Software Defined Networking (SDN) is developing as a new solution for the development and innovation of the Internet. SDN is expected to be the ideal future for the Internet, since it can provide a controllable, dynamic, and cost-effective network. The emergence of SDN provides a unique opportunity to achieve network security in a more efficient and flexible manner. However, SDN also has original structural vulnerabilities, which are the centralized controller, the control-data interface and the control-application interface. These vulnerabilities can be exploited by intruders to conduct several types of attacks. In this paper, we propose a deep learning (DL) approach for a network intrusion detection system (DeepIDS) in the SDN architecture. Our models are trained and tested with the NSL-KDD dataset and achieved an accuracy of 80.7% and 90% for a Fully Connected Deep Neural Network (DNN) and a Gated Recurrent Neural Network (GRU-RNN), respectively. Through experiments, we confirm that the DL approach has the potential for flow-based anomaly detection in the SDN environment. We also evaluate the performance of our system in terms of throughput, latency, and resource utilization. Our test results show that DeepIDS does not affect the performance of the OpenFlow controller and so is a feasible approach.

The closed-form expressions of the probability density function (pdf) and the moment-generating function for the exact end-to-end signal-to-noise ratio (SNR) of variable-gain relay networks are unknown for generalized fading models; thus, the exact evaluation for the ergodic capacity of these systems is cumbersome. In this paper, we develop a new unified framework for the exact ergodic capacity of multihop networks equipped with variable-gain relays, assuming that channel-state information (CSI) is available only at the receiving terminals. The resulting expression (which is based on the exact end-to-end SNR) is in the form of a single truncated infinite series and is valid for an arbitrary number of hops and for various fading models that are typically encountered in realistic scenarios. Furthermore, we show that the exact ergodic capacity of dual-hop variable-gain relay networks can be written in terms of the ergodic capacities of two equivalent single-input-single-output (SISO) channels and one single-input-multiple-output channel (SIMO), the closed-form expressions of which are already available for many commonly used fading/shadowing models. Finally, we show that there is an exact match between the Monte Carlo simulation and theoretical results over a whole range of per-hop average SNR.

Multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) is a key technology component in the evolution towards cognitive radio (CR) in next-generation communication in which the accuracy of timing and frequency synchronization significantly impacts the overall system performance. In this paper, we propose a novel scheme leveraging extreme learning machine (ELM) to achieve high-precision synchronization. Specifically, exploiting the preamble signals with synchronization offsets, two ELMs are incorporated into a traditional MIMO-OFDM system to estimate both the residual symbol timing offset (RSTO) and the residual carrier frequency offset (RCFO). The simulation results show that the performance of the proposed ELM-based synchronization scheme is superior to the traditional method under both additive white Gaussian noise (AWGN) and frequency selective fading channels. Furthermore, comparing with the existing machine learning based techniques, the proposed method shows outstanding performance without the requirement of perfect channel state information (CSI) and prohibitive computational complexity. Finally, the proposed method is robust in terms of the choice of channel parameters (e.g., number of paths) and also in terms of “generalization ability” from a machine learning standpoint.

Tiny machine learning (TinyML) is a promising approach to enable intelligent applications relying on Human Activity Recognition (HAR) on resource-limited and low-power internet of things (IoT) edge devices. However, designing efficient TinyML models for these devices remains challenging due to computational resource constraints and the need for customisation to unique use cases. To address this, we propose a novel approach that utilises transfer learning (TL) techniques on edge micro-controller units (MCUs) to accelerate TinyML development. Our strategy involves pre-training generalised ML models on large-scale and varied datasets and fine-tuning them on-device for specific applications using TL. We demonstrate the effectiveness of our approach for HAR by experimenting with a convolutional neural network, long short-term memory TL (CNN-LSTM-TL) model architecture and visualisation techniques like t-distributed stochastic neighbour embedding (t-SNE) for dimensionality reduction. To further validate our model’s proficiency and adaptability, we conducted extensive testing using two distinct datasets: MotionSense and UCI. This dual-dataset approach allowed us to assess the robustness of our model across different data domains, showcasing its versatility and effectiveness in various HAR scenarios. Our results show significant model accuracy and reduced training time while maintaining high inference rates and low MCU memory footprint. We also provide insights into best practices for implementing TL on edge MCUs and evaluate classification performance metrics such as accuracy, precision, recall, F1 score, and categorical cross-entropy loss. Our work lays a solid foundation for faster and more efficient TinyML deployments through TL framework across different application domains and types of edge IoT devices.

Federated Learning (FL) presents a mechanism to allow decentralized training for machine learning (ML) models inherently enabling privacy preservation. The classical FL is implemented as a client-server system, which is known as Centralised Federated Learning (CFL). There are challenges inherent in CFL since all participants need to interact with a central server resulting in a potential communication bottleneck and a single point of failure. In addition, it is difficult to have a central server in some scenarios due to the implementation cost and complexity. This study aims to use Decentralised Federated learning (DFL) without a central server through one-hop neighbors. Such collaboration depends on the dynamics of communication networks, e.g., the topology of the network, the MAC protocol, and both large-scale and small-scale fading on links. In this paper, we employ stochastic geometry to model these dynamics explicitly, allowing us to quantify the performance of the DFL. The core objective is to achieve better classification without sacrificing privacy while accommodating for networking dynamics. In this paper, we are interested in how such topologies impact the performance of ML when deployed in practice. The proposed system is trained on a well-known MINST dataset for benchmarking, which contains labelled data samples of 60K images each with a size 28×28 pixels, and 1000 random samples of this MNIST dataset are assigned for each participant’ device. The participants' devices implement a CNN model as a classifier model. To evaluate the performance of the model, a number of participants are randomly selected from the network. Due to randomness in the communication process, these participants interact with the random number of nodes in the neighborhood to exchange model parameters which are subsequently used to update the participants’ individual models. These participants connected successfully with a varying number of neighbours to exchange parameters and update their global models. The results show that the classification prediction system can achieve 95% accuracy using the three different model optimizers in the training settings (i.e., SGD, ADAM, and RMSprop optimizers). Consequently, the DFL over mesh networking shows more flexibility in IoT systems, which reduces the communication cost and increases the convergence speed which can outperform CFL.