With the increasing popularity of Cyber-physical Systems (CPS), there is a growing need for efficient and reliable methods for detecting and responding to threats. Federated Learning (FL) is a distributed Machine Learning (ML) technique that can be used to train models on data from multiple devices (i.e., edge devices) while keeping the data local. FL has the potential to improve the security and privacy of data while also reducing the training time and cost. Particularly, CNN-based FL has been shown to be effective for various tasks such as image classification and object detection. However, selecting suitable hyperparameters for constructing local ML models in FL is a significant challenge for practical inference and training on edge devices. In this paper, we focus on the optimization of CNN-based federated learning for the task of cyber-physical detection and we propose employing a novel metaheuristic optimization algorithm called Honey Badger Algorithm (HBA) for tuning the hyperparameters in local ML models (FL-HBA). To show the effectiveness of FL-HBA, we make an evaluation using an intelligent healthcare case study where we consider Sleep Apnea (SA) and use the PhysioNet apnea ECG dataset to diagnose SA. Our results show that the FL-HBA is superior to a Convolutional Neural Network (CNN) baseline, traditional ML techniques, and centralized learning models. Furthermore, we demonstrate that the proposed method for assigning the near-optimal hyperparameter values for centralized learning models improves accuracy by 2%.

Terminodes are personal devices that provide functionality of both the terminals and the nodes of the network. A network of terminodes is an autonomous, fully self-organized, wireless network, independent of any infrastructure. It must be able to scale up to millions of units, without any fixed backbone or server. In this paper we present the main challenges and discuss the main technical directions.

Congestion avoidance algorithms considering the network as a black-box model detect congestion through packet loss and variation in the throughput or in the round trip delay. In this paper we show, by means of analysis and simulation, an undesirable effect acting on delay and throughput based congestion avoidance algorithms. This effect is caused by congestion experienced by acknowledgements. We propose to change these algorithms by dividing the round trip time into a forward trip time and backward trip time. We show the performance improvement using this distinction. Finally, we describe a possible implementation in the TCP protocol.

We are concerned about the problem of transmitting constant quality video over the B-ISDN. A gain in channel utilization is achieved when several variable bit rate video sources share a common ATM connection. To achieve such gain, the impact of cell losses on video quality degradation should be considered. Multi-layered video coding has been shown to tolerate more cell losses than non-layered video coding while maintaining negligible quality degradation. We exploit this cell loss tolerability in a multi-layered video coding scheme to improve multiplexing efficiency while preserving a constant video quality.

We present a rate control algorithm adapted to MPEG video coders ensuring that output conforms to the parameters of a leaky-bucket network access controller. The algorithm avoids unpredictable rate variations without the rigidity and systematic coding delay of constant bit-rate (CBR) coders, and makes possible resource provision for guaranteed quality of service. A relatively large burst tolerance parameter allows considerable scope for variation at GoP scale, and only restricts the natural rate when necessary to avoid long-term overloads. Possible multiplexing schemes are discussed distinguishing buffer provision for cell-scale and burst-scale congestion.