2024 |
|
| 182. | Christos Anagnostopoulos, Alexandros Gkillas, Christos Mavrokefalidis, Erion-Vasilis Pikoulis, Nikos Piperigkos, Aris S Lalos Multimodal Federated Learning in AIoT Systems: Existing Solutions, Applications, and Challenges Journal Article IEEE Access, 2024. @article{Anagnostopoulos2024b, title = {Multimodal Federated Learning in AIoT Systems: Existing Solutions, Applications, and Challenges}, author = {Christos Anagnostopoulos, Alexandros Gkillas, Christos Mavrokefalidis, Erion-Vasilis Pikoulis, Nikos Piperigkos, Aris S Lalos}, doi = {10.1109/ACCESS.2024.3508030}, year = {2024}, date = {2024-11-27}, journal = {IEEE Access}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
| 181. | Alexandros Gkillas, Aris S Lalos Towards Resource-Efficient Federated Learning in Industrial IoT for Multivariate Time Series Analysis Journal Article arXiv , arXiv:2411.03996 , 2024. @article{Gkillas2024, title = {Towards Resource-Efficient Federated Learning in Industrial IoT for Multivariate Time Series Analysis}, author = {Alexandros Gkillas, Aris S Lalos}, doi = {10.48550/arXiv.2411.03996}, year = {2024}, date = {2024-11-06}, journal = {arXiv }, volume = {arXiv:2411.03996}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
| 180. | Nikos Piperigkos, Alexandros Gkillas, Gerasimos Arvanitis, Stavros Nousias, Aris Lalos, Apostolos Fournaris, Panagiotis Radoglou-Grammatikis, Panagiotis Sarigiannidis, Konstantinos Moustakas Distributed intelligence in industrial and automotive cyber–physical systems: a review Journal Article Frontiers in Robotics and AI, 11 , pp. 1-37, 2024. @article{Piperigkos2024b, title = {Distributed intelligence in industrial and automotive cyber–physical systems: a review}, author = {Nikos Piperigkos, Alexandros Gkillas, Gerasimos Arvanitis, Stavros Nousias, Aris Lalos, Apostolos Fournaris, Panagiotis Radoglou-Grammatikis, Panagiotis Sarigiannidis, Konstantinos Moustakas}, doi = {10.3389/frobt.2024.1430740}, year = {2024}, date = {2024-10-28}, journal = {Frontiers in Robotics and AI}, volume = {11}, pages = {1-37}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
| 179. | Christos Anagnostopoulos, Alexandros Gkillas, Nikos Piperigkos, Aris S Lalos Personalized Federated Learning for Cross-view Geo-localization Inproceedings 2024 IEEE 26th International Workshop on Multimedia Signal Processing (MMSP), pp. 1-6, 2024. @inproceedings{Anagnostopoulos2024, title = {Personalized Federated Learning for Cross-view Geo-localization}, author = {Christos Anagnostopoulos, Alexandros Gkillas, Nikos Piperigkos, Aris S Lalos}, doi = {10.1109/MMSP61759.2024.10743630}, year = {2024}, date = {2024-10-02}, booktitle = {2024 IEEE 26th International Workshop on Multimedia Signal Processing (MMSP)}, pages = {1-6}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
| 178. | Nikos Piperigkos, Alexandros Gkillas, Christos Anagnostopoulos, Aris S Lalos Federated Data-Driven Kalman Filtering for State Estimation Inproceedings 2024 IEEE 26th International Workshop on Multimedia Signal Processing (MMSP), pp. 1-6, 2024. @inproceedings{Piperigkos2024, title = {Federated Data-Driven Kalman Filtering for State Estimation}, author = {Nikos Piperigkos, Alexandros Gkillas, Christos Anagnostopoulos, Aris S Lalos}, doi = {10.1109/MMSP61759.2024.10743751}, year = {2024}, date = {2024-10-02}, booktitle = {2024 IEEE 26th International Workshop on Multimedia Signal Processing (MMSP)}, pages = {1-6}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
| 177. | Alexandros Gkillas; Christos Anagnostopoulos; Nikos Piperigkos; Aris S Lalos A Real-time Explainable-by-design Super-Resolution Model for LiDAR SLAM Inproceedings 2024 IEEE 7th International Conference on Industrial Cyber-Physical Systems (ICPS), pp. 1-8, 2024. @inproceedings{10640037, title = {A Real-time Explainable-by-design Super-Resolution Model for LiDAR SLAM}, author = {Alexandros Gkillas and Christos Anagnostopoulos and Nikos Piperigkos and Aris S Lalos}, doi = {10.1109/ICPS59941.2024.10640037}, year = {2024}, date = {2024-01-01}, booktitle = {2024 IEEE 7th International Conference on Industrial Cyber-Physical Systems (ICPS)}, pages = {1-8}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
| 176. | Nikos Piperigkos; Alexandros Gkillas; Christos Anagnostopoulos; Aris S Lalos Cooperative Plug-and-Play-KalmanNet for 4D situational awareness in autonomous driving Inproceedings 2024 IEEE 7th International Conference on Industrial Cyber-Physical Systems (ICPS), pp. 1-6, 2024. @inproceedings{10639944, title = {Cooperative Plug-and-Play-KalmanNet for 4D situational awareness in autonomous driving}, author = {Nikos Piperigkos and Alexandros Gkillas and Christos Anagnostopoulos and Aris S Lalos}, doi = {10.1109/ICPS59941.2024.10639944}, year = {2024}, date = {2024-01-01}, booktitle = {2024 IEEE 7th International Conference on Industrial Cyber-Physical Systems (ICPS)}, pages = {1-6}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
| 175. | Nikos Piperigkos; Christos Anagnostopoulos; Aris S Lalos; Petros Kapsalas; Duong Van Nguyen Graph Laplacian Processing based multi-modal localization backend for robots and autonomous Systems Journal Article IEEE Transactions on Cognitive and Developmental Systems, pp. 1-18, 2024. @article{10695035, title = {Graph Laplacian Processing based multi-modal localization backend for robots and autonomous Systems}, author = {Nikos Piperigkos and Christos Anagnostopoulos and Aris S Lalos and Petros Kapsalas and Duong Van Nguyen}, doi = {10.1109/TCDS.2024.3468712}, year = {2024}, date = {2024-01-01}, journal = {IEEE Transactions on Cognitive and Developmental Systems}, pages = {1-18}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
2023 |
|
| 174. | Stavros Nousias; Gerasimos Arvanitis; Aris Lalos; Konstantinos Moustakas Deep Saliency Mapping for 3D Meshes and Applications Journal Article ACM Trans. Multimedia Comput. Commun. Appl., 19 (2), 2023, ISSN: 1551-6857. @article{10.1145/3550073b, title = {Deep Saliency Mapping for 3D Meshes and Applications}, author = {Stavros Nousias and Gerasimos Arvanitis and Aris Lalos and Konstantinos Moustakas}, url = {https://doi.org/10.1145/3550073}, doi = {10.1145/3550073}, issn = {1551-6857}, year = {2023}, date = {2023-02-01}, journal = {ACM Trans. Multimedia Comput. Commun. Appl.}, volume = {19}, number = {2}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, abstract = {Nowadays, three-dimensional (3D) meshes are widely used in various applications in different areas (e.g., industry, education, entertainment and safety). The 3D models are captured with multiple RGB-D sensors, and the sampled geometric manifolds are processed, compressed, simplified, stored, and transmitted to be reconstructed in a virtual space. These low-level processing applications require the accurate representation of the 3D models that can be achieved through saliency estimation mechanisms that identify specific areas of the 3D model representing surface patches of importance. Therefore, saliency maps guide the selection of feature locations facilitating the prioritization of 3D manifold segments and attributing to vertices more bits during compression or lower decimation probability during simplification, since compression and simplification are counterparts of the same process. In this work, we present a novel deep saliency mapping approach applied to 3D meshes, emphasizing decreasing the execution time of the saliency map estimation, especially when compared with the corresponding time by other relevant approaches. Our method utilizes baseline 3D importance maps to train convolutional neural networks. Furthermore, we present applications that utilize the extracted saliency, namely feature-aware multiscale compression and simplification frameworks.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Nowadays, three-dimensional (3D) meshes are widely used in various applications in different areas (e.g., industry, education, entertainment and safety). The 3D models are captured with multiple RGB-D sensors, and the sampled geometric manifolds are processed, compressed, simplified, stored, and transmitted to be reconstructed in a virtual space. These low-level processing applications require the accurate representation of the 3D models that can be achieved through saliency estimation mechanisms that identify specific areas of the 3D model representing surface patches of importance. Therefore, saliency maps guide the selection of feature locations facilitating the prioritization of 3D manifold segments and attributing to vertices more bits during compression or lower decimation probability during simplification, since compression and simplification are counterparts of the same process. In this work, we present a novel deep saliency mapping approach applied to 3D meshes, emphasizing decreasing the execution time of the saliency map estimation, especially when compared with the corresponding time by other relevant approaches. Our method utilizes baseline 3D importance maps to train convolutional neural networks. Furthermore, we present applications that utilize the extracted saliency, namely feature-aware multiscale compression and simplification frameworks. |
| 173. | N Piperigkos; A S Lalos; C Anagnostopoulos; S Z N Zukhraf; C Laoudias; M K Michael Robust Cooperative Sparse Representation Solutions for Detecting and Mitigating Spoofing Attacks in Autonomous Vehicles Inproceedings 2023 31st Mediterranean Conference on Control and Automation (MED), pp. 407-412, 2023. @inproceedings{10185772, title = {Robust Cooperative Sparse Representation Solutions for Detecting and Mitigating Spoofing Attacks in Autonomous Vehicles}, author = {N Piperigkos and A S Lalos and C Anagnostopoulos and S Z N Zukhraf and C Laoudias and M K Michael}, doi = {10.1109/MED59994.2023.10185772}, year = {2023}, date = {2023-01-01}, booktitle = {2023 31st Mediterranean Conference on Control and Automation (MED)}, pages = {407-412}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
| 172. | Alexandros Gkillas; Gerasimos Arvanitis; Aris S Lalos; Konstantinos Moustakas Federated Learning for Lidar Super Resolution on Automotive Scenes Inproceedings 2023 24th International Conference on Digital Signal Processing (DSP), pp. 1-5, 2023. @inproceedings{10167942, title = {Federated Learning for Lidar Super Resolution on Automotive Scenes}, author = {Alexandros Gkillas and Gerasimos Arvanitis and Aris S Lalos and Konstantinos Moustakas}, doi = {10.1109/DSP58604.2023.10167942}, year = {2023}, date = {2023-01-01}, booktitle = {2023 24th International Conference on Digital Signal Processing (DSP)}, pages = {1-5}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
| 171. | Christos Anagnostopoulos; Alexandros Gkillas; Nikos Piperigkos; Aris S Lalos Federated Deep Feature Extraction-based SLAM for Autonomous Vehicles Inproceedings 2023 24th International Conference on Digital Signal Processing (DSP), pp. 1-5, 2023. @inproceedings{10167897, title = {Federated Deep Feature Extraction-based SLAM for Autonomous Vehicles}, author = {Christos Anagnostopoulos and Alexandros Gkillas and Nikos Piperigkos and Aris S Lalos}, doi = {10.1109/DSP58604.2023.10167897}, year = {2023}, date = {2023-01-01}, booktitle = {2023 24th International Conference on Digital Signal Processing (DSP)}, pages = {1-5}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
| 170. | Christos Anagnostopoulos; Aris S Lalos; Petros Kapsalas; Duong Van Nguyen; Chrysostomos Stylios Reviewing Deep Learning-Based Feature Extractors in a Novel Automotive SLAM Framework Inproceedings 2023 31st Mediterranean Conference on Control and Automation (MED), pp. 107-112, 2023. @inproceedings{10185780, title = {Reviewing Deep Learning-Based Feature Extractors in a Novel Automotive SLAM Framework}, author = {Christos Anagnostopoulos and Aris S Lalos and Petros Kapsalas and Duong Van Nguyen and Chrysostomos Stylios}, doi = {10.1109/MED59994.2023.10185780}, year = {2023}, date = {2023-01-01}, booktitle = {2023 31st Mediterranean Conference on Control and Automation (MED)}, pages = {107-112}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
| 169. | Alexandros Gkillas; Aris S Lalos; Evangelos K Markakis; Ilias Politis A Federated Deep Unrolling Method for Lidar Super-resolution: Benefits in SLAM Journal Article IEEE Transactions on Intelligent Vehicles, pp. 1-17, 2023. @article{10314010, title = {A Federated Deep Unrolling Method for Lidar Super-resolution: Benefits in SLAM}, author = {Alexandros Gkillas and Aris S Lalos and Evangelos K Markakis and Ilias Politis}, doi = {10.1109/TIV.2023.3331533}, year = {2023}, date = {2023-01-01}, journal = {IEEE Transactions on Intelligent Vehicles}, pages = {1-17}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
| 168. | Nikos Piperigkos; Christos Anagnostopoulos; Aris S Lalos; Kostas Berberidis Extending Online 4D Situational Awareness in Connected and Automated Vehicles Journal Article IEEE Transactions on Intelligent Vehicles, 2023. @article{10314010b, title = {Extending Online 4D Situational Awareness in Connected and Automated Vehicles}, author = {Nikos Piperigkos and Christos Anagnostopoulos and Aris S Lalos and Kostas Berberidis}, year = {2023}, date = {2023-01-01}, journal = {IEEE Transactions on Intelligent Vehicles}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
| 167. | Alexandros Gkillas; Aris Lalos Resource Efficient Federated Learning for Deep Anomaly Detection in Industrial IoT applications Inproceedings 2023 24th International Conference on Digital Signal Processing (DSP), pp. 1-5, 2023. @inproceedings{10167873, title = {Resource Efficient Federated Learning for Deep Anomaly Detection in Industrial IoT applications}, author = {Alexandros Gkillas and Aris Lalos}, doi = {10.1109/DSP58604.2023.10167873}, year = {2023}, date = {2023-01-01}, booktitle = {2023 24th International Conference on Digital Signal Processing (DSP)}, pages = {1-5}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
| 166. | Nikos Piperigkos; Aris S Lalos; Kostas Berberidis; Christos Anagnostopoulos Cooperative Five Degrees Of Freedom Motion Estimation For A Swarm Of Autonomous Vehicles Inproceedings ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1-2, 2023. @inproceedings{10096821, title = {Cooperative Five Degrees Of Freedom Motion Estimation For A Swarm Of Autonomous Vehicles}, author = {Nikos Piperigkos and Aris S Lalos and Kostas Berberidis and Christos Anagnostopoulos}, doi = {10.1109/ICASSP49357.2023.10096821}, year = {2023}, date = {2023-01-01}, booktitle = {ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, pages = {1-2}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
| 165. | Stavros Nousias; Erion-Vasilis Pikoulis; Christos Mavrokefalidis; Aris S Lalos Accelerating Deep Neural Networks for Efficient Scene Understanding in Multi-Modal Automotive Applications Journal Article IEEE Access, 11 , pp. 28208-28221, 2023. @article{10073550, title = {Accelerating Deep Neural Networks for Efficient Scene Understanding in Multi-Modal Automotive Applications}, author = {Stavros Nousias and Erion-Vasilis Pikoulis and Christos Mavrokefalidis and Aris S Lalos}, doi = {10.1109/ACCESS.2023.3258400}, year = {2023}, date = {2023-01-01}, journal = {IEEE Access}, volume = {11}, pages = {28208-28221}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
| 164. | Christos Anagnostopoulos; Gerasimos Arvanitis; Nikos Piperigkos; Aris S Lalos; Konstantinos Moustakas A Multi-stereo Camera System for Improving Physical Ergonomics in Human-Robot Collaboration Scenarios. Journal Article ERCIM News, 2023 (132), 2023. @article{anagnostopoulos2023multi, title = {A Multi-stereo Camera System for Improving Physical Ergonomics in Human-Robot Collaboration Scenarios.}, author = {Christos Anagnostopoulos and Gerasimos Arvanitis and Nikos Piperigkos and Aris S Lalos and Konstantinos Moustakas}, year = {2023}, date = {2023-01-01}, journal = {ERCIM News}, volume = {2023}, number = {132}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
| 163. | Gerasimos Arvanitis; Nikos Piperigkos; Christos Anagnostopoulos; Aris S Lalos; Konstantinos Moustakas 2023 IEEE International Conference on Industrial Technology (ICIT), pp. 1-6, 2023. @inproceedings{10143035, title = {Real time enhancement of operator's ergonomics in physical human - robot collaboration scenarios using a multi-stereo camera system}, author = {Gerasimos Arvanitis and Nikos Piperigkos and Christos Anagnostopoulos and Aris S Lalos and Konstantinos Moustakas}, doi = {10.1109/ICIT58465.2023.10143035}, year = {2023}, date = {2023-01-01}, booktitle = {2023 IEEE International Conference on Industrial Technology (ICIT)}, pages = {1-6}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
| 162. | Georgios Mylonas; Athanasios Kalogeras; George Pavlidis; Aris Lalos; Ana García-López Digital Twins for Protecting Cultural Heritage Against Climate Change Journal Article Computer, 56 (9), pp. 100-104, 2023. @article{10224610, title = {Digital Twins for Protecting Cultural Heritage Against Climate Change}, author = {Georgios Mylonas and Athanasios Kalogeras and George Pavlidis and Aris Lalos and Ana García-López}, doi = {10.1109/MC.2023.3290687}, year = {2023}, date = {2023-01-01}, journal = {Computer}, volume = {56}, number = {9}, pages = {100-104}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
| 161. | Nikos Piperigkos; Christos Anagnostopoulos; Aris S Lalos Enabling Global Location Awareness of CAVs via Resilient Diffusion in Vehicular Ad-Hoc Networks Inproceedings 2023 IEEE 25th International Workshop on Multimedia Signal Processing (MMSP), pp. 1-1, 2023. @inproceedings{10337689, title = {Enabling Global Location Awareness of CAVs via Resilient Diffusion in Vehicular Ad-Hoc Networks}, author = {Nikos Piperigkos and Christos Anagnostopoulos and Aris S Lalos}, doi = {10.1109/MMSP59012.2023.10337689}, year = {2023}, date = {2023-01-01}, booktitle = {2023 IEEE 25th International Workshop on Multimedia Signal Processing (MMSP)}, pages = {1-1}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
| 160. | Alexandros Gkillas; Christos Anagnostopoulos; Aris S Lalos Deep Federated Unrolling for Boosting Low-Resolution Lidar-Based SLAM Solutions Inproceedings 2023 IEEE 25th International Workshop on Multimedia Signal Processing (MMSP), pp. 1-1, 2023. @inproceedings{10337642, title = {Deep Federated Unrolling for Boosting Low-Resolution Lidar-Based SLAM Solutions}, author = {Alexandros Gkillas and Christos Anagnostopoulos and Aris S Lalos}, doi = {10.1109/MMSP59012.2023.10337642}, year = {2023}, date = {2023-01-01}, booktitle = {2023 IEEE 25th International Workshop on Multimedia Signal Processing (MMSP)}, pages = {1-1}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
| 159. | Georgios Mylonas; Athanasios Kalogeras; George Pavlidis; Aris Lalos; Ana García-López Digital Twins for Protecting Cultural Heritage Against Climate Change Journal Article Computer, 56 (9), pp. 100-104, 2023. @article{10224610b, title = {Digital Twins for Protecting Cultural Heritage Against Climate Change}, author = {Georgios Mylonas and Athanasios Kalogeras and George Pavlidis and Aris Lalos and Ana García-López}, doi = {10.1109/MC.2023.3290687}, year = {2023}, date = {2023-01-01}, journal = {Computer}, volume = {56}, number = {9}, pages = {100-104}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
| 158. | Alexandros Gkillas; Aris S Lalos; Dimitris Ampeliotis An Efficient Deep Unrolling Super-Resolution Network for Lidar Automotive Scenes Inproceedings 2023 IEEE International Conference on Image Processing (ICIP), pp. 1840-1844, 2023. @inproceedings{10222856, title = {An Efficient Deep Unrolling Super-Resolution Network for Lidar Automotive Scenes}, author = {Alexandros Gkillas and Aris S Lalos and Dimitris Ampeliotis}, doi = {10.1109/ICIP49359.2023.10222856}, year = {2023}, date = {2023-01-01}, booktitle = {2023 IEEE International Conference on Image Processing (ICIP)}, pages = {1840-1844}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
2022 |
|
| 157. | Stavros Nousias; Gerasimos Arvanitis; Aris Lalos; Konstantinos Moustakas Deep Saliency Mapping for 3D Meshes and Applications Journal Article ACM Trans. Multimedia Comput. Commun. Appl., 2022, ISSN: 1551-6857, (Just Accepted). @article{10.1145/3550073, title = {Deep Saliency Mapping for 3D Meshes and Applications}, author = {Stavros Nousias and Gerasimos Arvanitis and Aris Lalos and Konstantinos Moustakas}, url = {https://doi.org/10.1145/3550073}, doi = {10.1145/3550073}, issn = {1551-6857}, year = {2022}, date = {2022-07-01}, journal = {ACM Trans. Multimedia Comput. Commun. Appl.}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, abstract = {Nowadays, 3D meshes are widely used in various applications in different areas (e.g., industry, education, entertainment and safety). 3D models are captured with multiple RGB-D sensors, and the sampled geometric manifolds are processed, compressed, simplified, stored, and transmitted to be reconstructed in a virtual space. These low-level processing applications require the accurate representation of the 3D models that can be achieved through saliency estimation mechanisms which identify specific areas of the 3D model representing surface patches of importance. Therefore, saliency maps guide the selection of feature locations facilitating the prioritization of 3D manifold segments and attributing to vertices more bits during compression or lower decimation probability during simplification since compression and simplification are counterparts of the same process. In this work, we present a novel deep saliency mapping approach applied to 3D meshes, emphasizing decreasing the execution time of the saliency map estimation, especially when compared with the corresponding time by other relevant approaches. Our method utilizes baseline 3D importance maps to train convolutional neural networks. Furthermore, we present applications that utilize the extracted saliency, namely feature-aware multiscale compression and simplification frameworks.}, note = {Just Accepted}, keywords = {}, pubstate = {published}, tppubtype = {article} } Nowadays, 3D meshes are widely used in various applications in different areas (e.g., industry, education, entertainment and safety). 3D models are captured with multiple RGB-D sensors, and the sampled geometric manifolds are processed, compressed, simplified, stored, and transmitted to be reconstructed in a virtual space. These low-level processing applications require the accurate representation of the 3D models that can be achieved through saliency estimation mechanisms which identify specific areas of the 3D model representing surface patches of importance. Therefore, saliency maps guide the selection of feature locations facilitating the prioritization of 3D manifold segments and attributing to vertices more bits during compression or lower decimation probability during simplification since compression and simplification are counterparts of the same process. In this work, we present a novel deep saliency mapping approach applied to 3D meshes, emphasizing decreasing the execution time of the saliency map estimation, especially when compared with the corresponding time by other relevant approaches. Our method utilizes baseline 3D importance maps to train convolutional neural networks. Furthermore, we present applications that utilize the extracted saliency, namely feature-aware multiscale compression and simplification frameworks. |
| 156. | Andreas Kloukiniotis; Andreas Papandreou; Christos Anagnostopoulos; Aris Lalos; Petros Kapsalas; Duong-Van Nguyen; Konstantinos Moustakas CarlaScenes: A Synthetic Dataset for Odometry in Autonomous Driving Inproceedings Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 4520-4528, 2022. @inproceedings{Kloukiniotis_2022_CVPR, title = {CarlaScenes: A Synthetic Dataset for Odometry in Autonomous Driving}, author = {Andreas Kloukiniotis and Andreas Papandreou and Christos Anagnostopoulos and Aris Lalos and Petros Kapsalas and Duong-Van Nguyen and Konstantinos Moustakas}, year = {2022}, date = {2022-06-01}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, pages = {4520-4528}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
| 155. | G. Arvanitis; S. Nousias; A S Lalos; K. Moustakas Coarse-to-fine defects detection of heritage 3D objects using a CNN learning approach Inproceedings International Conference on Industrial Cyber-Physical Systems, 2022. @inproceedings{icps2022, title = {Coarse-to-fine defects detection of heritage 3D objects using a CNN learning approach}, author = {G. Arvanitis and S. Nousias and A S Lalos and K. Moustakas}, year = {2022}, date = {2022-05-25}, booktitle = {International Conference on Industrial Cyber-Physical Systems}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
| 154. | Mohsin Kamal; Christos Kyrkou; Nikos Piperigkos; Andreas Papandreou; Andreas Kloukiniotis; Jordi Casademont; Natlia Porras Mateu; Daniel Baos Castillo; Rodrigo Diaz Rodriguez; Nicola Gregorio Durante; Peter Hofmann; Petros Kapsalas; Aris S Lalos; Konstantinos Moustakas; Christos Laoudias; Theocharis Theocharides; Georgios Ellinas A Comprehensive Solution for Securing Connected and Autonomous Vehicles Inproceedings 2022 Design, Automation & Test in Europe Conference & Exhibition (DATE), pp. 790-795, 2022, ISSN: 1558-1101. @inproceedings{9774594, title = {A Comprehensive Solution for Securing Connected and Autonomous Vehicles}, author = {Mohsin Kamal and Christos Kyrkou and Nikos Piperigkos and Andreas Papandreou and Andreas Kloukiniotis and Jordi Casademont and Natlia Porras Mateu and Daniel Baos Castillo and Rodrigo Diaz Rodriguez and Nicola Gregorio Durante and Peter Hofmann and Petros Kapsalas and Aris S Lalos and Konstantinos Moustakas and Christos Laoudias and Theocharis Theocharides and Georgios Ellinas}, doi = {10.23919/DATE54114.2022.9774594}, issn = {1558-1101}, year = {2022}, date = {2022-03-01}, booktitle = {2022 Design, Automation & Test in Europe Conference & Exhibition (DATE)}, pages = {790-795}, abstract = {With the advent of Connected and Autonomous Vehicles (CAVs) comes the very real risk that these vehicles will be exposed to cyber-attacks by exploiting various vulnerabilities. This paper gives a technical overview of the H2020 CARAMEL project (currently in the intermediate stage) in which Artificial Intelligent (AI)-based cybersecurity for CAVs is the main goal. Most of the possible scenarios are considered, by which an adversary can generate attacks on CAVs, such as attacks on camera sensors, GPS location, Vehicle to Everything (V2X) message transmission, the vehicle's On-Board Unit (OBU), etc. The counter-measures to these attacks and vulnerabilities are presented via the current results in the CARAMEL project achieved by implementing the designed security algorithms.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } With the advent of Connected and Autonomous Vehicles (CAVs) comes the very real risk that these vehicles will be exposed to cyber-attacks by exploiting various vulnerabilities. This paper gives a technical overview of the H2020 CARAMEL project (currently in the intermediate stage) in which Artificial Intelligent (AI)-based cybersecurity for CAVs is the main goal. Most of the possible scenarios are considered, by which an adversary can generate attacks on CAVs, such as attacks on camera sensors, GPS location, Vehicle to Everything (V2X) message transmission, the vehicle's On-Board Unit (OBU), etc. The counter-measures to these attacks and vulnerabilities are presented via the current results in the CARAMEL project achieved by implementing the designed security algorithms. |
| 153. | Erion Vasilis Pikoulis; Christos Mavrokefalidis; Stavros Nousias; Aris S Lalos A new clustering-based technique for the acceleration of deep convolutional networks Book Chapter Arif M Wani; Bhiksha Raj; Feng Luo; Dejing Dou (Ed.): Deep Learning Applications, Volume 3, pp. 123–150, Springer Singapore, Singapore, 2022, ISBN: 978-981-16-3357-7. @inbook{Pikoulis2022, title = {A new clustering-based technique for the acceleration of deep convolutional networks}, author = {Erion Vasilis Pikoulis and Christos Mavrokefalidis and Stavros Nousias and Aris S Lalos}, editor = {Arif M Wani and Bhiksha Raj and Feng Luo and Dejing Dou}, url = {https://doi.org/10.1007/978-981-16-3357-7_5}, doi = {10.1007/978-981-16-3357-7_5}, isbn = {978-981-16-3357-7}, year = {2022}, date = {2022-01-01}, booktitle = {Deep Learning Applications, Volume 3}, pages = {123--150}, publisher = {Springer Singapore}, address = {Singapore}, abstract = {Pikoulis, Erion VasilisMavrokefalidis, ChristosNousias, StavrosLalos, Aris S.Deep learning and especially the use of Deep Neural Networks (DNNs) provide impressive results in various regression and classification tasks. However, to achieve these results, there is a high demand for computing and storing resources. This becomes problematic when, for instance, real-time mobile applications are considered, in which the involved (embedded) devices have limited resources. A common way of addressing this problem is to transform the original large pre-trained networks into new smaller models, by utilizing Model Compression and Acceleration (MCA) techniques. Within the MCA framework, we propose a clustering-based approach that is able to increase the number of employed centroids/representatives, while, at the same time, having an acceleration gain compared to conventional, k-means-based approaches. This is achieved by imposing a special structure to the employed representatives, which is enabled by the particularities of the problem at hand. Moreover, the theoretical acceleration gains are presented and the key system hyper-parameters that affect that gain are identified. Extensive evaluation studies carried out using various state-of-the-art DNN models trained in image classification and object detection validate the effectiveness of the proposed method in MCA tasks.}, keywords = {}, pubstate = {published}, tppubtype = {inbook} } Pikoulis, Erion VasilisMavrokefalidis, ChristosNousias, StavrosLalos, Aris S.Deep learning and especially the use of Deep Neural Networks (DNNs) provide impressive results in various regression and classification tasks. However, to achieve these results, there is a high demand for computing and storing resources. This becomes problematic when, for instance, real-time mobile applications are considered, in which the involved (embedded) devices have limited resources. A common way of addressing this problem is to transform the original large pre-trained networks into new smaller models, by utilizing Model Compression and Acceleration (MCA) techniques. Within the MCA framework, we propose a clustering-based approach that is able to increase the number of employed centroids/representatives, while, at the same time, having an acceleration gain compared to conventional, k-means-based approaches. This is achieved by imposing a special structure to the employed representatives, which is enabled by the particularities of the problem at hand. Moreover, the theoretical acceleration gains are presented and the key system hyper-parameters that affect that gain are identified. Extensive evaluation studies carried out using various state-of-the-art DNN models trained in image classification and object detection validate the effectiveness of the proposed method in MCA tasks. |
| 152. | Kloukiniotis, A.; Papandreou, A.; Lalos, A.; Kapsalas, P.; Nguyen, D.-V.; Moustakas, K. Countering Adversarial Attacks on Autonomous Vehicles Using Denoising Techniques: A Review Journal Article IEEE Open Journal of Intelligent Transportation Systems, 3 , pp. 61-80, 2022. @article{9678365, title = {Countering Adversarial Attacks on Autonomous Vehicles Using Denoising Techniques: A Review}, author = {Kloukiniotis, A. and Papandreou, A. and Lalos, A. and Kapsalas, P. and Nguyen, D.-V. and Moustakas, K.}, doi = {10.1109/OJITS.2022.3142612}, year = {2022}, date = {2022-01-01}, journal = {IEEE Open Journal of Intelligent Transportation Systems}, volume = {3}, pages = {61-80}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
| 151. | Christos Anagnostopoulos; Christos Koulamas; Aris Lalos; Chrysostomos Stylios Open-Source Integrated Simulation Framework for Cooperative Autonomous Vehicles Inproceedings 2022 11th Mediterranean Conference on Embedded Computing (MECO), pp. 1-4, 2022. @inproceedings{9797115, title = {Open-Source Integrated Simulation Framework for Cooperative Autonomous Vehicles}, author = {Christos Anagnostopoulos and Christos Koulamas and Aris Lalos and Chrysostomos Stylios}, doi = {10.1109/MECO55406.2022.9797115}, year = {2022}, date = {2022-01-01}, booktitle = {2022 11th Mediterranean Conference on Embedded Computing (MECO)}, pages = {1-4}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
| 150. | Nikos Piperigkos; Stavros Nousias; Aris S Lalos Robust 4D awareness via diffusion adaptation over Connected and Autonomated vehicles Inproceedings 2022 IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP), pp. 1-5, 2022. @inproceedings{9816204, title = {Robust 4D awareness via diffusion adaptation over Connected and Autonomated vehicles}, author = {Nikos Piperigkos and Stavros Nousias and Aris S Lalos}, doi = {10.1109/IVMSP54334.2022.9816204}, year = {2022}, date = {2022-01-01}, booktitle = {2022 IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP)}, pages = {1-5}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
| 149. | Nikos Piperigkos; Aris S Lalos; Kostas Berberidis Alternating optimization for multimodal collaborating odometry estimation in CAVs Inproceedings 2022 30th Mediterranean Conference on Control and Automation (MED), pp. 670-675, 2022. @inproceedings{9837156, title = {Alternating optimization for multimodal collaborating odometry estimation in CAVs}, author = {Nikos Piperigkos and Aris S Lalos and Kostas Berberidis}, doi = {10.1109/MED54222.2022.9837156}, year = {2022}, date = {2022-01-01}, booktitle = {2022 30th Mediterranean Conference on Control and Automation (MED)}, pages = {670-675}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
| 148. | Alexandros Gkillas; Aris S Lalos Missing Data Imputation for Multivariate Time series in Industrial IoT: A Federated Learning Approach Inproceedings 2022 IEEE 20th International Conference on Industrial Informatics (INDIN), pp. 87-94, 2022. @inproceedings{9976093, title = {Missing Data Imputation for Multivariate Time series in Industrial IoT: A Federated Learning Approach}, author = {Alexandros Gkillas and Aris S Lalos}, doi = {10.1109/INDIN51773.2022.9976093}, year = {2022}, date = {2022-01-01}, booktitle = {2022 IEEE 20th International Conference on Industrial Informatics (INDIN)}, pages = {87-94}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
2021 |
|
| 147. | Andreas Papandreou; Andreas Kloukiniotis; Aris Lalos; Konstantinos Moustakas Deep multi-modal data analysis and fusion for robust scene understanding in CAVs Inproceedings 2021 IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP), pp. 1-6, 2021, ISSN: 2473-3628. @inproceedings{9733604, title = {Deep multi-modal data analysis and fusion for robust scene understanding in CAVs}, author = {Andreas Papandreou and Andreas Kloukiniotis and Aris Lalos and Konstantinos Moustakas}, doi = {10.1109/MMSP53017.2021.9733604}, issn = {2473-3628}, year = {2021}, date = {2021-10-01}, booktitle = {2021 IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP)}, pages = {1-6}, abstract = {Deep learning (DL) tends to be the integral part of Autonomous Vehicles (AVs). Therefore the development of scene analysis modules that are robust to various vulnerabilities such as adversarial inputs or cyber-attacks is becoming an imperative need for the future AV perception systems. In this paper, we deal with this issue by exploring the recent progress in Artificial Intelligence (AI) and Machine Learning (ML) to provide holistic situational awareness and eliminate the effect of the previous attacks on the scene analysis modules. We propose novel multi-modal approaches against which achieve robustness to adversarial attacks, by appropriately modifying the analysis Neural networks and by utilizing late fusion methods. More specifically, we propose a holistic approach by adding new layers to a 2D segmentation DL model enhancing its robustness to adversarial noise. Then, a novel late fusion technique has been applied, by extracting direct features from the 3D space and project them into the 2D segmented space for identifying inconsistencies. Extensive evaluation studies using the KITTI odometry dataset provide promising performance results under various types of noise.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Deep learning (DL) tends to be the integral part of Autonomous Vehicles (AVs). Therefore the development of scene analysis modules that are robust to various vulnerabilities such as adversarial inputs or cyber-attacks is becoming an imperative need for the future AV perception systems. In this paper, we deal with this issue by exploring the recent progress in Artificial Intelligence (AI) and Machine Learning (ML) to provide holistic situational awareness and eliminate the effect of the previous attacks on the scene analysis modules. We propose novel multi-modal approaches against which achieve robustness to adversarial attacks, by appropriately modifying the analysis Neural networks and by utilizing late fusion methods. More specifically, we propose a holistic approach by adding new layers to a 2D segmentation DL model enhancing its robustness to adversarial noise. Then, a novel late fusion technique has been applied, by extracting direct features from the 3D space and project them into the 2D segmented space for identifying inconsistencies. Extensive evaluation studies using the KITTI odometry dataset provide promising performance results under various types of noise. |
| 146. | Nikos Piperigkos; Aris S Lalos Impact of False Data Injection attacks on Decentralized Electric Vehicle Charging Protocols Journal Article Transportation Research Procedia, 52 , pp. 331–338, 2021, ISSN: 23521465. @article{piperigkos2021impact, title = {Impact of False Data Injection attacks on Decentralized Electric Vehicle Charging Protocols}, author = {Nikos Piperigkos and Aris S Lalos}, doi = {10.1016/j.trpro.2021.01.039}, issn = {23521465}, year = {2021}, date = {2021-01-01}, journal = {Transportation Research Procedia}, volume = {52}, pages = {331--338}, publisher = {Elsevier}, abstract = {Electric vehicles (EVs) gain great attention nowadays since the electrification of private and public transport has a great potential to reduce greenhouse gas emissions and mitigate oil dependency. However, the influx of a large number of electrical loads without any coordination could have adverse affects to the electrical grid. More importantly, the complexity in the coordination of a large number of EVs, pose critical challenges in ensuring overall system integrity. A typical attack found in the controllers of connected EVs is false data injection (FDI), which can be utilized to distort real energy demand and supply figures. Energy distribution requests may therefore be erroneous, which results in additional costs or more devastating hazards. The lack of a proper coordination scheme, robust to such cyber attacks could cause voltage magnitude drops and unacceptable load peaks. In this work, we study the impact of FDI attacks, on various decentralized charging protocols with reduced computational requirements. The proposed decentralized EV charging algorithms only require from each EV to solve a local problem, hence the proposed implementation require low computational resources. An extensive evaluation study highlights the strengths and weaknesses of the presented solutions which are based on iterative convex optimization solvers.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Electric vehicles (EVs) gain great attention nowadays since the electrification of private and public transport has a great potential to reduce greenhouse gas emissions and mitigate oil dependency. However, the influx of a large number of electrical loads without any coordination could have adverse affects to the electrical grid. More importantly, the complexity in the coordination of a large number of EVs, pose critical challenges in ensuring overall system integrity. A typical attack found in the controllers of connected EVs is false data injection (FDI), which can be utilized to distort real energy demand and supply figures. Energy distribution requests may therefore be erroneous, which results in additional costs or more devastating hazards. The lack of a proper coordination scheme, robust to such cyber attacks could cause voltage magnitude drops and unacceptable load peaks. In this work, we study the impact of FDI attacks, on various decentralized charging protocols with reduced computational requirements. The proposed decentralized EV charging algorithms only require from each EV to solve a local problem, hence the proposed implementation require low computational resources. An extensive evaluation study highlights the strengths and weaknesses of the presented solutions which are based on iterative convex optimization solvers. |
| 145. | Kostas Blekos; Anastasios Tsakas; Christos Xouris; Ioannis Evdokidis; Dimitris Alexandropoulos; Christos Alexakos; Sofoklis Katakis; Andreas Makedonas; Christos Theoharatos; Aris Lalos Analysis, modeling and multi-spectral sensing for the predictive management of verticillium wilt in olive groves Journal Article Journal of Sensor and Actuator Networks, 10 (1), pp. 15, 2021, ISSN: 22242708. @article{blekos2021analysis, title = {Analysis, modeling and multi-spectral sensing for the predictive management of verticillium wilt in olive groves}, author = {Kostas Blekos and Anastasios Tsakas and Christos Xouris and Ioannis Evdokidis and Dimitris Alexandropoulos and Christos Alexakos and Sofoklis Katakis and Andreas Makedonas and Christos Theoharatos and Aris Lalos}, url = {https://drive.google.com/file/d/1Hdhu6T9-ryKo9Kz54W2qUvmZINE7054X/view?usp=sharing}, doi = {10.3390/jsan10010015}, issn = {22242708}, year = {2021}, date = {2021-01-01}, journal = {Journal of Sensor and Actuator Networks}, volume = {10}, number = {1}, pages = {15}, publisher = {Multidisciplinary Digital Publishing Institute}, abstract = {The intensification and expansion in the cultivation of olives have contributed to the significant spread of Verticillium wilt, which is the most important fungal problem affecting olive trees. Recent studies confirm that practices such as the use of innovative natural minerals (Zeoshell ZF1) and the application of beneficial microorganisms (Micosat F BS WP) restore health in infected trees. However, for their efficient implementation the above methodologies require the marking of trees in the early stages of infestation—a task that is impractical with traditional means (manual labor) but also very difficult, as early stages are difficult to perceive with the naked eye. In this paper, we present the results of the My Olive Grove Coach (MyOGC) project, which used multispectral imaging from unmanned aerial vehicles to develop an olive grove monitoring system based on the autonomous and automatic processing of the multispectral images using computer vision and machine learning techniques. The goal of the system is to monitor and assess the health of olive groves, help in the prediction of Verticillium wilt spread and implement a decision support system that guides the farmer/agronomist.}, keywords = {}, pubstate = {published}, tppubtype = {article} } The intensification and expansion in the cultivation of olives have contributed to the significant spread of Verticillium wilt, which is the most important fungal problem affecting olive trees. Recent studies confirm that practices such as the use of innovative natural minerals (Zeoshell ZF1) and the application of beneficial microorganisms (Micosat F BS WP) restore health in infected trees. However, for their efficient implementation the above methodologies require the marking of trees in the early stages of infestation—a task that is impractical with traditional means (manual labor) but also very difficult, as early stages are difficult to perceive with the naked eye. In this paper, we present the results of the My Olive Grove Coach (MyOGC) project, which used multispectral imaging from unmanned aerial vehicles to develop an olive grove monitoring system based on the autonomous and automatic processing of the multispectral images using computer vision and machine learning techniques. The goal of the system is to monitor and assess the health of olive groves, help in the prediction of Verticillium wilt spread and implement a decision support system that guides the farmer/agronomist. |
| 144. | Petros Kapsalas; Aris S Lalos; Konstantinos Moustakas; DImitrios Serpanos The Role of Modularity in Multimodal Simultaneous Localization and Mapping Systems Journal Article Computer, 54 (3), pp. 63–67, 2021, ISSN: 15580814. @article{kapsalas2021role, title = {The Role of Modularity in Multimodal Simultaneous Localization and Mapping Systems}, author = {Petros Kapsalas and Aris S Lalos and Konstantinos Moustakas and DImitrios Serpanos}, doi = {10.1109/MC.2021.3049889}, issn = {15580814}, year = {2021}, date = {2021-01-01}, journal = {Computer}, volume = {54}, number = {3}, pages = {63--67}, publisher = {IEEE}, abstract = {Simultaneous localization and mapping (SLAM) refers to the problem of mapping an environment using measurements from mobile sensors while simultaneously estimating the motion of those sensors relative to the map Modular architectures are required to enable the commoditization and fast penetration of SLAMs in the emerging mobile computing systems.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Simultaneous localization and mapping (SLAM) refers to the problem of mapping an environment using measurements from mobile sensors while simultaneously estimating the motion of those sensors relative to the map Modular architectures are required to enable the commoditization and fast penetration of SLAMs in the emerging mobile computing systems. |
| 143. | Christian Vitale; Nikos Piperigkos; Christos Laoudias; Georgios Ellinas; Jordi Casademont; Josep Escrig; Andreas Kloukiniotis; Aris S Lalos; Konstantinos Moustakas; Rodrigo Diaz Rodriguez; Daniel Baños; Gemma Roqueta Crusats; Petros Kapsalas; Klaus Peter Hofmann; Pouria Sayyad Khodashenas CARAMEL: results on a secure architecture for connected and autonomous vehicles detecting GPS spoofing attacks Journal Article Eurasip Journal on Wireless Communications and Networking, 2021 (1), pp. 1–28, 2021, ISSN: 16871499. @article{vitale2021caramel, title = {CARAMEL: results on a secure architecture for connected and autonomous vehicles detecting GPS spoofing attacks}, author = {Christian Vitale and Nikos Piperigkos and Christos Laoudias and Georgios Ellinas and Jordi Casademont and Josep Escrig and Andreas Kloukiniotis and Aris S Lalos and Konstantinos Moustakas and Rodrigo {Diaz Rodriguez} and Daniel Ba{ñ}os and Gemma {Roqueta Crusats} and Petros Kapsalas and Klaus Peter Hofmann and Pouria Sayyad Khodashenas}, url = {https://drive.google.com/file/d/1O1pMk79cYeb-Y8aaAOqlFwb-otteyLde/view?usp=sharing}, doi = {10.1186/s13638-021-01971-x}, issn = {16871499}, year = {2021}, date = {2021-01-01}, journal = {Eurasip Journal on Wireless Communications and Networking}, volume = {2021}, number = {1}, pages = {1--28}, publisher = {SpringerOpen}, abstract = {The main goal of the H2020-CARAMEL project is to address the cybersecurity gaps introduced by the new technological domains adopted by modern vehicles applying, among others, advanced Artificial Intelligence and Machine Learning techniques. As a result, CARAMEL enhances the protection against threats related to automated driving, smart charging of Electric Vehicles, and communication among vehicles or between vehicles and the roadside infrastructure. This work focuses on the latter and presents the CARAMEL architecture aiming at assessing the integrity of the information transmitted by vehicles, as well as at improving the security and privacy of communication for connected and autonomous driving. The proposed architecture includes: (1) multi-radio access technology capabilities, with simultaneous 802.11p and LTE-Uu support, enabled by the connectivity infrastructure; (2) a MEC platform, where, among others, algorithms for detecting attacks are implemented; (3) an intelligent On-Board Unit with anti-hacking features inside the vehicle; (4) a Public Key Infrastructure that validates in real-time the integrity of vehicle's data transmissions. As an indicative application, the interaction between the entities of the CARAMEL architecture is showcased in case of a GPS spoofing attack scenario. Adopted attack detection techniques exploit robust in-vehicle and cooperative approaches that do not rely on encrypted GPS signals, but only on measurements available in the CARAMEL architecture.}, keywords = {}, pubstate = {published}, tppubtype = {article} } The main goal of the H2020-CARAMEL project is to address the cybersecurity gaps introduced by the new technological domains adopted by modern vehicles applying, among others, advanced Artificial Intelligence and Machine Learning techniques. As a result, CARAMEL enhances the protection against threats related to automated driving, smart charging of Electric Vehicles, and communication among vehicles or between vehicles and the roadside infrastructure. This work focuses on the latter and presents the CARAMEL architecture aiming at assessing the integrity of the information transmitted by vehicles, as well as at improving the security and privacy of communication for connected and autonomous driving. The proposed architecture includes: (1) multi-radio access technology capabilities, with simultaneous 802.11p and LTE-Uu support, enabled by the connectivity infrastructure; (2) a MEC platform, where, among others, algorithms for detecting attacks are implemented; (3) an intelligent On-Board Unit with anti-hacking features inside the vehicle; (4) a Public Key Infrastructure that validates in real-time the integrity of vehicle's data transmissions. As an indicative application, the interaction between the entities of the CARAMEL architecture is showcased in case of a GPS spoofing attack scenario. Adopted attack detection techniques exploit robust in-vehicle and cooperative approaches that do not rely on encrypted GPS signals, but only on measurements available in the CARAMEL architecture. |
| 142. | Stavros Nousias; Erion Vasilis Pikoulis; Christos Mavrokefalidis; Aris S Lalos Accelerating deep neural networks for efficient scene understanding in automotive cyber-physical systems Inproceedings Proceedings - 2021 4th IEEE International Conference on Industrial Cyber-Physical Systems, ICPS 2021, pp. 63–69, IEEE 2021, ISBN: 9781728162072. @inproceedings{nousias2021accelerating, title = {Accelerating deep neural networks for efficient scene understanding in automotive cyber-physical systems}, author = {Stavros Nousias and Erion Vasilis Pikoulis and Christos Mavrokefalidis and Aris S Lalos}, url = {https://drive.google.com/file/d/1BjNrSNGNvqrXykm1g3Fh6pYQjeWEKOzx/view?usp=sharing}, doi = {10.1109/ICPS49255.2021.9468126}, isbn = {9781728162072}, year = {2021}, date = {2021-01-01}, booktitle = {Proceedings - 2021 4th IEEE International Conference on Industrial Cyber-Physical Systems, ICPS 2021}, pages = {63--69}, organization = {IEEE}, abstract = {Automotive Cyber-Physical Systems (ACPS) have attracted a significant amount of interest in the past few decades, while one of the most critical operations in these systems is the perception of the environment. Deep learning and, especially, the use of Deep Neural Networks (DNNs) provides impressive results in analyzing and understanding complex and dynamic scenes from visual data. The prediction horizons for those perception systems are very short and inference must often be performed in real time, stressing the need of transforming the original large pre-trained networks into new smaller models, by utilizing Model Compression and Acceleration (MCA) techniques. Our goal in this work is to investigate best practices for appropriately applying novel weight sharing techniques, optimizing the available variables and the training procedures towards the significant acceleration of widely adopted DNNs. Extensive evaluation studies carried out using various state-of-the-art DNN models in object detection and tracking experiments, provide details about the type of errors that manifest after the application of weight sharing techniques, resulting in significant acceleration gains with negligible accuracy losses.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Automotive Cyber-Physical Systems (ACPS) have attracted a significant amount of interest in the past few decades, while one of the most critical operations in these systems is the perception of the environment. Deep learning and, especially, the use of Deep Neural Networks (DNNs) provides impressive results in analyzing and understanding complex and dynamic scenes from visual data. The prediction horizons for those perception systems are very short and inference must often be performed in real time, stressing the need of transforming the original large pre-trained networks into new smaller models, by utilizing Model Compression and Acceleration (MCA) techniques. Our goal in this work is to investigate best practices for appropriately applying novel weight sharing techniques, optimizing the available variables and the training procedures towards the significant acceleration of widely adopted DNNs. Extensive evaluation studies carried out using various state-of-the-art DNN models in object detection and tracking experiments, provide details about the type of errors that manifest after the application of weight sharing techniques, resulting in significant acceleration gains with negligible accuracy losses. |
| 141. | Nikos Piperigkos; Aris S Lalos; Kostas Berberidis Graph Laplacian extended Kalman filter for connected and automated vehicles localization Inproceedings Proceedings - 2021 4th IEEE International Conference on Industrial Cyber-Physical Systems, ICPS 2021, pp. 328–333, IEEE 2021, ISBN: 9781728162072. @inproceedings{piperigkos2021graph, title = {Graph Laplacian extended Kalman filter for connected and automated vehicles localization}, author = {Nikos Piperigkos and Aris S Lalos and Kostas Berberidis}, doi = {10.1109/ICPS49255.2021.9468263}, isbn = {9781728162072}, year = {2021}, date = {2021-01-01}, booktitle = {Proceedings - 2021 4th IEEE International Conference on Industrial Cyber-Physical Systems, ICPS 2021}, pages = {328--333}, organization = {IEEE}, abstract = {Extended Kalman Filters have been widely applied for tracking the location of moving semi-autonomous vehicles. The latter are equipped with a multitude of sensors generating multi-modal data, while at the same time they are capable of cooperating via Vehicle-to-Vehicle communication technologies. In this paper, we have formulated a cooperative tracking scheme based on Extended Kalman Filter, in order to cope with erroneous GPS location information. It performs multi-modal fusion in a centralized and distributed manner, assuming the existence of an overall fusion center or local interaction among neighbouring and connected vehicles only. It features the property of encoding in a linear form the different measurement modalities, including range and GPS measurements, exploiting the connectivity topology of cooperating vehicles, using the graph Laplacian operator. The extended experimental evaluation using realistic vehicle trajectories extracted by CARLA autonomous driving simulator, verify the significant reduction of GPS error under various realistic conditions. Moreover, both schemes outperform existing cooperative localization methods. Finally, the distributed tracking approach exhibits similar performance and in specific cases outperforms the centralized counterpart.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Extended Kalman Filters have been widely applied for tracking the location of moving semi-autonomous vehicles. The latter are equipped with a multitude of sensors generating multi-modal data, while at the same time they are capable of cooperating via Vehicle-to-Vehicle communication technologies. In this paper, we have formulated a cooperative tracking scheme based on Extended Kalman Filter, in order to cope with erroneous GPS location information. It performs multi-modal fusion in a centralized and distributed manner, assuming the existence of an overall fusion center or local interaction among neighbouring and connected vehicles only. It features the property of encoding in a linear form the different measurement modalities, including range and GPS measurements, exploiting the connectivity topology of cooperating vehicles, using the graph Laplacian operator. The extended experimental evaluation using realistic vehicle trajectories extracted by CARLA autonomous driving simulator, verify the significant reduction of GPS error under various realistic conditions. Moreover, both schemes outperform existing cooperative localization methods. Finally, the distributed tracking approach exhibits similar performance and in specific cases outperforms the centralized counterpart. |
| 140. | Stavros Nousias; Nikos Piperigkos; Gerasimos Arvanitis; Apostolos Fournaris; Aris S Lalos; Konstantinos Moustakas Empowering cyberphysical systems of systems with intelligence Journal Article arXiv preprint arXiv:2107.02264, 2021. @article{nousias2021empowering, title = {Empowering cyberphysical systems of systems with intelligence}, author = {Stavros Nousias and Nikos Piperigkos and Gerasimos Arvanitis and Apostolos Fournaris and Aris S Lalos and Konstantinos Moustakas}, url = {http://arxiv.org/abs/2107.02264}, year = {2021}, date = {2021-01-01}, journal = {arXiv preprint arXiv:2107.02264}, abstract = {Cyber Physical Systems have been going into a transition phase from individual systems to a collecttives of systems that collaborate in order to achieve a highly complex cause, realizing a system of systems approach. The automotive domain has been making a transition to the system of system approach aiming to provide a series of emergent functionality like traffic management, collaborative car fleet management or large-scale automotive adaptation to physical environment thus providing significant environmental benefits (e.g air pollution reduction) and achieving significant societal impact. Similarly, large infrastructure domains, are evolving into global, highly integrated cyber-physical systems of systems covering all parts of the value chain. In practice, there are significant challenges in CPSoS applicability and usability to be addressed, i.e. even a small CPSoS such as a car consists several subsystems Decentralization of CPSoS appoints tasks to individual CPSs within the System of Systems. CPSoSs are heterogenous systems. They comprise of various, autonomous, CPSs, each one of them having unique performance capabilities, criticality level, priorities and pursued goals. all CPSs must also harmonically pursue system-based achievements and collaborate in order to make system-of-system based decisions and implement the CPSoS functionality. This survey will provide a comprehensive review on current best practices in connected cyberphysical systems. The basis of our investigation is a dual layer architecture encompassing a perception layer and a behavioral layer. Perception algorithms with respect to scene understanding (object detection and tracking, pose estimation), localization mapping and path planning are thoroughly investigated. Behavioural part focuses on decision making and human in the loop control.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Cyber Physical Systems have been going into a transition phase from individual systems to a collecttives of systems that collaborate in order to achieve a highly complex cause, realizing a system of systems approach. The automotive domain has been making a transition to the system of system approach aiming to provide a series of emergent functionality like traffic management, collaborative car fleet management or large-scale automotive adaptation to physical environment thus providing significant environmental benefits (e.g air pollution reduction) and achieving significant societal impact. Similarly, large infrastructure domains, are evolving into global, highly integrated cyber-physical systems of systems covering all parts of the value chain. In practice, there are significant challenges in CPSoS applicability and usability to be addressed, i.e. even a small CPSoS such as a car consists several subsystems Decentralization of CPSoS appoints tasks to individual CPSs within the System of Systems. CPSoSs are heterogenous systems. They comprise of various, autonomous, CPSs, each one of them having unique performance capabilities, criticality level, priorities and pursued goals. all CPSs must also harmonically pursue system-based achievements and collaborate in order to make system-of-system based decisions and implement the CPSoS functionality. This survey will provide a comprehensive review on current best practices in connected cyberphysical systems. The basis of our investigation is a dual layer architecture encompassing a perception layer and a behavioral layer. Perception algorithms with respect to scene understanding (object detection and tracking, pose estimation), localization mapping and path planning are thoroughly investigated. Behavioural part focuses on decision making and human in the loop control. |
| 139. | Nikos Piperigkos; Aris S Lalos; Senior Member; Kostas Berberidis; Senior Member Graph Laplacian Diffusion Localization of Connected and Automated Vehicles Journal Article Intelligent Transportation Systems (ITSC), (Cll), pp. 1–14, 2021. @article{piperigkos2021graphb, title = {Graph Laplacian Diffusion Localization of Connected and Automated Vehicles}, author = {Nikos Piperigkos and Aris S Lalos and Senior Member and Kostas Berberidis and Senior Member}, year = {2021}, date = {2021-01-01}, journal = {Intelligent Transportation Systems (ITSC)}, number = {Cll}, pages = {1--14}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
| 138. | Gerasimos Arvanitis; Aris S Lalos; Konstantinos Moustakas Robust and Fast 3-D Saliency Mapping for Industrial Modeling Applications Journal Article IEEE Transactions on Industrial Informatics, 17 (2), pp. 1307–1317, 2021, ISSN: 19410050. @article{Arvanitis2021, title = {Robust and Fast 3-D Saliency Mapping for Industrial Modeling Applications}, author = {Gerasimos Arvanitis and Aris S Lalos and Konstantinos Moustakas}, doi = {10.1109/TII.2020.3003455}, issn = {19410050}, year = {2021}, date = {2021-01-01}, journal = {IEEE Transactions on Industrial Informatics}, volume = {17}, number = {2}, pages = {1307--1317}, abstract = {New generation 3-D scanning technologies are expected to create a revolution at the Industry 4.0, facilitating a large number of virtual manufacturing tools and systems. Such applications require the accurate representation of physical objects and/or systems achieved through saliency estimation mechanisms that identify certain areas of the 3-D model, leading to a meaningful and easier to analyze representation of a 3-D object. 3-D saliency mapping is, therefore, guiding the selection of feature locations and is adopted in a large number of low-level 3-D processing applications including denoising, compression, simplification, and registration. In this article, we propose a robust and fast method for creating 3-D saliency maps that accurately identifies sharp and small-scale geometric features in various industrial 3-D models. An extensive experimental study using a large number of 3-D scanned and CAD models verifies the effectiveness of the proposed method as compared to other recent and relevant approaches despite the constraints posed by complex geometry patterns or the presence of noise.}, keywords = {}, pubstate = {published}, tppubtype = {article} } New generation 3-D scanning technologies are expected to create a revolution at the Industry 4.0, facilitating a large number of virtual manufacturing tools and systems. Such applications require the accurate representation of physical objects and/or systems achieved through saliency estimation mechanisms that identify certain areas of the 3-D model, leading to a meaningful and easier to analyze representation of a 3-D object. 3-D saliency mapping is, therefore, guiding the selection of feature locations and is adopted in a large number of low-level 3-D processing applications including denoising, compression, simplification, and registration. In this article, we propose a robust and fast method for creating 3-D saliency maps that accurately identifies sharp and small-scale geometric features in various industrial 3-D models. An extensive experimental study using a large number of 3-D scanned and CAD models verifies the effectiveness of the proposed method as compared to other recent and relevant approaches despite the constraints posed by complex geometry patterns or the presence of noise. |
| 137. | Nikos Piperigkos; Aris S Lalos; Kostas Berberidis Multi-modal cooperative awareness of connected and automated vehicles in smart cities Inproceedings 2021 IEEE International Conference on Smart Internet of Things (SmartIoT), pp. 377-382, 2021. @inproceedings{9556210, title = {Multi-modal cooperative awareness of connected and automated vehicles in smart cities}, author = {Nikos Piperigkos and Aris S Lalos and Kostas Berberidis}, doi = {10.1109/SmartIoT52359.2021.00070}, year = {2021}, date = {2021-01-01}, booktitle = {2021 IEEE International Conference on Smart Internet of Things (SmartIoT)}, pages = {377-382}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
| 136. | Gerasimos Arvanitis; Aris S Lalos; Konstantinos Moustakas Fast Spatio-temporal Compression of Dynamic 3D Meshes Newsletter 2021. @misc{arvanitis2021fast, title = {Fast Spatio-temporal Compression of Dynamic 3D Meshes}, author = {Gerasimos Arvanitis and Aris S Lalos and Konstantinos Moustakas}, url = {https://arxiv.org/ftp/arxiv/papers/2111/2111.10105.pdf}, year = {2021}, date = {2021-01-01}, keywords = {}, pubstate = {published}, tppubtype = {misc} } |
| 135. | Christian Vitale; Piperigkos Nikos; Laoudias Christos; Ellinas Georgios; Casademont Jordi; Escrig Josep; Kloukiniotis Andreas; Aris S Lalos; Moustakas Konstantinos; Rodriguez R Diaz; Daniel Baños; Roqueta C Gemma; Kapsalas Petros; Klaus-Peter Hofmann; Pouria S Khodashenas CARAMEL: results on a secure architecture for connected and autonomous vehicles detecting GPS spoofing attacks Journal Article EURASIP Journal on Wireless Communications and Networking, 2021 (1), 2021, ISBN: 16871472, (Copyright - © The Author(s) 2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License; Last updated - 2021-05-05). @article{, title = {CARAMEL: results on a secure architecture for connected and autonomous vehicles detecting GPS spoofing attacks}, author = {Christian Vitale and Piperigkos Nikos and Laoudias Christos and Ellinas Georgios and Casademont Jordi and Escrig Josep and Kloukiniotis Andreas and Aris S Lalos and Moustakas Konstantinos and Rodriguez R Diaz and Daniel Baños and Roqueta C Gemma and Kapsalas Petros and Klaus-Peter Hofmann and Pouria S Khodashenas}, url = {https://www.proquest.com/scholarly-journals/caramel-results-on-secure-architecture-connected/docview/2521815903/se-2}, isbn = {16871472}, year = {2021}, date = {2021-01-01}, journal = {EURASIP Journal on Wireless Communications and Networking}, volume = {2021}, number = {1}, abstract = {The main goal of the H2020-CARAMEL project is to address the cybersecurity gaps introduced by the new technological domains adopted by modern vehicles applying, among others, advanced Artificial Intelligence and Machine Learning techniques. As a result, CARAMEL enhances the protection against threats related to automated driving, smart charging of Electric Vehicles, and communication among vehicles or between vehicles and the roadside infrastructure. This work focuses on the latter and presents the CARAMEL architecture aiming at assessing the integrity of the information transmitted by vehicles, as well as at improving the security and privacy of communication for connected and autonomous driving. The proposed architecture includes: (1) multi-radio access technology capabilities, with simultaneous 802.11p and LTE-Uu support, enabled by the connectivity infrastructure; (2) a MEC platform, where, among others, algorithms for detecting attacks are implemented; (3) an intelligent On-Board Unit with anti-hacking features inside the vehicle; (4) a Public Key Infrastructure that validates in real-time the integrity of vehicle’s data transmissions. As an indicative application, the interaction between the entities of the CARAMEL architecture is showcased in case of a GPS spoofing attack scenario. Adopted attack detection techniques exploit robust in-vehicle and cooperative approaches that do not rely on encrypted GPS signals, but only on measurements available in the CARAMEL architecture.}, note = {Copyright - © The Author(s) 2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License; Last updated - 2021-05-05}, keywords = {}, pubstate = {published}, tppubtype = {article} } The main goal of the H2020-CARAMEL project is to address the cybersecurity gaps introduced by the new technological domains adopted by modern vehicles applying, among others, advanced Artificial Intelligence and Machine Learning techniques. As a result, CARAMEL enhances the protection against threats related to automated driving, smart charging of Electric Vehicles, and communication among vehicles or between vehicles and the roadside infrastructure. This work focuses on the latter and presents the CARAMEL architecture aiming at assessing the integrity of the information transmitted by vehicles, as well as at improving the security and privacy of communication for connected and autonomous driving. The proposed architecture includes: (1) multi-radio access technology capabilities, with simultaneous 802.11p and LTE-Uu support, enabled by the connectivity infrastructure; (2) a MEC platform, where, among others, algorithms for detecting attacks are implemented; (3) an intelligent On-Board Unit with anti-hacking features inside the vehicle; (4) a Public Key Infrastructure that validates in real-time the integrity of vehicle’s data transmissions. As an indicative application, the interaction between the entities of the CARAMEL architecture is showcased in case of a GPS spoofing attack scenario. Adopted attack detection techniques exploit robust in-vehicle and cooperative approaches that do not rely on encrypted GPS signals, but only on measurements available in the CARAMEL architecture. |
| 134. | Stavros Nousias; Erion-Vasilis Pikoulis; Christos Mavrokefalidis; Aris S Lalos; Konstantinos Moustakas Accelerating 3D scene analysis for autonomous driving on embedded AI computing platforms Inproceedings 2021 IFIP/IEEE 29th International Conference on Very Large Scale Integration (VLSI-SoC), pp. 1-6, 2021. @inproceedings{9606990, title = {Accelerating 3D scene analysis for autonomous driving on embedded AI computing platforms}, author = {Stavros Nousias and Erion-Vasilis Pikoulis and Christos Mavrokefalidis and Aris S Lalos and Konstantinos Moustakas}, url = {https://ieeexplore.ieee.org/abstract/document/9606990}, doi = {10.1109/VLSI-SoC53125.2021.9606990}, year = {2021}, date = {2021-01-01}, booktitle = {2021 IFIP/IEEE 29th International Conference on Very Large Scale Integration (VLSI-SoC)}, pages = {1-6}, abstract = {The design of 3D object detection schemes that use point clouds as input in automotive applications has gained a lot of interest recently. Those schemes capitalize on Deep Neural Networks (DNNs) that have demonstrated impressive results in analyzing complex scenes. The proposed schemes are generally designed to improve the achieved performance, leading however to high performing approaches with high computational complexity. To mitigate this high complexity and to facilitate their deployment on edge devices, model compression and acceleration techniques can be utilized. In this paper, we propose compressed versions of two well-known 3D object detectors, namely, PointPillars and PV-RCNN, utilizing dictionary learning-based weight-sharing techniques. It is demonstrated that significant acceleration gains can be achieved with acceptable average precision loss when evaluated on the KITTI 3D object detection benchmark. These findings constitute a concrete step towards the deployment of high-performance networks in edge devices of limited resources, such as NVIDIA’s Jetson TX2.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } The design of 3D object detection schemes that use point clouds as input in automotive applications has gained a lot of interest recently. Those schemes capitalize on Deep Neural Networks (DNNs) that have demonstrated impressive results in analyzing complex scenes. The proposed schemes are generally designed to improve the achieved performance, leading however to high performing approaches with high computational complexity. To mitigate this high complexity and to facilitate their deployment on edge devices, model compression and acceleration techniques can be utilized. In this paper, we propose compressed versions of two well-known 3D object detectors, namely, PointPillars and PV-RCNN, utilizing dictionary learning-based weight-sharing techniques. It is demonstrated that significant acceleration gains can be achieved with acceptable average precision loss when evaluated on the KITTI 3D object detection benchmark. These findings constitute a concrete step towards the deployment of high-performance networks in edge devices of limited resources, such as NVIDIA’s Jetson TX2. |
2020 |
|
| 133. | Erion-Vasilis Pikoulis; Christos Mavrokefalidis; Aris S Lalos A new clustering-based technique for the acceleration of deep convolutional networks Inproceedings 19th IEEE International Conference on Machine Learning and Applications (ICMLA), Virtual Conference, 2020. @inproceedings{pikoulis2020a, title = {A new clustering-based technique for the acceleration of deep convolutional networks}, author = {Erion-Vasilis Pikoulis and Christos Mavrokefalidis and Aris S Lalos}, year = {2020}, date = {2020-11-01}, journal = {19th IEEE International Conference on Machine Learning and Applications (ICMLA), Virtual Conference, Nov. 2020}, publisher = {19th IEEE International Conference on Machine Learning and Applications (ICMLA), Virtual Conference}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |