CNR Author
operator:
and / or
Typology
operator:
and / or
Language
operator:
and / or
Date
operator:
and / or
Rights
operator:
and / or
2023
Conference article
Open Access
A federated channel modeling system using generative neural networks
Bano S., Cassarà P., Tonellotto N., Gotta A.
The paper proposes a data-driven approach to air-to-ground channel estimation in a millimeter-wave wireless network on an unmanned aerial vehicle. Unlike traditional centralized learning methods that are specific to certain geographical areas and inappropriate for others, we propose a generalized model that uses Federated Learning (FL) for channel estimation and can predict the air-to-ground path loss between a low-altitude platform and a terrestrial terminal. To this end, our proposed FL-based Generative Adversarial Network (FL-GAN) is designed to function as a generative data model that can learn different types of data distributions and generate realistic patterns from the same distributions without requiring prior data analysis before the training phase. To evaluate the effectiveness of the proposed model, we evaluate its performance using Kullback-Leibler divergence (KL), and Wasserstein distance between the synthetic data distribution generated by the model and the actual data distribution. We also compare the proposed technique with other generative models, such as FL-Variational Autoencoder (FL-VAE) and stand-alone VAE and GAN models. The results of the study show that the synthetic data generated by FL-GAN has the highest similarity in distribution with the real data. This shows the effectiveness of the proposed approach in generating data-driven channel models that can be used in different regions.Source: VTC2023-Spring - IEEE 97th Vehicular Technology Conference, Florence, Italy, 20-23/06/2023
DOI: 10.1109/vtc2023-spring57618.2023.10199491
Metrics:
Bano S., Cassarà P., Tonellotto N., Gotta A.
The paper proposes a data-driven approach to air-to-ground channel estimation in a millimeter-wave wireless network on an unmanned aerial vehicle. Unlike traditional centralized learning methods that are specific to certain geographical areas and inappropriate for others, we propose a generalized model that uses Federated Learning (FL) for channel estimation and can predict the air-to-ground path loss between a low-altitude platform and a terrestrial terminal. To this end, our proposed FL-based Generative Adversarial Network (FL-GAN) is designed to function as a generative data model that can learn different types of data distributions and generate realistic patterns from the same distributions without requiring prior data analysis before the training phase. To evaluate the effectiveness of the proposed model, we evaluate its performance using Kullback-Leibler divergence (KL), and Wasserstein distance between the synthetic data distribution generated by the model and the actual data distribution. We also compare the proposed technique with other generative models, such as FL-Variational Autoencoder (FL-VAE) and stand-alone VAE and GAN models. The results of the study show that the synthetic data generated by FL-GAN has the highest similarity in distribution with the real data. This shows the effectiveness of the proposed approach in generating data-driven channel models that can be used in different regions.Source: VTC2023-Spring - IEEE 97th Vehicular Technology Conference, Florence, Italy, 20-23/06/2023
DOI: 10.1109/vtc2023-spring57618.2023.10199491
Metrics:
See at:
ISTI Repository 
| ieeexplore.ieee.org 
| CNR ExploRA
2023
Journal article
Open Access
Artificial intelligence of things at the edge: scalable and efficient distributed learning for massive scenarios
Bano S., Tonellotto N., Cassarà P., Gotta A.
Federated Learning (FL) is a distributed optimization method in which multiple client nodes collaborate to train a machine learning model without sharing data with a central server. However, communication between numerous clients and the central aggregation server to share model parameters can cause several problems, including latency and network congestion. To address these issues, we propose a scalable communication infrastructure based on Information-Centric Networking built and tested on Apache Kafka®. The proposed architecture consists of a two-tier communication model. In the first layer, client updates are cached at the edge between clients and the server, while in the second layer, the server computes global model updates by aggregating the cached models. The data stored in the intermediate nodes at the edge enables reliable and effective data transmission and solves the problem of intermittent connectivity of mobile nodes. While many local model updates provided by clients can result in a more accurate global model in FL, they can also result in massive data traffic that negatively impacts congestion at the edge. For this reason, we couple a client selection procedure based on a congestion control mechanism at the edge for the given architecture of FL. The proposed algorithm selects a subset of clients based on their resources through a time-based backoff system to account for the time-averaged accuracy of FL while limiting the traffic load. Experiments show that our proposed architecture has an improvement of over 40% over the network-centric based FL architecture, i.e., Flower. The architecture also provides scalability and reliability in the case of mobile nodes. It also improves client resource utilization, avoids overflow, and ensures fairness in client selection. The experiments show that the proposed algorithm leads to the desired client selection patterns and is adaptable to changing network environments.Source: Computer communications 205 (2023): 45–57. doi:10.1016/j.comcom.2023.04.010
DOI: 10.1016/j.comcom.2023.04.010
Project(s): TEACHING
Metrics:
Bano S., Tonellotto N., Cassarà P., Gotta A.
Federated Learning (FL) is a distributed optimization method in which multiple client nodes collaborate to train a machine learning model without sharing data with a central server. However, communication between numerous clients and the central aggregation server to share model parameters can cause several problems, including latency and network congestion. To address these issues, we propose a scalable communication infrastructure based on Information-Centric Networking built and tested on Apache Kafka®. The proposed architecture consists of a two-tier communication model. In the first layer, client updates are cached at the edge between clients and the server, while in the second layer, the server computes global model updates by aggregating the cached models. The data stored in the intermediate nodes at the edge enables reliable and effective data transmission and solves the problem of intermittent connectivity of mobile nodes. While many local model updates provided by clients can result in a more accurate global model in FL, they can also result in massive data traffic that negatively impacts congestion at the edge. For this reason, we couple a client selection procedure based on a congestion control mechanism at the edge for the given architecture of FL. The proposed algorithm selects a subset of clients based on their resources through a time-based backoff system to account for the time-averaged accuracy of FL while limiting the traffic load. Experiments show that our proposed architecture has an improvement of over 40% over the network-centric based FL architecture, i.e., Flower. The architecture also provides scalability and reliability in the case of mobile nodes. It also improves client resource utilization, avoids overflow, and ensures fairness in client selection. The experiments show that the proposed algorithm leads to the desired client selection patterns and is adaptable to changing network environments.Source: Computer communications 205 (2023): 45–57. doi:10.1016/j.comcom.2023.04.010
DOI: 10.1016/j.comcom.2023.04.010
Project(s): TEACHING
Metrics:
See at:
ISTI Repository | Computer Communications | CNR ExploRA
2022
Conference article
Open Access
A novel approach to distributed model aggregation using Apache Kafka
Bano S., Carlini E., Cassarà P., Coppola M., Dazzi P., Gotta A.
Multi-Access Edge Computing (MEC) is attracting a lot of interest because it complements cloud-based approaches. Indeed, MEC is opening up in the direction of reducing both interaction delays and data sharing, called Cyber-Physical Systems (CPSs). In the near fu-ture, edge technologies will be a fundamental tool to better support time-dependent and data-intensive applications. In this context, this work explores existing and emerging platforms for MEC and human-centric applications, and proposes a suitable architecture that can be used in the context of autonomous vehicle systems.The proposed architecture will support scalable communication among sensing devices and edge/cloud computing platforms, as well as orchestrate services for computing, storage, and learning with the use of an Information-centric paradigm such as Apache KafkaSource: FRAME '22 - 2nd Workshop on Flexible Resource and Application Management on the Edge, pp. 33–36, Minneapolis, Minnesota, USA, 27/06-01/07/2022
DOI: 10.1145/3526059.3533621
Project(s): TEACHING
Metrics:
Bano S., Carlini E., Cassarà P., Coppola M., Dazzi P., Gotta A.
Multi-Access Edge Computing (MEC) is attracting a lot of interest because it complements cloud-based approaches. Indeed, MEC is opening up in the direction of reducing both interaction delays and data sharing, called Cyber-Physical Systems (CPSs). In the near fu-ture, edge technologies will be a fundamental tool to better support time-dependent and data-intensive applications. In this context, this work explores existing and emerging platforms for MEC and human-centric applications, and proposes a suitable architecture that can be used in the context of autonomous vehicle systems.The proposed architecture will support scalable communication among sensing devices and edge/cloud computing platforms, as well as orchestrate services for computing, storage, and learning with the use of an Information-centric paradigm such as Apache KafkaSource: FRAME '22 - 2nd Workshop on Flexible Resource and Application Management on the Edge, pp. 33–36, Minneapolis, Minnesota, USA, 27/06-01/07/2022
DOI: 10.1145/3526059.3533621
Project(s): TEACHING
Metrics:
See at:
ZENODO | dl.acm.org | doi.org | CNR ExploRA
2022
Conference article
Open Access
FedTCS: federated learning with time-based client selection to optimize edge resources
Bano S., Tonellotto N., Cassarà P., Gotta A.
Client sampling in federated learning (FL) is a significant problem, especially in massive cross-device scenarios where communication with all devices is not possible. In this work, we study the client selection problem using a time-based back-off system in federated learning for a MEC-based network infrastructure. In the FL paradigm, where a group of nodes can jointly train a machine learning model with the help of a central server, client selection is expected to have a significant impact in FL applications deployed in future 6G networks, given the increasing number of connected devices. Our timer settings are based on an exponential distribution to obtain an expected number of clients for the FL process. Empirical results show that our technique is scalable and robust for a large number of clients and keeps data queues stable at the edge.Source: AI6G 2022 - First International Workshop on Artificial Intelligence in Beyond 5G and 6G Wireless Networks, Padua, Italy, 18/06/2022
Project(s): TEACHING
Bano S., Tonellotto N., Cassarà P., Gotta A.
Client sampling in federated learning (FL) is a significant problem, especially in massive cross-device scenarios where communication with all devices is not possible. In this work, we study the client selection problem using a time-based back-off system in federated learning for a MEC-based network infrastructure. In the FL paradigm, where a group of nodes can jointly train a machine learning model with the help of a central server, client selection is expected to have a significant impact in FL applications deployed in future 6G networks, given the increasing number of connected devices. Our timer settings are based on an exponential distribution to obtain an expected number of clients for the FL process. Empirical results show that our technique is scalable and robust for a large number of clients and keeps data queues stable at the edge.Source: AI6G 2022 - First International Workshop on Artificial Intelligence in Beyond 5G and 6G Wireless Networks, Padua, Italy, 18/06/2022
Project(s): TEACHING
See at:
ceur-ws.org | ISTI Repository | CNR ExploRA
2022
Conference article
Open Access
KafkaFed: two-tier federated learning communication architecture for internet of vehicles
Bano S., Tonellotto N., Cassarà P., Gotta A.
In the current era of the Internet of Vehicles (IoV), vehicle to vehicle data sharing can provide customized applications for Connected and Autonomous Vehicles (CAVs). The advancement of Deep Learning (DL) methodologies is one of the key driving forces for CAVs, allowing elaborating a massive amount of data by the resource-constrained onboard devices. In a traditional centralized DL approach, vehicle data are transmitted to the cloud for the training of models. This approach leads to significant communication overhead, high delays, and data privacy concerns. Conversely, Federated Learning (FL) performs the training using the local models in a distributed fashion and mitigates the data privacy risks by sharing only the model parameters with the server, optimizing the FL to be used with resources-constrained devices. In this paper, we propose the design of a scalable communication infrastructure to support the FL procedure based on Information-Centric Networking (ICN) using Apache Kafka, called KafkaFed. The ICN-based infrastructure allows to overcome the shortcomings of current client-server architectures for FL, in which routing is content-based or name-based to achieve efficient data retrieval for mobile nodes. In ICN, data are stored at intermediate nodes to provide efficient and reliable data delivery. A proof of concept of the KafkaFed communication architecture is developed and tested in an emulated environment. The performance of the proposed framework compared to the client server-based FL architecture, i.e., FLOWER showed a boost of almost 40% with just 32 clients in addition to several other advantages of scalability, reliability, and securitySource: PerCom Workshops - 2022 IEEE International Conference on Pervasive Computing and Communications, pp. 515–520, Pisa, Italy, 21-25 March 2022
DOI: 10.1109/percomworkshops53856.2022.9767510
Project(s): TEACHING
Metrics:
Bano S., Tonellotto N., Cassarà P., Gotta A.
In the current era of the Internet of Vehicles (IoV), vehicle to vehicle data sharing can provide customized applications for Connected and Autonomous Vehicles (CAVs). The advancement of Deep Learning (DL) methodologies is one of the key driving forces for CAVs, allowing elaborating a massive amount of data by the resource-constrained onboard devices. In a traditional centralized DL approach, vehicle data are transmitted to the cloud for the training of models. This approach leads to significant communication overhead, high delays, and data privacy concerns. Conversely, Federated Learning (FL) performs the training using the local models in a distributed fashion and mitigates the data privacy risks by sharing only the model parameters with the server, optimizing the FL to be used with resources-constrained devices. In this paper, we propose the design of a scalable communication infrastructure to support the FL procedure based on Information-Centric Networking (ICN) using Apache Kafka, called KafkaFed. The ICN-based infrastructure allows to overcome the shortcomings of current client-server architectures for FL, in which routing is content-based or name-based to achieve efficient data retrieval for mobile nodes. In ICN, data are stored at intermediate nodes to provide efficient and reliable data delivery. A proof of concept of the KafkaFed communication architecture is developed and tested in an emulated environment. The performance of the proposed framework compared to the client server-based FL architecture, i.e., FLOWER showed a boost of almost 40% with just 32 clients in addition to several other advantages of scalability, reliability, and securitySource: PerCom Workshops - 2022 IEEE International Conference on Pervasive Computing and Communications, pp. 515–520, Pisa, Italy, 21-25 March 2022
DOI: 10.1109/percomworkshops53856.2022.9767510
Project(s): TEACHING
Metrics:
See at:
ISTI Repository | ZENODO | doi.org | ieeexplore.ieee.org | CNR ExploRA
2022
Contribution to conference
Open Access
Drivers stress identification in real-world driving tasks
Bano S., Tonellotto N., Gotta A.
In the past few years, cross-modal distillation has garnered a lot of interest due to the rapid growth of multi-modal data. In this paper, we study stress recognition of the drivers corresponding to the driving situation. Our method enables us to recognize stress from unlabeled videos. We perform cross-modal distillation based on wearable physiological sensors and videos from on-board cameras. In this cross-modal distillation, knowledge is transferred from sensor to vision modality.Source: PerCom Workshops - 2022 IEEE International Conference on Pervasive Computing and Communications, pp. 140–141, Pisa, Italy, 21-25 March 2022
DOI: 10.1109/percomworkshops53856.2022.9767455
Metrics:
Bano S., Tonellotto N., Gotta A.
In the past few years, cross-modal distillation has garnered a lot of interest due to the rapid growth of multi-modal data. In this paper, we study stress recognition of the drivers corresponding to the driving situation. Our method enables us to recognize stress from unlabeled videos. We perform cross-modal distillation based on wearable physiological sensors and videos from on-board cameras. In this cross-modal distillation, knowledge is transferred from sensor to vision modality.Source: PerCom Workshops - 2022 IEEE International Conference on Pervasive Computing and Communications, pp. 140–141, Pisa, Italy, 21-25 March 2022
DOI: 10.1109/percomworkshops53856.2022.9767455
Metrics:
See at:
ISTI Repository | ieeexplore.ieee.org | CNR ExploRA
2022
Conference article
Open Access
Federated semi-supervised classification of multimedia flows for 3D networks
Bano S., Machumilane A., Valerio L., Cassarà P., Gotta A.
Automatic traffic classification is increasingly becoming important in traffic engineering, as the current trend of encrypting transport information (e.g., behind HTTP-encrypted tunnels) prevents intermediate nodes from accessing end-to-end packet headers. However, this information is crucial for traffic shaping, network slicing, and Quality of Service (QoS) management, for preventing network intrusion, and for anomaly detection. 3D networks offer multiple routes that can guarantee different levels of QoS. Therefore, service classification and separation are essential to guarantee the required QoS level to each traffic sub-flow through the appropriate network trunk. In this paper, a federated feature selection and feature reduction learning scheme is proposed to classify network traffic in a semi-supervised cooperative manner. The federated gateways of 3D network help to enhance the global knowledge of network traffic to improve the accuracy of anomaly and intrusion detection and service identification of a new traffic flow.Source: MELECON 2022 - 21st IEEE Mediterranean Electrotechnical Conference, pp. 165–170, Palermo, Italy, 14-16 June 2022
DOI: 10.1109/melecon53508.2022.9843104
Project(s): TEACHING
Metrics:
Bano S., Machumilane A., Valerio L., Cassarà P., Gotta A.
Automatic traffic classification is increasingly becoming important in traffic engineering, as the current trend of encrypting transport information (e.g., behind HTTP-encrypted tunnels) prevents intermediate nodes from accessing end-to-end packet headers. However, this information is crucial for traffic shaping, network slicing, and Quality of Service (QoS) management, for preventing network intrusion, and for anomaly detection. 3D networks offer multiple routes that can guarantee different levels of QoS. Therefore, service classification and separation are essential to guarantee the required QoS level to each traffic sub-flow through the appropriate network trunk. In this paper, a federated feature selection and feature reduction learning scheme is proposed to classify network traffic in a semi-supervised cooperative manner. The federated gateways of 3D network help to enhance the global knowledge of network traffic to improve the accuracy of anomaly and intrusion detection and service identification of a new traffic flow.Source: MELECON 2022 - 21st IEEE Mediterranean Electrotechnical Conference, pp. 165–170, Palermo, Italy, 14-16 June 2022
DOI: 10.1109/melecon53508.2022.9843104
Project(s): TEACHING
Metrics:
See at:
ISTI Repository | ieeexplore.ieee.org | CNR ExploRA
2022
Conference article
Open Access
AI-as-a-Service toolkit for human-centered intelligence in autonomous driving
De Caro V., Bano S., Machumilane A., Gotta A., Cassarà P., Carta A., Semola R., Sardianos C., Chronis C., Varlamis I., Tserpes K., Lomonaco V., Gallicchio C., Bacciu D.
This paper presents a proof-of-concept implementation of the AI-as-a-Service toolkit developed within the H2020 TEACHING project and designed to implement an autonomous driving personalization system according to the output of an automatic driver's stress recognition algorithm, both of them realizing a Cyber-Physical System of Systems. In addition, we implemented a data-gathering subsystem to collect data from different sensors, i.e., wearables and cameras, to automatize stress recognition. The system was attached for testing to a driving emulation software, CARLA, which allows testing the approach's feasibility with minimum cost and without putting at risk drivers and passengers. At the core of the relative subsystems, different learning algorithms were implemented using Deep Neural Networks, Recurrent Neural Networks, and Reinforcement Learning.Source: PerCom Workshops - 2022 IEEE International Conference on Pervasive Computing and Communications, pp. 91–93, Pisa, Italy, 21-25 March 2022
DOI: 10.1109/percomworkshops53856.2022.9767501
DOI: 10.48550/arxiv.2202.01645
Project(s): TEACHING
Metrics:
De Caro V., Bano S., Machumilane A., Gotta A., Cassarà P., Carta A., Semola R., Sardianos C., Chronis C., Varlamis I., Tserpes K., Lomonaco V., Gallicchio C., Bacciu D.
This paper presents a proof-of-concept implementation of the AI-as-a-Service toolkit developed within the H2020 TEACHING project and designed to implement an autonomous driving personalization system according to the output of an automatic driver's stress recognition algorithm, both of them realizing a Cyber-Physical System of Systems. In addition, we implemented a data-gathering subsystem to collect data from different sensors, i.e., wearables and cameras, to automatize stress recognition. The system was attached for testing to a driving emulation software, CARLA, which allows testing the approach's feasibility with minimum cost and without putting at risk drivers and passengers. At the core of the relative subsystems, different learning algorithms were implemented using Deep Neural Networks, Recurrent Neural Networks, and Reinforcement Learning.Source: PerCom Workshops - 2022 IEEE International Conference on Pervasive Computing and Communications, pp. 91–93, Pisa, Italy, 21-25 March 2022
DOI: 10.1109/percomworkshops53856.2022.9767501
DOI: 10.48550/arxiv.2202.01645
Project(s): TEACHING
Metrics:
See at:
arXiv.org e-Print Archive | ISTI Repository | doi.org | doi.org | ieeexplore.ieee.org | ZENODO | CNR ExploRA
2021
Conference article
Restricted
PhD forum abstract: efficient computing and communication paradigms for federated learning data streams
Bano S.
In this work, we proposed an integration of Federated Learning with Apache Kafka, an open-source framework that enables the management of continuous data streams with fault tolerance, low latency, and horizontal scalability. Our main focus is to evaluate the impact of learning delays and network overhead when hundred of users are sending their model updates for the aggregation to improve the global model in Federated Learning.Source: SMARTCOMP 2021 - IEEE International Conference on Smart Computing, pp. 410–411, Irvine, USA, 23-27/08/2021
DOI: 10.1109/smartcomp52413.2021.00086
Metrics:
Bano S.
In this work, we proposed an integration of Federated Learning with Apache Kafka, an open-source framework that enables the management of continuous data streams with fault tolerance, low latency, and horizontal scalability. Our main focus is to evaluate the impact of learning delays and network overhead when hundred of users are sending their model updates for the aggregation to improve the global model in Federated Learning.Source: SMARTCOMP 2021 - IEEE International Conference on Smart Computing, pp. 410–411, Irvine, USA, 23-27/08/2021
DOI: 10.1109/smartcomp52413.2021.00086
Metrics:
See at:
doi.org | ieeexplore.ieee.org | CNR ExploRA