2022 |
Konstantinos-Filippos Kollias; Christine K Syriopoulou-Delli; Panagiotis Sarigiannidis; George F Fragulis , "Autism detection in High-Functioning Adults with the application of Eye-Tracking technology and Machine Learning", 2022 11th International Conference on Modern Circuits and Systems Technologies (MOCAST), 2022, ISBN: 978-1-6654-6717-9. Conference Περίληψη | BibTeX | Ετικέτες: eye-tracking, High-Functioning Autism detection, IoT, machine learning, Transfer learning, web | Σύνδεσμοι: @conference{9837653, title = {Autism detection in High-Functioning Adults with the application of Eye-Tracking technology and Machine Learning}, author = {Konstantinos-Filippos Kollias and Christine K Syriopoulou-Delli and Panagiotis Sarigiannidis and George F Fragulis}, url = {https://www.researchgate.net/publication/362340239_Autism_detection_in_High-Functioning_Adults_with_the_application_of_Eye-Tracking_technology_and_Machine_Learning}, doi = {10.1109/MOCAST54814.2022.9837653}, isbn = {978-1-6654-6717-9}, year = {2022}, date = {2022-06-08}, booktitle = {2022 11th International Conference on Modern Circuits and Systems Technologies (MOCAST)}, pages = {1-4}, abstract = {High-Functioning Autism Detection in Adults is significantly difficult compared with early Autism Spectrum Disorder (ASD) diagnosis with severe symptoms. ASD diagnosis is usually achieved by behavioural instruments relying on subjective rather on objective criteria, whereas advances in research indicate cutting -edge methods for early assessment, such as eye-tracking technology, machine learning, Internet of Things (IoT), and other assessment tools. This study suggests the detection of ASD in high-functioning adults with the contribution of Transfer Learning. Decision Trees, Logistic Regression and Transfer Learning were applied on a dataset consisting of high-functioning ASD adults and controls, who looked for information within web pages. A high classification accuracy was achieved regarding a Browse (80.50%) and a Search (81%) task showing that our method could be considered a promising tool regarding automatic ASD detection. Limitations and suggestions for future research are also included.}, keywords = {eye-tracking, High-Functioning Autism detection, IoT, machine learning, Transfer learning, web}, pubstate = {published}, tppubtype = {conference} } High-Functioning Autism Detection in Adults is significantly difficult compared with early Autism Spectrum Disorder (ASD) diagnosis with severe symptoms. ASD diagnosis is usually achieved by behavioural instruments relying on subjective rather on objective criteria, whereas advances in research indicate cutting -edge methods for early assessment, such as eye-tracking technology, machine learning, Internet of Things (IoT), and other assessment tools. This study suggests the detection of ASD in high-functioning adults with the contribution of Transfer Learning. Decision Trees, Logistic Regression and Transfer Learning were applied on a dataset consisting of high-functioning ASD adults and controls, who looked for information within web pages. A high classification accuracy was achieved regarding a Browse (80.50%) and a Search (81%) task showing that our method could be considered a promising tool regarding automatic ASD detection. Limitations and suggestions for future research are also included. |
2021 |
C. Chaschatzis; C. Karaiskou; E. Mouratidis; E. Karagiannis; P. Sarigiannidis , "Detection and Characterization of Stressed Sweet Cherry Tissues Using Machine Learning", Drones, 6 , pp. 3, 2021. Journal Article Περίληψη | BibTeX | Ετικέτες: diseases detection, machine learning, precision agriculture, ResNet, smart farming, stress detection, sweet cherries trees, Yolov5 | Σύνδεσμοι: @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. |
I. Siniosoglou; V. Argyriou; S. Bibi; T. Lagkas; P. Sarigiannidis , "Unsupervised Ethical Equity Evaluation of Adversarial Federated Networks", The 16th International Conference on Availability, Reliability and Security, 2021. Conference Περίληψη | BibTeX | Ετικέτες: adverserial federated networks, machine learning, security | Σύνδεσμοι: @conference{Siniosoglou2021c, title = {Unsupervised Ethical Equity Evaluation of Adversarial Federated Networks}, author = {I. Siniosoglou and V. Argyriou and S. Bibi and T. Lagkas and P. Sarigiannidis}, url = {https://www.researchgate.net/publication/353936098_Unsupervised_Ethical_Equity_Evaluation_of_Adversarial_Federated_Networks}, doi = {10.1145/3465481.3470478}, year = {2021}, date = {2021-08-17}, booktitle = {The 16th International Conference on Availability, Reliability and Security}, pages = {1-6}, abstract = {While the technology of Deep Learning (DL) is a powerful tool when properly trained for image analysis and classification applications, some factors for its optimization rely solely on the training data and their environment. In an effort to tackle the problem of knowledge bias created during the training process of a Deep Neural Network (DNN) and specifically Adversarial Networks for image augmentation, this work presents an entirely unsupervised methodology for discovering the unfairness level of Deep Learning (DL) models and in extend, its wrongly accumulated or biased classes. Fdi, the proposed evaluation metric for quantizing the level of unfairness of a model is introduced, along with the method of weighting the model’s knowledge and producing its weakest aspects in a data-agnostic way.}, keywords = {adverserial federated networks, machine learning, security}, pubstate = {published}, tppubtype = {conference} } While the technology of Deep Learning (DL) is a powerful tool when properly trained for image analysis and classification applications, some factors for its optimization rely solely on the training data and their environment. In an effort to tackle the problem of knowledge bias created during the training process of a Deep Neural Network (DNN) and specifically Adversarial Networks for image augmentation, this work presents an entirely unsupervised methodology for discovering the unfairness level of Deep Learning (DL) models and in extend, its wrongly accumulated or biased classes. Fdi, the proposed evaluation metric for quantizing the level of unfairness of a model is introduced, along with the method of weighting the model’s knowledge and producing its weakest aspects in a data-agnostic way. |
S. Sotiroudis; K. Siakavara; G. Koudouridis; P. Sarigiannidis; S. Goudos , "Enhancing Machine Learning Models for Path Loss Prediction Using Image Texture Techniques", IEEE Antennas and Wireless Propagation Letters, (Early Access) , 2021. Journal Article Περίληψη | BibTeX | Ετικέτες: image texture, machine learning, mobile communications, pathloss prediction | Σύνδεσμοι: @article{Sotiroudis2021b, title = {Enhancing Machine Learning Models for Path Loss Prediction Using Image Texture Techniques}, author = {S. Sotiroudis and K. Siakavara and G. Koudouridis and P. Sarigiannidis and S. Goudos}, url = {https://www.researchgate.net/publication/352111245_Enhancing_Machine_Learning_Models_for_Path_Loss_Prediction_Using_Image_Texture_Techniques}, doi = {10.1109/LAWP.2021.3086180}, year = {2021}, date = {2021-06-03}, journal = {IEEE Antennas and Wireless Propagation Letters}, volume = {(Early Access)}, abstract = {The performance of machine learning-based path loss models relies heavily on the data they use at their inputs. Feature engineering is therefore essential for the models success. In the work at hand, we extract a new set of input features, based on image texture. The image that we use represents the footprint of the urban built-up area, where the gray scale values of the building blocks are analogue to their heights. We extract texture information by applying the Segmentation-based Fractal Texture Analysis algorithm on the orthogonal area that is bounded between the transmitter and the receiver. To the best of our knowledge this is the first time that such a technique is applied to a path loss modeling problem in electromagnetics. The algorithm thus delivers a new set of features, based on the images texture, which eventually reveal the built-up profile of the area. These new features are injected to an already existing feature set. Comparative analysis shows that the addition of texture-based features leads to enhanced predictions, for a diverse set of transmitter heights, machine learning algorithms, and performance metrics.}, keywords = {image texture, machine learning, mobile communications, pathloss prediction}, pubstate = {published}, tppubtype = {article} } The performance of machine learning-based path loss models relies heavily on the data they use at their inputs. Feature engineering is therefore essential for the models success. In the work at hand, we extract a new set of input features, based on image texture. The image that we use represents the footprint of the urban built-up area, where the gray scale values of the building blocks are analogue to their heights. We extract texture information by applying the Segmentation-based Fractal Texture Analysis algorithm on the orthogonal area that is bounded between the transmitter and the receiver. To the best of our knowledge this is the first time that such a technique is applied to a path loss modeling problem in electromagnetics. The algorithm thus delivers a new set of features, based on the images texture, which eventually reveal the built-up profile of the area. These new features are injected to an already existing feature set. Comparative analysis shows that the addition of texture-based features leads to enhanced predictions, for a diverse set of transmitter heights, machine learning algorithms, and performance metrics. |
Ilias Siniosoglou; Panagiotis Radoglou-Grammatikis; Georgios Efstathopoulos; Panagiotis Fouliras; Panagiotis Sarigiannidis , "A Unified Deep Learning Anomaly Detection and Classification Approach for Smart Grid Environments", {IEEE} Transactions on Network and Service Management, 1 (1), pp. 1, 2021. Journal Article Περίληψη | BibTeX | Ετικέτες: Anomaly Detection, Auto-encoder, Cybersecurity, Deep Learning, Generative Adversarial Network, machine learning, Modbus, Smart Grid | Σύνδεσμοι: @article{Siniosoglou2021b, title = {A Unified Deep Learning Anomaly Detection and Classification Approach for Smart Grid Environments}, author = {Ilias Siniosoglou and Panagiotis Radoglou-Grammatikis and Georgios Efstathopoulos and Panagiotis Fouliras and Panagiotis Sarigiannidis}, url = {https://www.researchgate.net/publication/351344684_A_Unified_Deep_Learning_Anomaly_Detection_and_Classification_Approach_for_Smart_Grid_Environments}, doi = {10.1109/TNSM.2021.3078381}, year = {2021}, date = {2021-05-07}, journal = {{IEEE} Transactions on Network and Service Management}, volume = {1}, number = {1}, pages = {1}, abstract = {The interconnected and heterogeneous nature of the next-generation Electrical Grid (EG), widely known as Smart Grid (SG), bring severe cybersecurity and privacy risks that can also raise domino effects against other Critical Infrastructures (CIs). In this paper, we present an Intrusion Detection System (IDS) specially designed for the SG environments that use Modbus/Transmission Control Protocol (TCP) and Distributed Network Protocol 3 (DNP3) protocols. The proposed IDS called MENSA (anoMaly dEtection aNd claSsificAtion) adopts a novel Autoencoder-Generative Adversarial Network (GAN) architecture for (a) detecting operational anomalies and (b) classifying Modbus/TCP and DNP3 cyberattacks. In particular, MENSA combines the aforementioned Deep Neural Networks (DNNs) in a common architecture, taking into account the adversarial loss and the reconstruction difference. The proposed IDS is validated in four real SG evaluation environments, namely (a) SG lab, (b) substation, (c) hydropower plant and (d) power plant, solving successfully an outlier detection (i.e., anomaly detection) problem as well as a challenging multiclass classification problem consisting of 14 classes (13 Modbus/TCP cyberattacks and normal instances). Furthermore, MENSA can discriminate five cyberattacks against DNP3. The evaluation results demonstrate the efficiency of MENSA compared to other Machine Learning (ML) and Deep Learning (DL) methods in terms of Accuracy, False Positive Rate (FPR), True Positive Rate (TPR) and the F1 score.}, keywords = {Anomaly Detection, Auto-encoder, Cybersecurity, Deep Learning, Generative Adversarial Network, machine learning, Modbus, Smart Grid}, pubstate = {published}, tppubtype = {article} } The interconnected and heterogeneous nature of the next-generation Electrical Grid (EG), widely known as Smart Grid (SG), bring severe cybersecurity and privacy risks that can also raise domino effects against other Critical Infrastructures (CIs). In this paper, we present an Intrusion Detection System (IDS) specially designed for the SG environments that use Modbus/Transmission Control Protocol (TCP) and Distributed Network Protocol 3 (DNP3) protocols. The proposed IDS called MENSA (anoMaly dEtection aNd claSsificAtion) adopts a novel Autoencoder-Generative Adversarial Network (GAN) architecture for (a) detecting operational anomalies and (b) classifying Modbus/TCP and DNP3 cyberattacks. In particular, MENSA combines the aforementioned Deep Neural Networks (DNNs) in a common architecture, taking into account the adversarial loss and the reconstruction difference. The proposed IDS is validated in four real SG evaluation environments, namely (a) SG lab, (b) substation, (c) hydropower plant and (d) power plant, solving successfully an outlier detection (i.e., anomaly detection) problem as well as a challenging multiclass classification problem consisting of 14 classes (13 Modbus/TCP cyberattacks and normal instances). Furthermore, MENSA can discriminate five cyberattacks against DNP3. The evaluation results demonstrate the efficiency of MENSA compared to other Machine Learning (ML) and Deep Learning (DL) methods in terms of Accuracy, False Positive Rate (FPR), True Positive Rate (TPR) and the F1 score. |
T. Kotsiopoulos; P. Sarigiannidis; D. Ioannidis; D. Tzovaras , "Machine Learning and Deep Learning in smart manufacturing: The Smart Grid paradigm", Computer Science Review, 40 , pp. 100341, 2021. Journal Article Περίληψη | BibTeX | Ετικέτες: Deep Learning, Industrial AI, Industry 4.0, machine learning, Smart Grid | Σύνδεσμοι: @article{Kotsiopoulos2021, title = {Machine Learning and Deep Learning in smart manufacturing: The Smart Grid paradigm}, author = { T. Kotsiopoulos and P. Sarigiannidis and D. Ioannidis and D. Tzovaras}, url = {https://www.researchgate.net/publication/346545781_Machine_Learning_and_Deep_Learning_in_Smart_Manufacturing_The_Smart_Grid_Paradigm}, doi = {10.1016/j.cosrev.2020.100341}, year = {2021}, date = {2021-05-01}, journal = {Computer Science Review}, volume = {40}, pages = {100341}, publisher = {Elsevier BV}, abstract = {Industry 4.0 is the new industrial revolution. By connecting every machine and activity through network sensors to the Internet, a huge amount of data is generated. Machine Learning (ML) and Deep Learning (DL) are two subsets of Artificial Intelligence (AI), which are used to evaluate the generated data and produce valuable information about the manufacturing enterprise, while introducing in parallel the Industrial AI (IAI). In this paper, the principles of the Industry 4.0 are highlighted, by giving emphasis to the features, requirements, and challenges behind Industry 4.0. In addition, a new architecture for AIA is presented. Furthermore, the most important ML and DL algorithms used in Industry 4.0 are presented and compiled in detail. Each algorithm is discussed and evaluated in terms of its features, its applications, and its efficiency. Then, we focus on one of the most important Industry 4.0 fields, namely the smart grid, where ML and DL models are presented and analyzed in terms of efficiency and effectiveness in smart grid applications. Lastly, trends and challenges in the field of data analysis in the context of the new Industrial era are highlighted and discussed such as scalability, cybersecurity, and big data.}, keywords = {Deep Learning, Industrial AI, Industry 4.0, machine learning, Smart Grid}, pubstate = {published}, tppubtype = {article} } Industry 4.0 is the new industrial revolution. By connecting every machine and activity through network sensors to the Internet, a huge amount of data is generated. Machine Learning (ML) and Deep Learning (DL) are two subsets of Artificial Intelligence (AI), which are used to evaluate the generated data and produce valuable information about the manufacturing enterprise, while introducing in parallel the Industrial AI (IAI). In this paper, the principles of the Industry 4.0 are highlighted, by giving emphasis to the features, requirements, and challenges behind Industry 4.0. In addition, a new architecture for AIA is presented. Furthermore, the most important ML and DL algorithms used in Industry 4.0 are presented and compiled in detail. Each algorithm is discussed and evaluated in terms of its features, its applications, and its efficiency. Then, we focus on one of the most important Industry 4.0 fields, namely the smart grid, where ML and DL models are presented and analyzed in terms of efficiency and effectiveness in smart grid applications. Lastly, trends and challenges in the field of data analysis in the context of the new Industrial era are highlighted and discussed such as scalability, cybersecurity, and big data. |
P. Radoglou-Grammatikis; P. Sarigiannidis; E. Iturbe; E. Rios; S. Martinez; A. Sarigiannidis; G. Eftathopoulos; I. Spyridis; A. Sesis; N. Vakakis; D. Tzovaras; E. Kafetzakis; I. Giannoulakis; M. Tzifas; A. Giannakoulias; M. Angelopoulos; F. Ramos , "SPEAR SIEM: A Security Information and Event Management system for the Smart Grid", Computer Networks, pp. 108008, 2021. Journal Article Περίληψη | BibTeX | Ετικέτες: Anomaly Detection, Cybersecurity, Deep Learning, Intrusion detection, machine learning, SCADA, Security Information and Event Management, Smart Grid | Σύνδεσμοι: @article{RadoglouGrammatikis2021, title = {SPEAR SIEM: A Security Information and Event Management system for the Smart Grid}, author = { P. Radoglou-Grammatikis and P. Sarigiannidis and E. Iturbe and E. Rios and S. Martinez and A. Sarigiannidis and G. Eftathopoulos and I. Spyridis and A. Sesis and N. Vakakis and D. Tzovaras and E. Kafetzakis and I. Giannoulakis and M. Tzifas and A. Giannakoulias and M. Angelopoulos and F. Ramos}, url = {https://www.researchgate.net/publication/350287201_SPEAR_SIEM_A_Security_Information_and_Event_Management_system_for_the_Smart_Grid}, doi = {10.1016/j.comnet.2021.108008}, year = {2021}, date = {2021-04-01}, journal = {Computer Networks}, pages = {108008}, publisher = {Elsevier BV}, abstract = {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.}, keywords = {Anomaly Detection, Cybersecurity, Deep Learning, Intrusion detection, machine learning, SCADA, Security Information and Event Management, Smart Grid}, pubstate = {published}, tppubtype = {article} } 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. |
V. Moysiadis; P. Sarigiannidis; V. Vitsas; A. Khelifi , "Smart Farming in Europe", Computer Science Review, 39 , pp. 100345, 2021. Journal Article Περίληψη | BibTeX | Ετικέτες: Μεγάλα Δεδομένα και Ευφυείς Εφαρμογές στο Διαδίκτυο των Πραγμάτων, Cloud Computing, Image Processing, machine learning, smart farming, Unmanned Aerial Vehicles (UAVs), Unmanned Ground Vehicles (UGVs), Wireless Sensor Networks (WSNs) | Σύνδεσμοι: @article{Moysiadis2021, title = {Smart Farming in Europe}, author = { V. Moysiadis and P. Sarigiannidis and V. Vitsas and A. Khelifi}, url = {https://www.researchgate.net/publication/346716261_Smart_Farming_in_Europe}, doi = {10.1016/j.cosrev.2020.100345}, year = {2021}, date = {2021-02-01}, journal = {Computer Science Review}, volume = {39}, pages = {100345}, publisher = {Elsevier BV}, abstract = {Smart Farming is the new term in the agriculture sector, aiming to transform the traditional techniques to innovative solutions based on Information Communication Technologies (ICT). Concretely, technologies like Unmanned Aerial Vehicles (UAVs), Unmanned Ground Vehicles (UGVs), Image Processing, Machine Learning, Big Data, Cloud Computing, and Wireless Sensor Networks (WSNs), are expected to bring significant changes in this area. Expected benefits are the increase in production, the decrease in cost by reducing the inputs needed such as fuel, fertilizer and pesticides, the reduction in labor efforts, and finally improvement in the quality of the final products. Such innovative methods are crucial in recent days, due to the exponential increase of the global population, the importance of producing healthier products grown with as much fewer pesticides, where public opinion of European citizens is sensitized. Moreover, due to the globalization of the world economy, European countries face the low cost of production of other low-income countries. In this vein, Europe tries to evolve its agriculture domain using technology, aiming at the sustainability of its agricultural sector. Although many surveys exist, most of them tackle in a specific scientific area of Smart Farming. An overview of Smart Farming covering all the involved technologies and providing an extensive reference of good practices around Europe is essential. Our expectation from our work is to become a good reference for researchers and help them with their future work. This paper aims to provide a comprehensive reference for European research efforts in Smart Farming and is two-fold. First, we present the research efforts from researchers in Smart Farming, who apply innovative technology trends in various crops around Europe. Second, we provide and analyze the most significant projects in Europe in the area of Smart Farming. © 2021 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.}, keywords = {Big Data, Cloud Computing, Image Processing, machine learning, smart farming, Unmanned Aerial Vehicles (UAVs), Unmanned Ground Vehicles (UGVs), Wireless Sensor Networks (WSNs)}, pubstate = {published}, tppubtype = {article} } Smart Farming is the new term in the agriculture sector, aiming to transform the traditional techniques to innovative solutions based on Information Communication Technologies (ICT). Concretely, technologies like Unmanned Aerial Vehicles (UAVs), Unmanned Ground Vehicles (UGVs), Image Processing, Machine Learning, Big Data, Cloud Computing, and Wireless Sensor Networks (WSNs), are expected to bring significant changes in this area. Expected benefits are the increase in production, the decrease in cost by reducing the inputs needed such as fuel, fertilizer and pesticides, the reduction in labor efforts, and finally improvement in the quality of the final products. Such innovative methods are crucial in recent days, due to the exponential increase of the global population, the importance of producing healthier products grown with as much fewer pesticides, where public opinion of European citizens is sensitized. Moreover, due to the globalization of the world economy, European countries face the low cost of production of other low-income countries. In this vein, Europe tries to evolve its agriculture domain using technology, aiming at the sustainability of its agricultural sector. Although many surveys exist, most of them tackle in a specific scientific area of Smart Farming. An overview of Smart Farming covering all the involved technologies and providing an extensive reference of good practices around Europe is essential. Our expectation from our work is to become a good reference for researchers and help them with their future work. This paper aims to provide a comprehensive reference for European research efforts in Smart Farming and is two-fold. First, we present the research efforts from researchers in Smart Farming, who apply innovative technology trends in various crops around Europe. Second, we provide and analyze the most significant projects in Europe in the area of Smart Farming. © 2021 Institute of Electrical and Electronics Engineers Inc.. All rights reserved. |
V. Kelli; V. Argyriou; T. Lagkas; G. Fragulis; E. Grigoriou; P. Sarigiannidis , "Ids for industrial applications: A federated learning approach with active personalization", Sensors, 21 (20), 2021, (cited By 0). Journal Article Περίληψη | BibTeX | Ετικέτες: Active learning, Critical infrastructure, Federated learning, IDS, IoT, machine learning, Personalization | Σύνδεσμοι: @article{Kelli2021b, title = {Ids for industrial applications: A federated learning approach with active personalization}, author = { V. Kelli and V. Argyriou and T. Lagkas and G. Fragulis and E. Grigoriou and P. Sarigiannidis}, url = {https://www.researchgate.net/publication/355191910_IDS_for_Industrial_Applications_A_Federated_Learning_Approach_with_Active_Personalization}, doi = {10.3390/s21206743}, year = {2021}, date = {2021-01-01}, journal = {Sensors}, volume = {21}, number = {20}, abstract = {Internet of Things (IoT) is a concept adopted in nearly every aspect of human life, leading to an explosive utilization of intelligent devices. Notably, such solutions are especially integrated in the industrial sector, to allow the remote monitoring and control of critical infrastructure. Such global integration of IoT solutions has led to an expanded attack surface against IoT-enabled infrastructures. Artificial intelligence and machine learning have demonstrated their ability to resolve issues that would have been impossible or difficult to address otherwise; thus, such solutions are closely associated with securing IoT. Classical collaborative and distributed machine learning approaches are known to compromise sensitive information. In our paper, we demonstrate the creation of a network flow-based Intrusion Detection System (IDS) aiming to protecting critical infrastructures, stemming from the pairing of two machine learning techniques, namely, federated learning and active learning. The former is utilized for privately training models in federation, while the latter is a semi-supervised approach applied for global model adaptation to each of the participant’s traffic. Experimental results indicate that global models perform significantly better for each participant, when locally personalized with just a few active learning queries. Specifically, we demonstrate how the accuracy increase can reach 7.07% in only 10 queries. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.}, note = {cited By 0}, keywords = {Active learning, Critical infrastructure, Federated learning, IDS, IoT, machine learning, Personalization}, pubstate = {published}, tppubtype = {article} } Internet of Things (IoT) is a concept adopted in nearly every aspect of human life, leading to an explosive utilization of intelligent devices. Notably, such solutions are especially integrated in the industrial sector, to allow the remote monitoring and control of critical infrastructure. Such global integration of IoT solutions has led to an expanded attack surface against IoT-enabled infrastructures. Artificial intelligence and machine learning have demonstrated their ability to resolve issues that would have been impossible or difficult to address otherwise; thus, such solutions are closely associated with securing IoT. Classical collaborative and distributed machine learning approaches are known to compromise sensitive information. In our paper, we demonstrate the creation of a network flow-based Intrusion Detection System (IDS) aiming to protecting critical infrastructures, stemming from the pairing of two machine learning techniques, namely, federated learning and active learning. The former is utilized for privately training models in federation, while the latter is a semi-supervised approach applied for global model adaptation to each of the participant’s traffic. Experimental results indicate that global models perform significantly better for each participant, when locally personalized with just a few active learning queries. Specifically, we demonstrate how the accuracy increase can reach 7.07% in only 10 queries. © 2021 by the authors. Licensee MDPI, Basel, Switzerland. |
K.-F. Kollias; C.K. Syriopoulou-Delli; P. Sarigiannidis; G.F. Fragulis , "The contribution of Machine Learning and Eye-tracking technology in Autism Spectrum Disorder research: A Review Study", 2021. Conference Περίληψη | BibTeX | Ετικέτες: ASD, ASD; Autism; Eye-tracking technology; Machine learning, Autism, Eye-tracking technology, machine learning | Σύνδεσμοι: @conference{Kollias2021, title = {The contribution of Machine Learning and Eye-tracking technology in Autism Spectrum Disorder research: A Review Study}, author = { K.-F. Kollias and C.K. Syriopoulou-Delli and P. Sarigiannidis and G.F. Fragulis}, url = {https://www.researchgate.net/publication/352737405_The_contribution_of_Machine_Learning_and_Eye-tracking_technology_in_Autism_Spectrum_Disorder_research_A_Review_Study}, doi = {10.1109/MOCAST52088.2021.9493357}, year = {2021}, date = {2021-01-01}, journal = {2021 10th International Conference on Modern Circuits and Systems Technologies, MOCAST 2021}, abstract = {According to Diagnostic and Statistical Manual of Mental Disorders, Autism spectrum disorder (ASD) is a developmental disorder characterised by reduced social interaction and communication, and by restricted, repetitive, and stereotyped behaviour. An important characteristic of autism, referred in several diagnostic tests, is a deficit in eye gaze. The objective of this study is to review the literature concerning machine learning and eye-tracking in ASD studies conducted since 2015. Our search on PubMed identified 18 studies which used various eye-tracking instruments, applied machine learning in different ways, distributed several tasks and had a wide range of sample sizes, age groups and functional skills of participants. There were also studies that utilised other instruments, such as Electroencephalography (EEG) and movement measures. Taken together, the results of these studies show that the combination of machine learning, and eye-tracking technology can contribute to autism identification characteristics by detecting the visual atypicalities of ASD people. In conclusion, machine learning and eye-tracking ASD studies could be considered a promising tool in autism research and future studies could involve other technological approaches, such as Internet of Things (IoT), as well. © 2021 IEEE.}, keywords = {ASD, ASD; Autism; Eye-tracking technology; Machine learning, Autism, Eye-tracking technology, machine learning}, pubstate = {published}, tppubtype = {conference} } According to Diagnostic and Statistical Manual of Mental Disorders, Autism spectrum disorder (ASD) is a developmental disorder characterised by reduced social interaction and communication, and by restricted, repetitive, and stereotyped behaviour. An important characteristic of autism, referred in several diagnostic tests, is a deficit in eye gaze. The objective of this study is to review the literature concerning machine learning and eye-tracking in ASD studies conducted since 2015. Our search on PubMed identified 18 studies which used various eye-tracking instruments, applied machine learning in different ways, distributed several tasks and had a wide range of sample sizes, age groups and functional skills of participants. There were also studies that utilised other instruments, such as Electroencephalography (EEG) and movement measures. Taken together, the results of these studies show that the combination of machine learning, and eye-tracking technology can contribute to autism identification characteristics by detecting the visual atypicalities of ASD people. In conclusion, machine learning and eye-tracking ASD studies could be considered a promising tool in autism research and future studies could involve other technological approaches, such as Internet of Things (IoT), as well. © 2021 IEEE. |
Διεύθυνση
Internet of Things and Applications Lab
Department of Electrical and Computer Engineering
University of Western Macedonia Campus
ZEP Area, Kozani 50100
Greece
Πληροφορίες Επικοινωνίας
tel: +30 2461 056527
Email: ithaca@uowm.gr