidis, Panagiotis; Efstathopoulos, George; Lagkas, Thomas; Fragulis, George; Sarigiannidis, Antonios
In: IEEE International Conference on Communications, 2021.
(Tags: )| | |
The rapid evolution of the Internet of Medical Things (IoMT) introduces the healthcare ecosystem into a new reality consisting of smart medical devices and applications that provide multiple benefits, such as remote medical assistance, timely administration of medication, real-time monitoring, preventive care and health education. However, despite the valuable advantages, this new reality increases the cybersecurity and privacy concerns since vulnerable IoMT devices can access and handle autonomously patients’ data. Furthermore, the continuous evolution of cyberattacks, malware and zero-day vulnerabilities require the development of the appropriate countermeasures. In the light of the aforementioned remarks, in this paper, we present an Intrusion Detection and Prevention System (IDPS), which can protect the healthcare communications that rely on the Hypertext Transfer Protocol (HTTP) and the Modbus/Transmission Control Protocol (TCP). HTTP is commonly adopted by conventional ICT healthcare-related services, such as web-based Electronic Health Record (EHR) applications, while Modbus/TCP is an industrial protocol adopted by IoMT. Although the Machine Learning (ML) and Deep Learning (DL) methods have already demonstrated their efficacy in detecting intrusions, the rarely available intrusion detection datasets (especially in the healthcare sector) complicate their global application. The main contribution of this work lies in the fact that an active learning approach is modelled and adopted in order to re-train dynamically the supervised classifiers behind the proposed IDPS. The evaluation analysis demonstrates the efficiency of this work against HTTP and Modbus/TCP cyberattacks, showing also how the entire accuracy is increased in the various re-training phases.
Khadka, A; Karipidis, Paris; Lytos, Anastasios; Efstathopoulos, G
A benchmarking framework for cyber-attacks on autonomous vehicles (Journal Article)
In: Transportation Research Procedia, 52 , pp. 323-330, 2021.
In this paper, a novel framework for a benchmark system for autonomous vehicles focusing on their security and reliability is proposed. Computer vision and networking technologies are improving offering solutions towards automation in connected autonomous vehicles. These systems are using sensor technologies, including vision and communication, providing information and measurements for the environment and other connected vehicles. As a result, unlike conventional vehicles, autonomous vehicles have to communicate with other vehicles as well as other external network infrastructure. However, such requirements make autonomous vulnerable to the attack. This may also motivate diverse types of cyber threats and attacks like traffic signs modification, GPS spoofing, and Vehicular Adhoc network distributed denial of service. Hence, this paper explores various aspects of security issues, vulnerabilities, exploitation methods and the adverse effect of them on connected autonomous vehicles and propose a novel benchmark framework focusing on physical and communication-based attack to evaluate and assets the state-of-the-art technologies that are currently use during cyber-attack.
Argyropoulos, Nikolaos; Khodashenas, Pouria Sayyad; Mavropoulos, Orestis; Karapistoli, Eirini; Lytos, Anastasios; Karypidis, Paris Alexandros; Hofmann, Klaus-Peter
In: Transportation Research Procedia, 52 , pp. 307-314, 2021, ISSN: 2352-1465, (23rd EURO Working Group on Transportation Meeting, EWGT 2020, 16-18 September 2020, Paphos, Cyprus).
The proliferation of next generation mobility, promotes the use of autonomous cars, connected vehicles and electromobility. It creates novel attack surfaces for high impact cyberattacks affecting the society. Addressing the cybersecurity challenges introduced by modern vehicles requires a proactive and multi-faceted approach combining techniques originating from various domains of ICT. Emerging technologies such as 5G, LiDAR, novel in-vehicle and roadside sensors and smart charging, used in modern cars, introduce new challenges and potential security gaps in the next generation mobility ecosystem. Thus, it is critical that the domain’s cybersecurity must be approached in a structured manner from a multi-domain and multi-technology perspective. The CARAMEL H2020 project aims to address the cybersecurity challenges on the pillars upon which the next generation mobility is constructed (i.e., autonomous mobility, connected mobility, electromobility). To achieve that, advanced Artificial Intelligence (AI) and Machine Learning (ML) techniques will be utilized for the identification of anomalies and the classification of incoming signals indicating a cyber-attack or a cybersecurity risk. Apart from risk detection, methods for the mitigation of the identified risks will also be continuously incorporated to the CARAMEL solution. The final goal of CARAMEL is to create an anti-hacking platform for the European automotive cybersecurity and to demonstrate its value through extensive attack and penetration scenarios. In this paper we will expand on the unique cybersecurity-relevant characteristics of the pillars upon which the CARAMEL solution is built. Next, a number of use cases emerging from such analysis will be extracted in order to form the basis upon which the CARAMEL platform will be evaluated. Finally, we will conclude with an overview of the platform’s architectural composition.
Margounakis, Dimitrios; Karalis, Themistoklis; Iliou, Theodoros
Interactive Serious Games for Cultural Heritage (Inproceedings)
In: Auer, Michael E; Tsiatsos, Thrasyvoulos (Ed.): Internet of Things, Infrastructures and Mobile Applications, pp. 606–617, Springer International Publishing, Cham, 2021, ISBN: 978-3-030-49932-7.
Interactive Music Video Games are games in which music plays a leading role. This paper presents an interactive serious music game about Rebetiko and Greek folk music and has as its primary musical instrument a traditional string instrument: the bouzouki. The user can play the bouzouki piece, aided by visual stimuli representing the notes and by the music itself that acts as acoustic stimuli at the same time. A special interface -- controller was created for the application needs by modifying a keyboard, which the user can hold like a bouzouki. These mechanisms, along with other elements of the gameplay, give the user the feeling that they are playing the bouzouki themselves in the rebetiko song being played. In addition, the application also has an educational dimension. The playing style comprises an introduction to playing a stringed musical instrument, as it involves movements that simulate pressing the frets and hitting the strings of the instrument. The user also encounters musical elements such as tonality, harmony and rhythm. Finally, the game incorporates information about Rebetiko and folk music, directly intertwined with the songs the user plays, offering an integrated experience.
Tzimas, Rafail; Margounakis, Dimitrios; Politis, Dionysios; Paris, Nektarios-Kyriakos
Interactive TV and Music Education (Inproceedings)
In: Auer, Michael E; Tsiatsos, Thrasyvoulos (Ed.): Internet of Things, Infrastructures and Mobile Applications, pp. 45–53, Springer International Publishing, Cham, 2021, ISBN: 978-3-030-49932-7.
Music Learning online has been promoted the last decades as an Interactive methodology with considerable outcomes, in terms of efficiency, effectiveness and attainment of popularity. However, a situation where no noticeable progress would be inferred as accredited benefit of massive learning was reported a decade ago. The advent of mobile computing communication proved a forceful exertion to situated learning in music having the power to influence the acquisition of music knowledge and skills. The case of a novel Byzantine Music learning protocol is examined for its potential to achieve relatively a big ``crop'' from rather limited in extend lessons but with the capacity to have a significant effect on the context of musical instruction.
Protopsaltis, Antonis; Sarigiannidis, Panagiotis; Margounakis, Dimitrios; Lytos, Anastasios
In: ARES 2020: The 15th International Conference on Availability, Reliability and Security, 2020.
As the Internet of Things (IoT) grows rapidly, huge amounts of wireless sensor networks emerged monitoring a wide range of infrastructure, in various domains such as healthcare, energy, transportation, smart city, building automation, agriculture, and industry producing continuously streamlines of data. Big Data technologies play a significant role within IoT processes, as visual analytics tools, generating valuable knowledge in real-time in order to support critical decision making. This paper provides a comprehensive survey of visualization methods, tools, and techniques for the IoT. We position data visualization inside the visual analytics process by reviewing the visual analytics pipeline. We provide a study of various chart types available for data visualization and analyze rules for employing each one of them, taking into account the special conditions of the particular use case. We further examine some of the most promising visualization tools. Since each IoT domain is isolated in terms of Big Data approaches, we investigate visualization issues in each domain. Additionally, we review visualization methods oriented to anomaly detection. Finally, we provide an overview of the major challenges in IoT visualizations.
Radoglou-Grammatikis, Panagiotis; Sarigiannidis, Panagiotis; Efstathopoulos, George; Karypidis, Paris-Alexandros; Sarigiannidis, Antonios
In: Proceedings of the 15th International Conference on Availability, Reliability and Security, Association for Computing Machinery, Virtual Event, Ireland, 2020, ISBN: 9781450388337.
In this paper, an Intrusion Detection and Prevention System (IDPS) for the Distributed Network Protocol 3 (DNP3) Supervisory Control and Data Acquisition (SCADA) systems is presented. The proposed IDPS is called DIDEROT (Dnp3 Intrusion DetEction pReventiOn sysTem) and relies on both supervised Machine Learning (ML) and unsupervised/outlier ML detection models capable of discriminating whether a DNP3 network flow is related to a particular DNP3 cyberattack or anomaly. First, the supervised ML detection model is applied, trying to identify whether a DNP3 network flow is related to a specific DNP3 cyberattack. If the corresponding network flow is detected as normal, then the unsupervised/outlier ML anomaly detection model is activated, seeking to recognise the presence of a possible anomaly. Based on the DIDEROT detection results, the Software Defined Networking (SDN) technology is adopted in order to mitigate timely the corresponding DNP3 cyberattacks and anomalies. The performance of DIDEROT is demonstrated using real data originating from a substation environment.
Grammatikis, Panagiotis Radoglou; Sarigiannidis, Panagiotis; Sarigiannidis, Antonios; Margounakis, Dimitrios; Tsiakalos, Apostolos; Efstathopoulos, Georgios
An Anomaly Detection Mechanism for IEC 60870-5-104 (Inproceedings)
In: 2020 9th International Conference on Modern Circuits and Systems Technologies (MOCAST), 2020.
The transformation of the conventional electricity grid into a new paradigm called smart grid demands the appropriate cybersecurity solutions. In this paper, we focus on the security of the IEC 60870-5-104 (IEC-104) protocol which is commonly used by Supervisory Control and Data Acquisition (SCADA) systems in the energy domain. In particular, after investigating its security issues, we provide a multivariate Intrusion Detection System (IDS) which adopts both access control and outlier detection mechanisms in order to detect timely possible anomalies against IEC-104. The efficiency of the proposed IDS is reflected by the Accuracy and F1 metrics that reach 98% and 87%, respectively.
Pliatsios, Dimitrios; Sarigiannidis, Panagiotis; Efstathopoulos, Georgios; Sarigiannidis, Antonios; Tsiakalos, Apostolos
Trust Management in Smart Grid: A Markov Trust Model (Inproceedings)
In: 2020 9th International Conference on Modern Circuits and Systems Technologies (MOCAST), pp. 1-4, 2020.
(Tags: )| | |
By leveraging the advancements in Information and Communication Technologies (ICT), Smart Grid (SG) aims to modernize the traditional electric power grid towards efficient distribution and reliable management of energy in the electrical domain. The SG Advanced Metering Infrastructure (AMI) contains numerous smart meters, which are deployed throughout the distribution grid. However, these smart meters are susceptible to cyberthreats that aim to disrupt the normal operation of the SG. Cyberattacks can have various consequences in the smart grid, such as incorrect customer billing or equipment destruction. Therefore, these devices should operate on a trusted basis in order to ensure the availability, confidentiality, and integrity of the metering data. In this paper, we propose a Markov chain trust model that determines the Trust Value (TV) for each AMI device based on its behavior. Finally, numerical computations were carried out in order to investigate the reaction of the proposed model to the behavior changes of a device.
Grammatikis, Panagiotis Radoglou; Sarigiannidis, Panagiotis; Iturbe, Eider; Rios, Erkuden; Sarigiannidis, Antonios; Nikolis, Odysseas; Ioannidis, Dimosthenis; Machamint, Vasileios; Tzifas, Michalis; Giannakoulias, Alkiviadis; Angelopoulos, Michail; Papadopoulos, Anastasios; Ramos, Francisco
Secure and Private Smart Grid: The SPEAR Architecture (Inproceedings)
In: 2020 6th IEEE International Conference on Network Softwarization (NetSoft), pp. 450-456, 2020.
Information and Communication Technology (ICT) is an integral part of Critical Infrastructures (CIs), bringing both significant pros and cons. Focusing our attention on the energy sector, ICT converts the conventional electrical grid into a new paradigm called Smart Grid (SG), providing crucial benefits such as pervasive control, better utilisation of the existing resources, self-healing, etc. However, in parallel, ICT increases the attack surface of this domain, generating new potential cyberthreats. In this paper, we present the Secure and PrivatE smArt gRid (SPEAR) architecture which constitutes an overall solution aiming at protecting SG, by enhancing situational awareness, detecting timely cyberattacks, collecting appropriate forensic evidence and providing an anonymous cybersecurity information-sharing mechanism. Operational characteristics and technical specifications details are analysed for each component, while also the communication interfaces among them are described in detail.
Triantafyllou, Anna; Sarigiannidis, Panagiotis; Lagkas, Thomas; Moscholios, Ioannis; Sarigiannidis, Antonios
In: Computer Networks, 186 , 2020.
(Tags: )| | |
The employment of Low-Power Wide Area Networks (LPWANs) has proven quite beneficial to the advancement of the Internet of Things (IoT) paradigm. The utilization of low power but long range communication links of the LoRaWAN technology promises low energy consumption, while ensuring sufficient throughput. However, due to LoRa’s original scheduling process there is a high chance of packet collisions, compromising the technology’s reliability. In this paper, we propose a new Medium Access Control (MAC) protocol, entitled the FCA-LoRa leveraging fairness and improving collision avoidance in LoRa wide-area networks. The novel scheduling process that is introduced is based on the broadcasting of beacon frames by the network’s gateway in order to synchronize communication with end devices. Our results demonstrate the benefits of FCA-LoRa over an enhanced version of the legacy LoRaWAN employing the ALOHA protocol and an advanced adaptive rate mechanism, in terms of throughput and collision avoidance. Indicatively, in a single gateway scenario with 600 nodes, FCA-LoRa can increase throughput by nearly 50% while in a multiple gateway scenario, throughput reaches an increase of 49% for 500 nodes.
Triantafyllou, Anna; Sarigiannidis, Panagiotis; Lagkas, Thomas; Sarigiannidis, Antonios
In: 2020 9th International Conference on Modern Circuits and Systems Technologies (MOCAST), pp. 1-4, 2020.
(Tags: )| |
Siniosoglou, Ilias; Efstathopoulos, Georgios; Pliatsios, Dimitrios; Moscholios, Ioannis; Sarigiannidis, Antonios; Sakellari, Georgia; Loukas, Georgios; Sarigiannidis, Panagiotis
In: 2020 IEEE Symposium on Computers and Communications (ISCC), pp. 1-7, 2020.
(Tags: )| |
Lytos, Anastasios; Lagkas, Thomas; Sarigiannidis, Panagiotis; Zervakis, Michalis; Livanos, George
In: Computer Networks, 172 , pp. 107147, 2020, ISSN: 1389-1286.
Agriculture is by its nature a complicated scientific field, related to a wide range of expertise, skills, methods and processes which can be effectively supported by computerized systems. There have been many efforts towards the establishment of an automated agriculture framework, capable to control both the incoming data and the corresponding processes. The recent advances in the Information and Communication Technologies (ICT) domain have the capability to collect, process and analyze data from different sources while materializing the concept of agriculture intelligence. The thriving environment for the implementation of different agriculture systems is justified by a series of technologies that offer the prospect of improving agricultural productivity through the intensive use of data. The concept of big data in agriculture is not exclusively related to big volume, but also on the variety and velocity of the collected data. Big data is a key concept for the future development of agriculture as it offers unprecedented capabilities and it enables various tools and services capable to change its current status. This survey paper covers the state-of-the-art agriculture systems and big data architectures both in research and commercial status in an effort to bridge the knowledge gap between agriculture systems and exploitation of big data. The first part of the paper is devoted to the exploration of the existing agriculture systems, providing the necessary background information for their evolution until they have reached the current status, able to support different platforms and handle multiple sources of information. The second part of the survey is focused on the exploitation of multiple sources of information, providing information for both the nature of the data and the combination of different sources of data in order to explore the full potential of ICT systems in agriculture.
Pliatsios, Dimitrios; Sarigiannidis, Panagiotis; Lagkas, Thomas; Sarigiannidis, Antonios G
In: IEEE Communications Surveys Tutorials, 22 (3), pp. 1942-1976, 2020.
Supervisory Control and Data Acquisition (SCADA) systems are the underlying monitoring and control components of critical infrastructures, such as power, telecommunication, transportation, pipelines, chemicals and manufacturing plants. Legacy SCADA systems operated on isolated networks, that made them less exposed to Internet threats. However, the increasing connection of SCADA systems to the Internet, as well as corporate networks, introduces severe security issues. Security considerations for SCADA systems are gaining higher attention, as the number of security incidents against these critical infrastructures is increasing. In this survey, we provide an overview of the general SCADA architecture, along with a detailed description of the SCADA communication protocols. Additionally, we discuss certain high-impact security incidents, objectives, and threats. Furthermore, we carry out an extensive review of the security proposals and tactics that aim to secure SCADA systems. We also discuss the state of SCADA system security. Finally, we present the current research trends and future advancements of SCADA security.
Margounakis, Dimitrios; Pachidis, Theodore; Politis, Dionysios
In: 8th International Scientific Conference Technics and Informatics in Education, 2020.
The COVID-19 pandemic has brought about rapid changes in the educational process in all countries where extreme measures, such as lockdown, were applied. Almost all levels of education have turned to synchronous teaching, using various video conferencing services. This study will attempt to evaluate specific applications with the assistance of appropriate methodology based on rubrics and the SUS questionnaire for interactive systems. A comparative evaluation of 5 popular video conferencing tools (Big Blue Button, Google Meet, Skype for Business, WebEx, Zoom) was attempted based on a methodological approach with usability and functionality criteria. A rubric was generated to assist the authors in assessing the selected five video conferencing tools. The research took place in May 2020. The sample of the survey included 73 adults (teachers at all levels of education) that used those video conferencing services. The aim of this study is to highlight teachers' views and needs from tools supporting synchronous education in order to improve the online learning process at all levels of education.
In: Enabling Technologies and Architectures for Next-Generation Networking Capabilities, IGI Global, 2019, ISBN: 2327-3305.
In the past few years, it's observed that cellular operators have experienced a fast growth of mobile broadband subscribers and traffic volume per subscriber. Simultaneously, operators are moving from a single to a multi-service offering by adding new services. This chapter presents a survey of the Quality of Service (QoS) drivers in LTE and LTE-Advanced, focusing on IP Frameworks and IP Services. It also includes a detailed list and description of the resource management mechanisms, such as power saving, admission control, scheduling and resource allocation that play a vital role in QoS. The authors describe the State-of-the-Art in IP frameworks and Services such as video, VoIP, Video on Demand (VoD). Also, resource management mechanisms are described such as Energy efficiency, admission control, and scheduling. In the end, the authors mentioned the future directions about QoS in 5G networks.
Perra, Cristian; Grigoriou, Elisavet; Liotta, Antonio; Song, Wei; Usai, Claudio; Giusto, Daniele
Augmented reality for cultural heritage education (Inproceedings)
In: IEEE 9th International Conference on Consumer Electronics (ICCE-Berlin), 2019.
In the past few years, it is noticed a fast adoption and increase of mobile devices that are able to retrieve information quickly, regardless of the user's physical environment. Thus, application developers have leveraged it by developing a variety of applications using mobile Augmented Reality (AR) in domains such as cultural heritage education, shopping, gaming, and more. AR technology overlays a virtual object into the real world that enables users to have virtual and real-world experience at the same time. During a visit to a cultural heritage site such as a museum or an art gallery, the learning experience and enjoyment is necessary for a visitor and AR introduces new opportunities to improve them. We propose an AR-based framework for cultural heritage education. We aim to promote cultural heritage education by enriching user's experience and at the same time to offer the knowledge with the most enjoyable way. In order to evaluate our framework, we have developed a server application and an AR-based smartphone application.
Dalamagkas, Christos; Sarigiannidis, Panagiotis; Ioannidis, Dimosthenis; Iturbe, Eider; Nikolis, Odysseas; Ramos, Francisco; Rios, Erkuden; Sarigiannidis, Antonios; Tzovaras, Dimitrios
In: 2019 IEEE Conference on Network Softwarization (NetSoft), pp. 93-100, 2019.
(Tags: )| | |
Power grid is a major part of modern Critical Infrastructure (CIN). The rapid evolution of Information and Communication Technologies (ICT) enables traditional power grids to encompass advanced technologies that allow them to monitor their state, increase their reliability, save costs and provide ICT services to end customers, thus converting them into smart grids. However, smart grid is exposed to several security threats, as hackers might try to exploit vulnerabilities of the industrial infrastructure and cause disruption to national electricity system with severe consequences to citizens and commerce. This paper investigates and compares honey-x technologies that could be applied to smart grid in order to distract intruders, obtain attack strategies, protect the real infrastructure and form forensic evidence to be used in court.
Efstathopoulos, Georgios; Grammatikis, Panagiotis Radoglou; Sarigiannidis, Panagiotis; Argyriou, Vasilis; Sarigiannidis, Antonios; Stamatakis, Konstantinos; Angelopoulos, Michail K; Athanasopoulos, Solon K
Operational Data Based Intrusion Detection System for Smart Grid (Inproceedings)
In: 2019 IEEE 24th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD), pp. 1-6, 2019.
With the rapid progression of Information and Communication Technology (ICT) and especially of Internet of Things (IoT), the conventional electrical grid is transformed into a new intelligent paradigm, known as Smart Grid (SG). SG provides significant benefits both for utility companies and energy consumers such as the two-way communication (both electricity and information), distributed generation, remote monitoring, self-healing and pervasive control. However, at the same time, this dependence introduces new security challenges, since SG inherits the vulnerabilities of multiple heterogeneous, co-existing legacy and smart technologies, such as IoT and Industrial Control Systems (ICS). An effective countermeasure against the various cyberthreats in SG is the Intrusion Detection System (IDS), informing the operator timely about the possible cyberattacks and anomalies. In this paper, we provide an anomaly-based IDS especially designed for SG utilising operational data from a real power plant. In particular, many machine learning and deep learning models were deployed, introducing novel parameters and feature representations in a comparative study. The evaluation analysis demonstrated the efficacy of the proposed IDS and the improvement due to the suggested complex data representation.
Lytos, Anastasios; Lagkas, Thomas; Sarigiannidis, Panagiotis; Bontcheva, Kalina
In: Information Processing & Management, 56 , 2019.
Argumentation mining is a rising subject in the computational linguistics domain focusing on extracting structured arguments from natural text, often from unstructured or noisy text. The initial approaches on modeling arguments was aiming to identify a flawless argument on specific fields (Law, Scientific Papers) serving specific needs (completeness, effectiveness). With the emerge of Web 2.0 and the explosion in the use of social media both the diffusion of the data and the argument structure have changed. In this survey article, we bridge the gap between theoretical approaches of argumentation mining and pragmatic schemes that satisfy the needs of social media generated data, recognizing the need for adapting more flexible and expandable schemes, capable to adjust to the argumentation conditions that exist in social media. We review, compare, and classify existing approaches, techniques and tools, identifying the positive outcome of combining tasks and features, and eventually propose a conceptual architecture framework. The proposed theoretical framework is an argumentation mining scheme able to identify the distinct sub-tasks and capture the needs of social media text, revealing the need for adopting more flexible and extensible frameworks.
Pliatsios, Dimitrios; Sarigiannidis, Panagiotis; Moscholios, Ioannis D; Tsiakalos, Apostolos
In: 2019 Panhellenic Conference on Electronics Telecommunications (PACET), pp. 1-4, 2019.
(Tags: )| | |
Dense small cell deployment is an effective way to address the increasing requirements of the emerging Fifth Generation mobile networks. The Cloud Radio Access Network (C-RAN) is an emerging concept that can achieve very dense small cell deployment. In ultra-dense C-RAN architectures with numerous Remote Radio Heads (RRHs), the minimization of the deployment cost is a critical issue in the radio network planning phase. In this paper, we propose a low complexity algorithm that minimizes the required number of small cells, while ensuring user satisfaction in terms of network capacity. The algorithm is based on the successive elimination of RRHs, and it simultaneously solves the minimization and the optimal deployment problems. The evaluation results indicate that the proposed algorithm can efficiently solve the aforementioned problems.
Iliou, Theodoros; Konstantopoulou, Georgia; Lymperopoulou, Christina; Anastasopoulos, Konstantinos; Anastassopoulos, George; Margounakis, Dimitrios; Lymberopoulos, Dimitrios
In: Artificial Intelligence Applications and Innovations, pp. 512–519, Springer International Publishing, Cham, 2019, ISBN: 978-3-030-19823-7.
As real world data tends to be incomplete, noisy and inconsistent, data preprocessing is an important issue for data mining. Data preparation includes data cleaning, data integration, data transformation and data reduction. In this paper, Iliou preprocessing method is compared with Principal Component Analysis in suicide prediction according to family history. The dataset consists of 360 students, aged 18 to 24, who were experiencing family history problems. The performance of Iliou and Principal Component Analysis data preprocessing methods was evaluated using the 10-fold cross validation method assessing ten classification algorithms, IB1, J48, Random Forest, MLP, SMO, JRip, RBF, Na"ive Bayes, AdaBoostM1 and HMM, respectively. Experimental results illustrate that Iliou data preprocessing algorithm outperforms Principal Component Analysis data preprocessing method, achieving 100% against 71.34% classification performance, respectively. According to the classification results, Iliou preprocessing method is the most suitable for suicide prediction.
Lytos, Anastasios; Lagkas, Thomas; Sarigiannidis, Panagiotis; Bontcheva, Kalina
In: 12th Annual South-East European Doctoral Student Conference (DSC2018), 2018.
The field of Argumentation Mining has arisen from the need of determining the underlying causes from an expressed opinion and the urgency to develop the established fields of Opinion Mining and Sentiment Analysis. The recent progress in the wider field of Artificial Intelligence in combination with the available data through Social Web has create great potential for every sub-field of Natural Language Process including Argumentation Mining.
Grigoriou, Elisavet; Saoulidis, Theocharis; Atzori, Luigi; Pilloni, Virginia; Chatzimisios, Periklis
A QoE monitoring solution for LTE-Advanced Pro networks (Inproceedings)
In: IEEE Computer-Aided Modeling Analysis and Design of Communication Links and Networks 2018, 2018.
(Tags: )| | |
This paper presents a distributed agent-based Quality of Experience (QoE) monitoring solution for Long Term Evolution (LTE)-Advanced Pro networks. The proposed solution relies on an approach that considers the computational complexity and the network load to adjust the frequency of measurements while considering the estimation accuracy. Accordingly, the proposed system allows the Internet Service Provider (ISP) to monitor the network QoE level accurately without overloading the network by considering different Influence Factors (IFs). Some preliminary results are shown in terms of accuracy of estimations and computational complexity in case of video streaming service.
Grigoriou, Elisavet; Atzori, Luigi; Saoulidis, Theocharis; Pilloni, Virginia; Chatzimisios, Periklis
An agent-based QoE monitoring strategy for LTE networks (Inproceedings)
In: ICC2018, 2018.
The new generation of Long Term Evolution (LTE) networks provides ubiquitous broadband access to mobile devices matching land communications in quality and speed. However, to optimize network resource usage in a dynamic environment network operators need models and strategies to constantly assess and manage the end-user's Quality of Experience (QoE). Given the importance of these activities, in the current paper, we focus on quality monitoring and the usage of QoE-agents in an LTE-Advanced Pro network. Specifically, we identify the location and the operation of the QoE-Agents based on the accuracy of the measurements and the load in the network by considering the frequency of the measurements and the running applications. Emulations have been also carried out to evaluate two considered scenarios with different network conditions as well as with different quality sampling rates and application configurations. The preliminary results have shown that the proposed strategy results in acceptable errors from our measurements, low CPU utilization and acceptable memory utilization.
Triantafyllou, Anna; Sarigiannidis, Panagiotis; Sarigiannidis, Antonios; Rios, Erkuden; Iturbe, Eider
In: Proceedings of the 22nd Pan-Hellenic Conference on Informatics, pp. 34–39, Association for Computing Machinery, Athens, Greece, 2018, ISBN: 9781450366106.
The Electric Smart Grid (ESG) is an intelligent critical infrastructure aiming to create an automated and distributed advanced energy delivery network, while preserving information privacy. This study proposes the implementation of an Anonymous Incident Communication Channel (AICC) amongst smart grids across Europe to improve situational awareness and enhance security of the new electric intelligent infrastructures. All participating organizations will have the ability to broadcast sensitive information, stored anonymously in a repository, without exposing the reputation of the organisation. This work focuses on the requirements of establishment, the possible obstacles and proposed data protection techniques to be applied in the AICC. Furthermore, a discussion is conducted regarding the documentation of cyber-incidents. Last but not least, the benefits and the potential risks of this AICC concept are also provided.
Politis, Dionysios; Tsirantonakis, Anastasios; Aleksić, Veljko; Nteropoulos, Panagiotis; Margounakis, Dimitrios
In: Auer, Michael E; Tsiatsos, Thrasyvoulos (Ed.): Interactive Mobile Communication Technologies and Learning, pp. 778–788, Springer International Publishing, Cham, 2018, ISBN: 978-3-319-75175-7.
This research examines how regulatory action by policy makers and the states involved may reshape the map of terrestrial television and radio broadcasts, not only in Greece, who serves as a case study, but for many countries who face similar problems. Taking as starting point the recent licensing competition this paper provides suggestions about how deregulating may be the amalgam of technologies that mix free on-line media providers with expensive, state regulated public goods in the frequency domain.
Sarigiannidis, Antonios; Karypidis, Paris-Alexandros; Sarigiannidis, Panagiotis; Pragidis, Ioannis-Chrysostomos
In: Internet Science, pp. 37–48, Springer International Publishing, Cham, 2018, ISBN: 978-3-319-77547-0.
Sentiment analysis refers to the use of natural language processing (NLP) and textual analysis approaches to identify and extract subjective information from textual sources. Extracting sensible financial knowledge from relevant textual material is significant in order to help leverage the predictive power of the financial and econometric forecasting models. However, the determination of the sentiment analysis from textual data such as headlines, news and user comments is not an easy task. One of the most arduous challenges when dealing with sentiment analysis is the accuracy. In this work, a new lexicon-based approach is presented which is based on supervised learning. The introduced model is able to create a new lexicon based on annotated textual data and then it applies that lexicon to determine the sentiment in new, not-annotated data. The proposed method seems able to work effectively with financial data while supporting accurate decisions.
Sarigiannidis, Panagiotis; Sarigiannidis, Antonios; Moscholios, Ioannis; Zwierzykowski, Piotr
In: Mobile Information Systems, 2017 , 2017.
(Tags: )| | |
Modern broadband hybrid optical-wireless access networks have gained the attention of academia and industry due to their strategic advantages. Namely they extend the network coverage in a cost-efficient way, they allow a larger number of potential subscribers than conventional access architectures and they exploit the huge bandwidth of the optical technology with the flexibility and mobility of wireless access networks. At the same time the proliferation of Software Defined Networking (SDN) enables the efficient reconfiguration of the underlying network components dynamically using SDN controllers. Hence, effective traffic-aware schemes are feasible in dynamically determining suitable configuration parameters for advancing the network performance. To this end, a novel machine learning mechanism is proposed for an SDN-enabled hybrid optical-wireless network. The proposed architecture consists of a 10-gigabit-capable passive optical network (XG-PON) in the network backhaul and multiple Long Term Evolution (LTE) radio access networks in the fronhaul. The proposed mechanism receives traffic-aware knowledge from the SDN controllers and applies an adjustment on the uplink-downlink configuration in the LTE radio communication. This traffic-aware mechanism is simple and capable of determining the most suitable configuration based on the traffic dynamics in the whole hybrid network. The introduced scheme is evaluated in a realistic environment using real traffic traces such as Voice over IP (VoIP), real-time video and streaming video. According to the obtained numerical results the proposed mechanism offers significant improvements in the network performance in terms of latency and jitter.
Grigoriou, Elisavet; Atzori, Luigi; Pilloni, Virginia
In: Globecom2017, 2017.
In this paper, we illustrate a Software Defined Network (SDN)-based architecture for Quality of Experience (QoE) management. This approach solves two of the major problems of current networking technologies which are related to the limitations in scalability and flexibility. Its advantage is the exploitation of the virtualization features of the network nodes and devices to flexibly deploy monitoring and control functions in the different points of the network according to the SDN control functions. As a result the QoE monitoring and management is deployed at the application layer on top of the controller. In order to evaluate the proposed framework and architecture, a platform has been developed, which is called QoE-MoMa (QoE-Monitoring and Management) platform, making use of the Opendaylight solution and Mininet emulation environment. To evaluate QoE-MoMa, we focused on the video streaming service, whose final quality has been evaluated using the estimated MOS (eMOS) model that mostly considers rebuffering events, duration of the rebuffering, switch quality rates, video resolution, and quantization parameter. The results show the efficiency of the proposed approach observing that higher QoE level is achieved if we consider application and network parameters. In conclusion, we consider that QoE-MoMa is useful as a QoE monitoring and management tool for a variety of services and can be deployed on a real network conveniently.
Grigoriou, Elisavet; Barakabitze, Alcardo Alex; Atzori, Luigi; Sun, Lingfen; Pilloni, Virginia
In: 2017 IEEE International Conference on Communications (ICC), pp. 1-7, 2017.
(Tags: )| | |
Future networks will be accompanied by new heterogeneous requirements in terms of end-users Quality of Experience (QoE) due to the increasing number of application scenarios being deployed. Network softwarization technologies such as Software Defined Networks (SDNs) and Network Function Virtualization (NFV) promise to provide these capabilities. In this paper, a novel QoE-driven resource allocation mechanism is proposed to dynamically assign tasks to virtual network nodes in order to achieve an optimized end-to-end quality. The aim is to find the best combination of network node functions that can provide an optimized level of QoE to the end users though node cooperation. The service in question is divided in tasks and the neighbor nodes negotiate the assignment of these considering the final quality. In the paper we specifically focus on the video streaming service. We also show that the agility provided by SDN/NFV is a key factor for enhancing video quality, resource allocation and QoE management in future networks. Preliminary results based on the Mininet network emulator and the OpenDaylight controller have shown that our approach can significantly improve the quality of a transmitted video by selecting the best path with normalized QoS values.
Sarigiannidis, Panagiotis; Zygiridis, Theodoros; Sarigiannidis, Antonios; Lagkas, Thomas D; Obaidat, Mohammad; Kantartzis, Nikolaos
Connectivity and coverage in machine-type communications (Inproceedings)
In: 2017 IEEE International Conference on Communications (ICC), pp. 1-6, 2017.
(Tags: )| | |
Machine-type communication (MTC) provides a potential playground for deploying machine-to-machine (M2M), IP-enabled `things' and wireless sensor networks (WSNs) that support modern, added-value services and applications. 4G/5G technology can facilitate the connectivity and the coverage of the MTC entities and elements by providing M2M-enabled gateways and base stations for carrying traffic streams to/from the backbone network. For example, the latest releases of long-term evolution (LTE) such as LTE-Advanced (LTE-A) are being transformed to support the migration of M2M devices. MTC-oriented technical definitions and requirements are defined to support the emerging M2M proliferation. ETSI describes three types of MTC access methods, namely a) the direct access, b) the gateway access and c) the coordinator access. This work is focused on studying coverage aspects when a gateway access takes place. A deployment planar field is considered where a number of M2M devices are randomly deployed, e.g., a hospital where body sensor networks form a M2M infrastructure. An analytical framework is devised that computes the average number of connected M2M devices when a M2C gateway is randomly placed for supporting connectivity access to the M2M devices. The introduced analytical framework is verified by simulation and numerical results.
Margounakis, Dimitrios; Aleksić, Veljko; Karanikas, Nikolaos
In: International Journal of New Technologies in Science and Engineering, 4 , 2017.
Similar to the music investment of movies is the composition of audio effects and music for the escalating industry of video gaming. Gamification has been endorsed as an interdisciplinary factor for promoting entertainment along constructivist learning. As a result, the production of music for games has been promoted as a state-of-the-art research field in computer science. Apart from its business sense it also provides a developmental journey that promotes sets of different expectations and attracts new groups of vendors. Since the production of games is characterized by maximum activity in terms of complication and cost (the production of a 3-D multiplayer game can sum up to millions of dollars), the role of sound engineer/composer/programmer becomes crucial. This research describes how sound investment can endow stimulating musical compositions. State of the art systems and techniques that develop algorithmic music composition for this specific audiovisual activity are analyzed.
Achilleas, Moukoulis; Diamantidou, Eleni; Karipidis, Paris; Dasygenis, Minas
In: PCI 2017: Proceedings of the 21st Pan-Hellenic Conference on Informatics, pp. 1-2, 2017, ISBN: 978-1-4503-5355-7.
(Tags: )| | |
This is a paper about a Real Time Object Tracking application based on Computer Vision tools. The Background Subtraction technique (BS Technique) is implemented and used to deal with the object tracking on video feeds.The application can extend an established surveillance system by providing custom alerts of suspicious objects to the operators.
Gounalakis, Orestis; Lytos, Anastasios; Dasygenis, Minas
Leveraging Parallelization Opportunities by an Online CAD Tool (Inproceedings)
In: Proceedings of the SouthEast European Design Automation, Computer Engineering, Computer Networks and Social Media Conference, pp. 25–31, Association for Computing Machinery, Kastoria, Greece, 2016, ISBN: 9781450348102.
High-performance computing utilizes many ranks and threads exploiting contemporary parallel and distributing processing architectures. Parallelizing an application is not a straightforward task as it is commonly admitted among all the researchers with this expertise. With all the different design decisions it's easy to be overwhelmed with the intricacies of the hardware and create strange bugs. Tools that aid developers to leverage their skills and knowledge are in great need. Here, we present an online tool that automates a part of the visualization of the parallelism, and can be used to pinpoint errant approaches, as we illustrate with a case study. The tool is available online at our web server, has very low runtime and can instrument via a web interface C and C++ files. The execution of these files can give an insight to the realization of the parallelism, like which thread or rank is accessing a memory address each time step. We have successfully used our tool on motion estimation kernels that were at our disposal, to aid towards their parallelization. As a test case, we present how this tool is used to pinpoint erroneous parallelization approaches on a well-known multimedia kernel.
Sarigiannidis, Antonios; Nicopolitidis, Petros
In: International Journal of Communication Systems, 29 (10), pp. 1658-1682, 2016.
Summary The convergence of optical and wireless technologies may offer a compelling network access infrastructure because these technologies combine major benefits such as large coverage in the wireless part and huge bandwidth in the optical part of the converged access network. The convergence of the passive optical networks with 4G wireless standards, such as the Worldwide Interoperability for Microwave Access and the Long Term Evolution, constitutes a quite attractive solution to meet the challenges of the modern bandwidth-hungry access networks. One of the most important objective a modern access network has to address is the adequate bandwidth distribution to the final users. In addition, several other aims are emerged towards this goal, such as fairness and quality of service provisioning. The adversity of designing an efficient bandwidth distribution scheme for hybrid optical-wireless access networks lies in the interdependence of both domains: the bandwidth distribution in the wireless domain depends on the optical transmission grant opportunities, while the bandwidth coordinator in the optical part has to be aware of the mobile user heterogeneity in the wireless domain. Moreover, the bandwidth decision-making module in both networks has to be aware of providing a fair allocation independently of the number of mobile users or the traffic requests in the network. In this work, we endeavor to address the aforementioned challenges. A novel, fair, and efficient bandwidth distribution scheme is proposed for hybrid optical-wireless access networks. By using weighted fairness provisioning techniques, the proposed scheme intends to alleviate the interdependence of the two domains, offering a fair and efficient bandwidth distribution to the mobile users. The weights are properly defined, by utilizing suitable optimization techniques such as the Lagrange multiplies, so as to incorporate the underlying features of each traffic requests, such as the population density and the propagation delay. Extensive simulation results indicate the capability of the proposed scheme, compared with other competitive allocation schemes, in provisioning a more efficient and fair bandwidth distribution in terms of latency, throughput, and packet drop ratio. Copyright © 2015 John Wiley & Sons, Ltd.
Sarigiannidis, Antonios; Nicopolitidis, Petros
In: IET Networks, 5 (3), pp. 56–63, 2016.
Fibre wireless (FiWi) access networks constitute a promising candidate to meet the demanding challenges of the modern bandwidth-hungry services and applications. Due to the dynamic nature of the network traffic in access domains, the bandwidth allocation process has to provide a fair and effective coordination between the users including an efficient quality-of-service (QoS) plan. However, the majority of the bandwidth allocation schemes neglect the measured QoS parameters, such as latency, jitter, and packet loss. In addition, the fairness issue is not always taken into account. As a result, the packet delivery of sensitive data streams is often problematic and the QoS guarantees are not addressed or even totally ignored. In this study, the authors present a novel bandwidth allocation policy which applies an efficient weighted-based, QoS-aware schedule in modern FiWi networks with fairness support. The innovation behind the proposed scheme lies in the direct association of the measured QoS parameters with the applied fair bandwidth allocation process.
Sarigiannidis, Antonios G; Iloridou, Maria; Nicopolitidis, Petros; Papadimitriou, Georgios; Pavlidou, Fotini-Niovi; Sarigiannidis, Panagiotis G; Louta, Malamati D; Vitsas, Vasileios
In: IEEE Communications Surveys Tutorials, 17 (1), pp. 427-468, 2015.
The combination of the most prestigious optical and wireless technologies for implementing a modern broadband integrated access network has been progressively gaining ground. By extending the network coverage in a cost-efficient way, hybrid wireless-optical networks are able to enclose a larger number of
potential subscribers than standalone access architectures. Hence, they are capable of increasing revenue levels and facilitating commercial penetration to the telecom market. At the same time, hybrid wireless-optical networks pose an ambitious, alternative, and efficient solution to coping with new bandwidth-hungry user applications. Hybrid wireless-optical networks incorporate sophisticated modules, fabrics, and network entities to effectively provide adequate quality of service (QoS) provisioning. This survey endeavors to classify the main features of wireless-optical integration. We provide a comprehensive compilation of the latest architectures, integrated technologies, QoS features, and dynamic bandwidth allocation (DBA) schemes. In addition, new trends towards wireless-optical convergence are presented. Moreover, as the up-to-date hybrid network standards remain under development, since there is not yet an integrated standard for approving hybrid network access platforms, we accompany this survey with detailed challenges indicating potential avenues of future research.