Telecom

The current paper retrieves implicit quiescent soliton solutions to optical metamaterials with nonlinear chromatic dispersion with generalized temporal evolution. Seven forms of self-phase modulation structures, as proposed by Kudryashov with time, are taken up. The implemented integration algorithm is Lie symmetry. A few of the solutions are in quadratures, while others are in terms of special functions. We also characterize the parameters that constrain the existence of such solutions.

This work presents an energy-efficient implementation of Unmanned Aerial Vehicle (UAV)-based systems over 5G networks with on-board accelerated processing capabilities and provides a preliminary evaluation of the integrated solution. The study is a two-fold comparative analysis focused on connectivity and edge processing for UAVs. Two discrete deployment scenarios are implemented, where standard 5G configuration with artificial neural network (ANN) processing is evaluated against 5G Reduced Capability (RedCap) connectivity, paired with Spiking Neural Networks (SNNs). Both proposed energy-efficient alternative solutions are designed to offer significant energy savings; this paper examines whether they are suitable candidates for energy-constrained environments, i.e., UAVs, and quantifies their impact on the overall energy consumption of the system. The integrated solution, with 5G RedCap/SNNs, achieves energy-use reductions approaching 60%, which translates to an approximate 35% increase in flight time. The experimental evaluations were performed in a real-world deployment using a 5G-equipped UAV with edge-processing capabilities based on NVIDIA’s Jetson Orin.

Space and satellite-based systems have had a monumental impact on providing greater interconnectivity across the world. The usage of space and satellite-based systems has increased the ability to access internet resources even in remote areas. Unfortunately, these systems are subject to malicious and multi-faceted cyberattacks. Therefore, proper threat detection systems must be implemented to safeguard these space systems. In our study, we present our novel intrusion detection framework, SpIDER, a space satellite intrusion detection system using explainable reinforcement learning. SpIDER leverages the benefits offered by reinforcement learning and Shapley additive global explanations to improve both the performance and explainability of space-based intrusion detection. We compare our SpIDER framework to several popular machine learning algorithms using the STIN and NSL-KDD datasets. We observe that our SpIDER framework achieves high performance, with accuracy and G-Mean above 99.98% on the STIN satellite dataset. SpIDER also outperforms other machine learning models on the NSL-KDD local area network dataset, achieving accuracy of 76.71% and a G-Mean of 80.49%. These results demonstrate that our SpIDER explainable deep reinforcement learning framework can perform as well or better than supervised machine learning models on both satellite-style and local area network data.