2022
Panagiotis Radoglou Grammatikis; Panagiotis Sarigiannidis; Panagiotis Diamantoulakis; Thomas Lagkas; Theocharis Saoulidis; Eleftherios Fountoukidis; George Karagiannidis
Strategic Honeypot Deployment in Ultra-Dense Beyond 5G Networks: A Reinforcement Learning Approach Journal Article
In: IEEE Transactions on Emerging Topics in Computing, 2022, ISSN: 2168-6750.
Abstract | BibTeX | Tags: Honeypot, Intrusion detection, ReinforcementLearning, Wireless communication | Links:
@article{articledb,
title = {Strategic Honeypot Deployment in Ultra-Dense Beyond 5G Networks: A Reinforcement Learning Approach},
author = {Panagiotis Radoglou Grammatikis and Panagiotis Sarigiannidis and Panagiotis Diamantoulakis and Thomas Lagkas and Theocharis Saoulidis and Eleftherios Fountoukidis and George Karagiannidis},
url = {https://www.researchgate.net/publication/361139812_Strategic_Honeypot_Deployment_in_Ultra-Dense_Beyond_5G_Networks_A_Reinforcement_Learning_Approach},
doi = {10.1109/TETC.2022.3184112},
issn = {2168-6750},
year = {2022},
date = {2022-06-01},
urldate = {2022-01-01},
journal = {IEEE Transactions on Emerging Topics in Computing},
abstract = {The progression of Software Defined Networking (SDN) and the virtualisation technologies lead to the beyond 5G era, providing multiple benefits in the smart economies. However, despite the advantages, security issues still remain. In particular, SDN/NFV and cloud/edge computing are related to various security issues. Moreover, due to the wireless nature of the entities, they are prone to a wide range of cyberthreats. Therefore, the presence of appropriate intrusion detection mechanisms is critical. Although both Machine Learning (ML) and Deep Learning (DL) have optimised the typical rule-based detection systems, the use of ML and DL requires labelled pre-existing datasets. However, this kind of data varies based on the nature of the respective environment. Another smart solution for detecting intrusions is to use honeypots. A honeypot acts as a decoy with the goal to mislead the cyberatatcker and protect the real assets. In this paper, we focus on Wireless Honeypots (WHs) in ultradense networks. In particular, we introduce a strategic honeypot deployment method, using two Reinforcement Learning (RL) techniques: (a) e−Greedy and (b) Q−Learning. Both methods aim to identify the optimal number of honeypots that can be deployed for protecting the actual entities. The experimental results demonstrate the efficacy of both methods.},
keywords = {Honeypot, Intrusion detection, ReinforcementLearning, Wireless communication},
pubstate = {published},
tppubtype = {article}
}
The progression of Software Defined Networking (SDN) and the virtualisation technologies lead to the beyond 5G era, providing multiple benefits in the smart economies. However, despite the advantages, security issues still remain. In particular, SDN/NFV and cloud/edge computing are related to various security issues. Moreover, due to the wireless nature of the entities, they are prone to a wide range of cyberthreats. Therefore, the presence of appropriate intrusion detection mechanisms is critical. Although both Machine Learning (ML) and Deep Learning (DL) have optimised the typical rule-based detection systems, the use of ML and DL requires labelled pre-existing datasets. However, this kind of data varies based on the nature of the respective environment. Another smart solution for detecting intrusions is to use honeypots. A honeypot acts as a decoy with the goal to mislead the cyberatatcker and protect the real assets. In this paper, we focus on Wireless Honeypots (WHs) in ultradense networks. In particular, we introduce a strategic honeypot deployment method, using two Reinforcement Learning (RL) techniques: (a) e−Greedy and (b) Q−Learning. Both methods aim to identify the optimal number of honeypots that can be deployed for protecting the actual entities. The experimental results demonstrate the efficacy of both methods.
Christos Chaschatzis; Anastasios Lytos; Stamatia Bibi; Thomas Lagkas; Christina Petaloti; Sotirios Goudos; Ioannis Moscholios; Panagiotis Sarigiannidis
2022, ISBN: 978-1-6654-6717-9.
Abstract | BibTeX | Tags: Education material, Farm-to-Fork, Green Deal, Information systems, Knowledge exchange | Links:
@conference{inproceedingsb,
title = {Integration of Information and Communication Technologies in Agriculture for Farm Management and Knowledge Exchange},
author = {Christos Chaschatzis and Anastasios Lytos and Stamatia Bibi and Thomas Lagkas and Christina Petaloti and Sotirios Goudos and Ioannis Moscholios and Panagiotis Sarigiannidis},
url = {https://www.researchgate.net/publication/362336475_Integration_of_Information_and_Communication_Technologies_in_Agriculture_for_Farm_Management_and_Knowledge_Exchange},
doi = {10.1109/MOCAST54814.2022.9837534},
isbn = {978-1-6654-6717-9},
year = {2022},
date = {2022-06-01},
pages = {1-4},
abstract = {The demographic growth of the last centuries has been followed by a demand for higher productivity of agriculture activities and an increase in the quality of farming products. Modern consumers seek quality by selecting foods containing high concentrations of healthy nutrients (e.g., antioxidants, vitamins, minerals) while also valuing eco-friendly practices and sustainable consumption. In line with the modern social needs, integrating Information Communication Technologies (ICT) solutions could assist in different levels of the agriculture lifecycle, such as crop monitoring, animal production, food safety, and farm management. Two aspects that are often neglected from many ICT solutions are the compilation of different data sources into the proposed software architecture and the facilitation of knowledge exchange between domain experts. In order to fill the gap of knowledge accumulation in this paper we take into consideration the PestNu architecture, as defined in section V that illustrates the different steps that are required for a complete data analysis life cycle into the development and deployment of the OpenHub platform. The OpenHub aims to cover the knowledge hub between experts with different backgrounds and promote the best practices from different users with hands-on experience.},
keywords = {Education material, Farm-to-Fork, Green Deal, Information systems, Knowledge exchange},
pubstate = {published},
tppubtype = {conference}
}
The demographic growth of the last centuries has been followed by a demand for higher productivity of agriculture activities and an increase in the quality of farming products. Modern consumers seek quality by selecting foods containing high concentrations of healthy nutrients (e.g., antioxidants, vitamins, minerals) while also valuing eco-friendly practices and sustainable consumption. In line with the modern social needs, integrating Information Communication Technologies (ICT) solutions could assist in different levels of the agriculture lifecycle, such as crop monitoring, animal production, food safety, and farm management. Two aspects that are often neglected from many ICT solutions are the compilation of different data sources into the proposed software architecture and the facilitation of knowledge exchange between domain experts. In order to fill the gap of knowledge accumulation in this paper we take into consideration the PestNu architecture, as defined in section V that illustrates the different steps that are required for a complete data analysis life cycle into the development and deployment of the OpenHub platform. The OpenHub aims to cover the knowledge hub between experts with different backgrounds and promote the best practices from different users with hands-on experience.
Vasiliki Kelli; Panagiotis Radoglou-Grammatikis; Achilleas Sesis; Thomas Lagkas; Eleftherios Fountoukidis; Emmanouil Kafetzakis; Ioannis Giannoulakis; Panagiotis Sarigiannidis
Attacking and Defending DNP3 ICS/SCADA Systems Conference
2022 18th International Conference on Distributed Computing in Sensor Systems (DCOSS), 2022, ISBN: 978-1-6654-9512-7.
Abstract | BibTeX | Tags: cyberattack, DNP3, ICS, Intrusion detection, SCADA | Links:
@conference{9881726,
title = {Attacking and Defending DNP3 ICS/SCADA Systems},
author = {Vasiliki Kelli and Panagiotis Radoglou-Grammatikis and Achilleas Sesis and Thomas Lagkas and Eleftherios Fountoukidis and Emmanouil Kafetzakis and Ioannis Giannoulakis and Panagiotis Sarigiannidis},
doi = {10.1109/DCOSS54816.2022.00041},
isbn = {978-1-6654-9512-7},
year = {2022},
date = {2022-05-30},
booktitle = {2022 18th International Conference on Distributed Computing in Sensor Systems (DCOSS)},
pages = {183-190},
abstract = {The highly beneficial contribution of intelligent systems in the industrial domain is undeniable. Automation, supervision, remote control, and fault reduction are some of the various advantages new technologies offer. A protocol demonstrating high utility in industrial settings, and specifically, in smart grids, is Distributed Network Protocol 3 (DNP3), a multi-tier, application layer protocol. Notably, multiple industrial protocols are not as securely designed as expected, considering the highly critical operations occurring in their application domain. In this paper, we explore the internal vulnerabilities-by-design of DNP3, and proceed with the implementation of the attacks discovered, demonstrated through 8 DNP3 attack scenarios. Finally, we design and demonstrate a Deep Neural Network (DNN)-based, multi-model Intrusion Detection Systems (IDS), trained with our experimental network flow cyberattack dataset, and compare our solution with multiple machine learning algorithms used for classification. Our solution demonstrates a high efficiency in the classification of DNP3 cyberattacks, showing an accuracy of 99.0%.},
keywords = {cyberattack, DNP3, ICS, Intrusion detection, SCADA},
pubstate = {published},
tppubtype = {conference}
}
The highly beneficial contribution of intelligent systems in the industrial domain is undeniable. Automation, supervision, remote control, and fault reduction are some of the various advantages new technologies offer. A protocol demonstrating high utility in industrial settings, and specifically, in smart grids, is Distributed Network Protocol 3 (DNP3), a multi-tier, application layer protocol. Notably, multiple industrial protocols are not as securely designed as expected, considering the highly critical operations occurring in their application domain. In this paper, we explore the internal vulnerabilities-by-design of DNP3, and proceed with the implementation of the attacks discovered, demonstrated through 8 DNP3 attack scenarios. Finally, we design and demonstrate a Deep Neural Network (DNN)-based, multi-model Intrusion Detection Systems (IDS), trained with our experimental network flow cyberattack dataset, and compare our solution with multiple machine learning algorithms used for classification. Our solution demonstrates a high efficiency in the classification of DNP3 cyberattacks, showing an accuracy of 99.0%.
Georgios Amponis; Panagiotis Radoglou Grammatikis; Thomas Lagkas; W Mallouli; Ana Cavalli; Dimitris Klonidis; Evangelos Markakis; Panagiotis Sarigiannidis
Threatening the 5G Core via PFCP DoS Attacks: The Case of Blocking UAV Communications Journal Article
In: 2022.
Abstract | BibTeX | Tags: 5G Security, 5G Testbed, DoS Attacks, PFCP, UAV Communications | Links:
@article{unknown,
title = {Threatening the 5G Core via PFCP DoS Attacks: The Case of Blocking UAV Communications},
author = {Georgios Amponis and Panagiotis Radoglou Grammatikis and Thomas Lagkas and W Mallouli and Ana Cavalli and Dimitris Klonidis and Evangelos Markakis and Panagiotis Sarigiannidis},
url = {https://www.researchgate.net/publication/361231451_Threatening_the_5G_Core_via_PFCP_DoS_Attacks_The_Case_of_Blocking_UAV_Communications},
doi = {10.21203/rs.3.rs-1708948/v1},
year = {2022},
date = {2022-05-01},
abstract = {The modern communications landscape requires reliable, high-speed, high- throughput and secure links and sessions between user equipment instances and the data network. The 5G core implements the newly defined 3GPP network ar- chitecture enabling faster connectivity, low latency, higher bit rates and network reliability. The full potential of this set of networks will support a set of critical Internet of Things (IoT) and industrial use cases. Nevertheless, several compo- nents and interfaces of the Next-Generation Radio Access Network (NG-RAN) have proven to be vulnerable to attacks that can potentially obstruct the net- work’s capability to provide reliable end-to-end communication services. Various inherent security flaws and protocol-specific weaknesses have also been identified within the 5G core itself. However, little to no research has gone into testing and exposing said core-related weaknesses, contrary to those concerning the NG-RAN. In this paper, we investigate, describe, develop, implement and finally test a set of attacks on the Packet Forwarding Control Protocol (PFCP) inside the 5G core. We find that, by transmitting unauthorised session control packets, we were able to disrupt established 5G tunnels without disrupting subscribers’ connectivity to the NG-RAN, thus hindering the detection of said attacks. We evaluate the identi- fied PFCP attacks in a drone-based scenario involving 5G tunnelling between two swarms.},
keywords = {5G Security, 5G Testbed, DoS Attacks, PFCP, UAV Communications},
pubstate = {published},
tppubtype = {article}
}
The modern communications landscape requires reliable, high-speed, high- throughput and secure links and sessions between user equipment instances and the data network. The 5G core implements the newly defined 3GPP network ar- chitecture enabling faster connectivity, low latency, higher bit rates and network reliability. The full potential of this set of networks will support a set of critical Internet of Things (IoT) and industrial use cases. Nevertheless, several compo- nents and interfaces of the Next-Generation Radio Access Network (NG-RAN) have proven to be vulnerable to attacks that can potentially obstruct the net- work’s capability to provide reliable end-to-end communication services. Various inherent security flaws and protocol-specific weaknesses have also been identified within the 5G core itself. However, little to no research has gone into testing and exposing said core-related weaknesses, contrary to those concerning the NG-RAN. In this paper, we investigate, describe, develop, implement and finally test a set of attacks on the Packet Forwarding Control Protocol (PFCP) inside the 5G core. We find that, by transmitting unauthorised session control packets, we were able to disrupt established 5G tunnels without disrupting subscribers’ connectivity to the NG-RAN, thus hindering the detection of said attacks. We evaluate the identi- fied PFCP attacks in a drone-based scenario involving 5G tunnelling between two swarms.
M. Stauch P. Radoglou-Grammatikis P. Sarigiannidis G. Lazaridis A. Drosou I. Nwankwo; D. Tzovaras
Data Protection and Cybersecurity Certification Activities and Schemes in the Energy Sector Journal Article
In: Electronics, vol. 11, no. 6, 2022, ISSN: 2079-9292.
Abstract | BibTeX | Tags: certification, Cybersecurity, data protection, energy | Links:
@article{electronics11060965,
title = {Data Protection and Cybersecurity Certification Activities and Schemes in the Energy Sector},
author = { M. Stauch P. Radoglou-Grammatikis P. Sarigiannidis G. Lazaridis A. Drosou I. Nwankwo and D. Tzovaras},
url = {https://www.researchgate.net/publication/359370929_Data_Protection_and_Cybersecurity_Certification_Activities_and_Schemes_in_the_Energy_Sector},
doi = {10.3390/electronics11060965},
issn = {2079-9292},
year = {2022},
date = {2022-02-12},
journal = {Electronics},
volume = {11},
number = {6},
abstract = {Cybersecurity concerns have been at the forefront of regulatory reform in the European Union (EU) recently. One of the outcomes of these reforms is the introduction of certification schemes for information and communication technology (ICT) products, services and processes, as well as for data processing operations concerning personal data. These schemes aim to provide an avenue for consumers to assess the compliance posture of organisations concerning the privacy and security of ICT products, services and processes. They also present manufacturers, providers and data controllers with the opportunity to demonstrate compliance with regulatory requirements through a verifiable third-party assessment. As these certification schemes are being developed, various sectors, including the electrical power and energy sector, will need to access the impact on their operations and plan towards successful implementation. Relying on a doctrinal method, this paper identifies relevant EU legal instruments on data protection and cybersecurity certification and their interpretation in order to examine their potential impact when applying certification schemes within the Electrical Power and Energy System (EPES) domain. The result suggests that the EPES domain employs different technologies and services from diverse areas, which can result in the application of several certification schemes within its environment, including horizontal, technological and sector-specific schemes. This has the potential for creating a complex constellation of implementation models and would require careful design to avoid proliferation and disincentivising of stakeholders.},
keywords = {certification, Cybersecurity, data protection, energy},
pubstate = {published},
tppubtype = {article}
}
Cybersecurity concerns have been at the forefront of regulatory reform in the European Union (EU) recently. One of the outcomes of these reforms is the introduction of certification schemes for information and communication technology (ICT) products, services and processes, as well as for data processing operations concerning personal data. These schemes aim to provide an avenue for consumers to assess the compliance posture of organisations concerning the privacy and security of ICT products, services and processes. They also present manufacturers, providers and data controllers with the opportunity to demonstrate compliance with regulatory requirements through a verifiable third-party assessment. As these certification schemes are being developed, various sectors, including the electrical power and energy sector, will need to access the impact on their operations and plan towards successful implementation. Relying on a doctrinal method, this paper identifies relevant EU legal instruments on data protection and cybersecurity certification and their interpretation in order to examine their potential impact when applying certification schemes within the Electrical Power and Energy System (EPES) domain. The result suggests that the EPES domain employs different technologies and services from diverse areas, which can result in the application of several certification schemes within its environment, including horizontal, technological and sector-specific schemes. This has the potential for creating a complex constellation of implementation models and would require careful design to avoid proliferation and disincentivising of stakeholders.
Ilias Siniosoglou; Vasileios Argyriou; Thomas Lagkas; Apostolos Tsiakalos; Antonios Sarigiannidis; Panagiotis Sarigiannidis
Covert Distributed Training of Deep Federated Industrial Honeypots Conference
2021 IEEE Globecom Workshops (GC Wkshps), 2022, ISBN: 978-1-6654-2391-5.
Abstract | BibTeX | Tags: Autoencoder, Data Generation, Deep Learning, Honeypots, Industrial Control System, SCADA | Links:
@conference{9682162,
title = {Covert Distributed Training of Deep Federated Industrial Honeypots},
author = { Ilias Siniosoglou and Vasileios Argyriou and Thomas Lagkas and Apostolos Tsiakalos and Antonios Sarigiannidis and Panagiotis Sarigiannidis},
url = {https://www.researchgate.net/publication/358085083_Covert_Distributed_Training_of_Deep_Federated_Industrial_Honeypots},
doi = {10.1109/GCWkshps52748.2021.9682162},
isbn = {978-1-6654-2391-5},
year = {2022},
date = {2022-01-24},
booktitle = {2021 IEEE Globecom Workshops (GC Wkshps)},
pages = {1-6},
abstract = {Since the introduction of automation technologies in the Industrial field and its subsequent scaling to horizontal and vertical extents, the need for interconnected industrial systems, supporting smart interoperability is ever higher. Due to this scaling, new and critical vulnerabilities have been created, notably in legacy systems, leaving Industrial infrastructures prone to cyber attacks, that can some times have catastrophic results. To tackle the need for extended security measures, this paper presents a Federated Industrial Honeypot that takes advantage of decentralized private Deep Training to produce models that accumulate and simulate real industrial devices. To enhance their camouflage, SCENT, a new custom and covert protocol is proposed, to fully immerse the Federated Honeypot to its industrial role, that handles the communication between the server and honeypot during the training, to hide any clues of operation of the honeypot other that its supposed objective to the eye of the attacker.},
keywords = {Autoencoder, Data Generation, Deep Learning, Honeypots, Industrial Control System, SCADA},
pubstate = {published},
tppubtype = {conference}
}
Since the introduction of automation technologies in the Industrial field and its subsequent scaling to horizontal and vertical extents, the need for interconnected industrial systems, supporting smart interoperability is ever higher. Due to this scaling, new and critical vulnerabilities have been created, notably in legacy systems, leaving Industrial infrastructures prone to cyber attacks, that can some times have catastrophic results. To tackle the need for extended security measures, this paper presents a Federated Industrial Honeypot that takes advantage of decentralized private Deep Training to produce models that accumulate and simulate real industrial devices. To enhance their camouflage, SCENT, a new custom and covert protocol is proposed, to fully immerse the Federated Honeypot to its industrial role, that handles the communication between the server and honeypot during the training, to hide any clues of operation of the honeypot other that its supposed objective to the eye of the attacker.
Dimitrios Pliatsios; Thomas Lagkas; Vasileios Argyriou; Antonios Sarigiannidis; Dimitrios Margounakis; Theocharis Saoulidis; Panagiotis Sarigiannidis
A Hybrid RF-FSO Offloading Scheme for Autonomous Industrial Internet of Things Conference
IEEE INFOCOM 2022 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), 2022, ISBN: 978-1-6654-0926-1.
Abstract | BibTeX | Tags: Computation offloading, energy efficiency, Free-space Optical Communications, Industrial Internet of Things, Multi-access Edge Computing | Links:
@conference{9798011,
title = {A Hybrid RF-FSO Offloading Scheme for Autonomous Industrial Internet of Things},
author = { Dimitrios Pliatsios and Thomas Lagkas and Vasileios Argyriou and Antonios Sarigiannidis and Dimitrios Margounakis and Theocharis Saoulidis and Panagiotis Sarigiannidis},
doi = {10.1109/INFOCOMWKSHPS54753.2022.9798011},
isbn = {978-1-6654-0926-1},
year = {2022},
date = {2022-01-01},
booktitle = {IEEE INFOCOM 2022 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)},
pages = {1-6},
abstract = {The ever increasing demand for bandwidth triggered by data-intensive applications is imposing a considerable burden on the radio-frequency (RF) spectrum. A promising solution to address the spectrum congestion problem is the adoption of free-space optical (FSO) communications. In this work, we consider a hybrid RF-FSO system that enables the task offloading process from Industrial Internet-of-Things devices to a multi-access edge computing (MEC)-enabled base station (BS). We propose a solution that minimizes the total energy consumption of the system by deciding whether the RF or FSO link will be used for the task offloading and optimally allocating the device transmission power while taking into account the task requirements in terms of delay. The proposed solution is based on a decomposition-driven algorithm that employs integer linear programming (ILP) and Lagrange dual decomposition. Finally, we carry out system-level Monte Carlo simulations to evaluate the performance of the solution. The simulation results show that the proposed solution can minimize the total energy consumption within a few iterations, while also considering the respective latency requirements.},
keywords = {Computation offloading, energy efficiency, Free-space Optical Communications, Industrial Internet of Things, Multi-access Edge Computing},
pubstate = {published},
tppubtype = {conference}
}
The ever increasing demand for bandwidth triggered by data-intensive applications is imposing a considerable burden on the radio-frequency (RF) spectrum. A promising solution to address the spectrum congestion problem is the adoption of free-space optical (FSO) communications. In this work, we consider a hybrid RF-FSO system that enables the task offloading process from Industrial Internet-of-Things devices to a multi-access edge computing (MEC)-enabled base station (BS). We propose a solution that minimizes the total energy consumption of the system by deciding whether the RF or FSO link will be used for the task offloading and optimally allocating the device transmission power while taking into account the task requirements in terms of delay. The proposed solution is based on a decomposition-driven algorithm that employs integer linear programming (ILP) and Lagrange dual decomposition. Finally, we carry out system-level Monte Carlo simulations to evaluate the performance of the solution. The simulation results show that the proposed solution can minimize the total energy consumption within a few iterations, while also considering the respective latency requirements.
2021
C. Chaschatzis; C. Karaiskou; E. Mouratidis; E. Karagiannis; P. Sarigiannidis
Detection and Characterization of Stressed Sweet Cherry Tissues Using Machine Learning Journal Article
In: Drones, vol. 6, pp. 3, 2021.
Abstract | BibTeX | Tags: diseases detection, machine learning, precision agriculture, ResNet, smart farming, stress detection, sweet cherries trees, Yolov5 | Links:
@article{article,
title = {Detection and Characterization of Stressed Sweet Cherry Tissues Using Machine Learning},
author = { C. Chaschatzis and C. Karaiskou and E. Mouratidis and E. Karagiannis and P. Sarigiannidis},
url = {https://www.researchgate.net/publication/357257849_Detection_and_Characterization_of_Stressed_Sweet_Cherry_Tissues_Using_Machine_Learning},
doi = {10.3390/drones6010003},
year = {2021},
date = {2021-12-22},
journal = {Drones},
volume = {6},
pages = {3},
abstract = {Recent technological developments in the primary sector and machine learning algorithms allow the combined application of many promising solutions in precision agriculture. For example, the YOLOv5 (You Only Look Once) and ResNet Deep Learning architecture provide high-precision real-time identifications of objects. The advent of datasets from different perspectives provides multiple benefits, such as spheric view of objects, increased information, and inference results from multiple objects detection per image. However, it also raises crucial obstacles such as total identifications (ground truths) and processing concerns that can lead to devastating consequences, including false-positive detections with other erroneous conclusions or even the inability to extract results. This paper introduces experimental results from the machine learning algorithm (Yolov5) on a novel dataset based on perennial fruit crops, such as sweet cherries, aiming to enhance precision agriculture resiliency. Detection is oriented on two points of interest: (a) Infected leaves and (b) Infected branches. It is noteworthy that infected leaves or branches indicate stress, which may be due to either a stress/disease (e.g., Armillaria for sweet cherries trees, etc.) or other factors (e.g., water shortage, etc). Correspondingly, the foliage of a tree shows symptoms, while this indicates the stages of the disease.},
keywords = {diseases detection, machine learning, precision agriculture, ResNet, smart farming, stress detection, sweet cherries trees, Yolov5},
pubstate = {published},
tppubtype = {article}
}
Recent technological developments in the primary sector and machine learning algorithms allow the combined application of many promising solutions in precision agriculture. For example, the YOLOv5 (You Only Look Once) and ResNet Deep Learning architecture provide high-precision real-time identifications of objects. The advent of datasets from different perspectives provides multiple benefits, such as spheric view of objects, increased information, and inference results from multiple objects detection per image. However, it also raises crucial obstacles such as total identifications (ground truths) and processing concerns that can lead to devastating consequences, including false-positive detections with other erroneous conclusions or even the inability to extract results. This paper introduces experimental results from the machine learning algorithm (Yolov5) on a novel dataset based on perennial fruit crops, such as sweet cherries, aiming to enhance precision agriculture resiliency. Detection is oriented on two points of interest: (a) Infected leaves and (b) Infected branches. It is noteworthy that infected leaves or branches indicate stress, which may be due to either a stress/disease (e.g., Armillaria for sweet cherries trees, etc.) or other factors (e.g., water shortage, etc). Correspondingly, the foliage of a tree shows symptoms, while this indicates the stages of the disease.
Dimitrios Pliatsios; Sotirios K. Goudos; Thomas Lagkas; Vasileios Argyriou; Alexandros Apostolos A. Boulogeorgos; Panagiotis Sarigiannidis
Drone-Base-Station for Next-Generation Internet-of-Things: A Comparison of Swarm Intelligence Approaches Journal Article
In: IEEE Open Journal of Antennas and Propagation, 2021, ISSN: 2637-6431.
Abstract | BibTeX | Tags: Drone base station, evolutionary algorithms, mobile communications, Optimization methods, Swarm intelligence | Links:
@article{Pliatsios2021b,
title = {Drone-Base-Station for Next-Generation Internet-of-Things: A Comparison of Swarm Intelligence Approaches},
author = {Dimitrios Pliatsios and Sotirios K. Goudos and Thomas Lagkas and Vasileios Argyriou and Alexandros Apostolos A. Boulogeorgos and Panagiotis Sarigiannidis},
url = {https://www.researchgate.net/publication/356863442_Drone-Base-Station_for_Next-Generation_Internet-of-Things_A_Comparison_of_Swarm_Intelligence_Approaches},
doi = {10.1109/OJAP.2021.3133459},
issn = {2637-6431},
year = {2021},
date = {2021-12-07},
journal = {IEEE Open Journal of Antennas and Propagation},
abstract = {The emergence of next-generation internet-of-things (NG-IoT) applications introduces several challenges for the sixth-generation (6G) mobile networks, such as massive connectivity, increased network capacity, and extremely low-latency. To countermeasure the aforementioned challenges, ultra-dense networking has been widely identified as a possible solution. However, the dense deployment of base stations (BSs) is not always possible or cost-efficient. Drone-base-stations (DBSs) can facilitate network expansion and efficiently address the requirements of NG-IoT. In addition, due to their flexibility, they can provide on-demand connectivity in emergency scenarios or address temporary increases in network traffic. Nevertheless, the optimal placement of a DBS is not a straightforward task due to the limited energy reserves and the increased signal quality degradation in air-to-ground links. To this end, swarm intelligence approaches can be attractive solutions for determining the optimal position of the DBS in the three-dimensional (3D) space. In this work, we explore well-known swarm intelligence approaches, namely the Cuckoo Search (CS), Elephant Herd Optimization (EHO), Grey Wolf Optimization (GWO), Monarch Butterfly Optimization (MBO), Salp Swarm Algorithm (SSA), and Particle Swarm Optimization (PSO) and investigate their performance and efficiency in solving the aforementioned problem. In particular, we investigate the performance of three scenarios in the presence of different swarm intelligence approaches. Additionally, we carry out non-parametric statistical tests, namely the Friedman and Wilcoxon tests, in order to compare the different approaches.},
keywords = {Drone base station, evolutionary algorithms, mobile communications, Optimization methods, Swarm intelligence},
pubstate = {published},
tppubtype = {article}
}
The emergence of next-generation internet-of-things (NG-IoT) applications introduces several challenges for the sixth-generation (6G) mobile networks, such as massive connectivity, increased network capacity, and extremely low-latency. To countermeasure the aforementioned challenges, ultra-dense networking has been widely identified as a possible solution. However, the dense deployment of base stations (BSs) is not always possible or cost-efficient. Drone-base-stations (DBSs) can facilitate network expansion and efficiently address the requirements of NG-IoT. In addition, due to their flexibility, they can provide on-demand connectivity in emergency scenarios or address temporary increases in network traffic. Nevertheless, the optimal placement of a DBS is not a straightforward task due to the limited energy reserves and the increased signal quality degradation in air-to-ground links. To this end, swarm intelligence approaches can be attractive solutions for determining the optimal position of the DBS in the three-dimensional (3D) space. In this work, we explore well-known swarm intelligence approaches, namely the Cuckoo Search (CS), Elephant Herd Optimization (EHO), Grey Wolf Optimization (GWO), Monarch Butterfly Optimization (MBO), Salp Swarm Algorithm (SSA), and Particle Swarm Optimization (PSO) and investigate their performance and efficiency in solving the aforementioned problem. In particular, we investigate the performance of three scenarios in the presence of different swarm intelligence approaches. Additionally, we carry out non-parametric statistical tests, namely the Friedman and Wilcoxon tests, in order to compare the different approaches.
Panagiotis Radoglou Grammatikis; Panagiotis Sarigiannidis; Christos Dalamagkas; Yannis Spyridis; Thomas Lagkas; Georgios Efstathopoulos; Achilleas Sesis; Ignacio Labrador Pavon; Ruben Trapero Burgos; Rodrigo Diaz; Antonios Sarigiannidis; Dimitris Papamartzivanos; Sofia Anna Menesidou; Giannis Ledakis; Achilleas Pasias; Thanasis Kotsiopoulos; Anastasios Drosou; Orestis Mavropoulos; Alba Colet Subirachs; Pol Paradell Sola; José Luis Domínguez-García; Marisa Escalante; Molinuevo Martin Alberto; Benito Caracuel; Francisco Ramos; Vasileios Gkioulos; Sokratis Katsikas; Hans Christian Bolstad; Dan-Eric Archer; Nikola Paunovic; Ramon Gallart; Theodoros Rokkas; Alicia Arce
SDN-Based Resilient Smart Grid: The SDN-microSENSE Architecture Journal Article
In: Digital, vol. 1, no. 4, pp. 173–187, 2021, ISSN: 2673-6470.
Abstract | BibTeX | Tags: Anomaly Detection, Blockchain, Cybersecurity, energy management; honeypots, intrusiondetection, islanding, Privacy, Smart Grid, Software Defined Networking | Links:
@article{digital1040013,
title = {SDN-Based Resilient Smart Grid: The SDN-microSENSE Architecture},
author = { Panagiotis Radoglou Grammatikis and Panagiotis Sarigiannidis and Christos Dalamagkas and Yannis Spyridis and Thomas Lagkas and Georgios Efstathopoulos and Achilleas Sesis and Ignacio Labrador Pavon and Ruben Trapero Burgos and Rodrigo Diaz and Antonios Sarigiannidis and Dimitris Papamartzivanos and Sofia Anna Menesidou and Giannis Ledakis and Achilleas Pasias and Thanasis Kotsiopoulos and Anastasios Drosou and Orestis Mavropoulos and Alba Colet Subirachs and Pol Paradell Sola and José Luis Domínguez-García and Marisa Escalante and Molinuevo Martin Alberto and Benito Caracuel and Francisco Ramos and Vasileios Gkioulos and Sokratis Katsikas and Hans Christian Bolstad and Dan-Eric Archer and Nikola Paunovic and Ramon Gallart and Theodoros Rokkas and Alicia Arce},
url = {https://www.researchgate.net/publication/354992483_SDN-Based_Resilient_Smart_Grid_The_SDN-microSENSE_Architecture},
doi = {10.3390/digital1040013},
issn = {2673-6470},
year = {2021},
date = {2021-09-24},
journal = {Digital},
volume = {1},
number = {4},
pages = {173--187},
abstract = {The technological leap of smart technologies and the Internet of Things has advanced the conventional model of the electrical power and energy systems into a new digital era, widely known as the Smart Grid. The advent of Smart Grids provides multiple benefits, such as self-monitoring, self-healing and pervasive control. However, it also raises crucial cybersecurity and privacy concerns that can lead to devastating consequences, including cascading effects with other critical infrastructures or even fatal accidents. This paper introduces a novel architecture, which will increase the Smart Grid resiliency, taking full advantage of the Software-Defined Networking (SDN) technology. The proposed architecture called SDN-microSENSE architecture consists of three main tiers: (a) Risk assessment, (b) intrusion detection and correlation and (c) self-healing. The first tier is responsible for evaluating dynamically the risk level of each Smart Grid asset. The second tier undertakes to detect and correlate security events and, finally, the last tier mitigates the potential threats, ensuring in parallel the normal operation of the Smart Grid. It is noteworthy that all tiers of the SDN-microSENSE architecture interact with the SDN controller either for detecting or mitigating intrusions.},
keywords = {Anomaly Detection, Blockchain, Cybersecurity, energy management; honeypots, intrusiondetection, islanding, Privacy, Smart Grid, Software Defined Networking},
pubstate = {published},
tppubtype = {article}
}
The technological leap of smart technologies and the Internet of Things has advanced the conventional model of the electrical power and energy systems into a new digital era, widely known as the Smart Grid. The advent of Smart Grids provides multiple benefits, such as self-monitoring, self-healing and pervasive control. However, it also raises crucial cybersecurity and privacy concerns that can lead to devastating consequences, including cascading effects with other critical infrastructures or even fatal accidents. This paper introduces a novel architecture, which will increase the Smart Grid resiliency, taking full advantage of the Software-Defined Networking (SDN) technology. The proposed architecture called SDN-microSENSE architecture consists of three main tiers: (a) Risk assessment, (b) intrusion detection and correlation and (c) self-healing. The first tier is responsible for evaluating dynamically the risk level of each Smart Grid asset. The second tier undertakes to detect and correlate security events and, finally, the last tier mitigates the potential threats, ensuring in parallel the normal operation of the Smart Grid. It is noteworthy that all tiers of the SDN-microSENSE architecture interact with the SDN controller either for detecting or mitigating intrusions.
Address
Internet of Things and Applications Lab
Department of Electrical and Computer Engineering
University of Western Macedonia Campus
ZEP Area, Kozani 50100
Greece
Contact Information
tel: +30 2461 056527
Email: ithaca@uowm.gr
