The widespread adoption of IoT networks has made them vulnerable to jamming attacks, which disrupt communication and compromise critical applications. Traditional jamming detection methods face challenges due to resource constraints and the need for large labeled datasets. This paper proposes a Deep Active Learning (DAL) framework for jamming detection and classification, addressing these limitations by minimizing the reliance on annotated data while maintaining high accuracy. Leveraging pool-based and uncertainty sampling, our approach iteratively selects the most informative data points for labeling, significantly reducing the dataset size required for training. Using a real-world IoT dataset, the proposed framework achieved 98% accuracy with only 50% of the available dataset. This represents a 13% improvement in accuracy and a 50% reduction in dataset size. Experimental results, validated through Monte Carlo simulations, demonstrated the model’s robustness in distinguishing between normal channels, constant jammers, and periodic jammers, with minimal misclassification. The framework’s efficiency and accuracy make it a practical solution for resource-constrained IoT networks.

Time series prediction plays a crucial role in optimizing the operation of communication networks. Applications of time series prediction include traffic prediction, channel state prediction, handover prediction, etc. However, training high-quality models for these tasks requires large volumes of historical data. This requirement may not be available in some scenarios. In this case, instance-based Transfer Learning (TL) comes as a prominent solution for this problem. However, a few concerns could be raised such as: 1) the time and bandwidth resources consumed in the transfer, 2) it will be hard to specify the amount of data to be transferred, and 3) in case of transferring a subset of the data, which subset is better to transfer. To address these challenges, we propose a novel approach for TL, which is similar to, but different than, instance-based TL based on generative models. We coined the new approach as Surrogate Data Source Transfer (SDST), in which a generative model is trained on the source task. We then transfer the model to the target task (with limited historical data). Extensive experiments confirm the superior performance of the proposed approach in terms of prediction accuracy and consumed resources (time and bandwidth). Our TL approach reduced the mean absolute percentage error (MAPE) by a margin that hits 81% in some datasets. For the source code and data, we refer to the repository https://github.com/MoeR3za/Korsahy_TGAN.

The development of beyond-fifth-generation (B5G) communication systems introduces challenges in maintaining timing and frequency synchronization, especially in low SNR and extended coverage scenarios. Accurate carrier frequency offset (CFO) estimation is crucial for establishing calls under such conditions. Existing methods, like maximum likelihood estimation, have limitations, while machine learning (ML) techniques have shown promise in wireless communication. In this work, we propose an ML-based approach using Long Short-Term Memory (LSTM) neural networks and automated machine learning (AutoML) to tune hyperparameters and improve CFO estimation accuracy. We compare our model with a gradientboosting machine (GBM) approach and demonstrate superior accuracy. Our research addresses CFO estimation challenges in B5G systems and offers valuable insights for the development of robust techniques in advanced communication systems.

Transfer learning (TL) reduces the training overheads by transferring knowledge across domains/tasks. However, the advantages of TL come with computation and communication costs. Therefore, the decision to transfer knowledge between learners should be optimized while at the same time avoiding negative transfer (NT), i.e. when the source information does not improve but rather degrades the learning performance in the target. In this paper, we propose a new notion namely, regret of learner (RoL) as a quantitative measure for the learner's performance, computation costs and communication resources of TL. Then, we use a convex combination of the empirical source and target errors with respect to the feasibility and resource constraints to design an optimization model called OPTL that deploys a TL model in a resource-constrained environment to avoid NT. This model can be employed as a general framework for different ML methods and various communication scenarios and use cases by changing the unification parameters. To validate our approach, we use OPTL for optimized TL in a deep learning (DL)-based classification problem. Extensive experiments confirm the efficiency of our proposed method.

The anticipated huge number of devices and large traffic volumes impose new challenges on the communication system requirements and design. One of the main requirements of massive machine-type communication (mMTC) is to support network energy efficiency. Data compression is a widely adopted technique that enables higher energy efficiency, lower latency, and better bandwidth utilization. Unfortunately, the current compression techniques are mainly designed for human-type communications (HTC). Therefore, they consider the reconstruction fidelity, rather than the accuracy of inferred decisions, as the sole performance metric. In this work, we propose a novel encoder for data compression in mMTC communications, which is termed Distillation Encoder (DE). Unlike prior work, the design of the proposed DE aims to achieve high compression ratios while preserving the accuracy of the inferred decisions. DE inherits the knowledge of a large teacher model (trained on the raw data) through knowledge distillation. Evaluating the proposed framework on several public datasets shows a clear performance advantage compared with baseline models in terms of the inferred decision accuracy and generalizing to yet-unseen data. Moreover, the DE can be applied to learn efficient quantizers, as shown in the results.

In a multiple-input multiple-output frequency-division duplexing (MIMO-FDD) system, the user equipment (UE) sends the downlink channel state information (CSI) to the base station to report link status. Due to the complexity of MIMO systems, the overhead incurred in sending this information negatively affects the system bandwidth. Although this problem has been widely considered in the literature, prior work generally assumes an ideal feedback channel. In this paper, we introduce PRVNet, a neural network architecture inspired by variational autoencoders (VAE) to compress the CSI matrix before sending it back to the base station under noisy channel conditions. Moreover, we propose a customized loss function that best suits the special characteristics of the problem being addressed. We also introduce an additional regularization hyperparameter for the learning objective, which is crucial for achieving competitive performance. In addition, we provide an efficient way to tune this hyperparameter using KL-annealing. Experimental results show the proposed model outperforms the benchmark models including two deep learning-based models in a noise-free feedback channel assumption. In addition, the proposed model achieves an outstanding performance under different noise levels for additive white Gaussian noise feedback channels.

Recently, transfer learning (TL) has emerged as a powerful machine learning method in distributed environments. Transferring the knowledge between distributed agents helps reduce both learning time and computing costs. However, in a communication system, the advantage of TL comes with communication costs. To make an optimal decision of transfer between two agents, we try to answer three key questions: i) which information should be transferred from a source to a target?, ii) how this transferred information will be adapted to the target? and iii) when should TL be triggered to optimize the costs?. To this end, we introduce a new concept of similarity based on the Best Approximation Theory and a general transfer rule. Then, we propose a model to evaluate the feasibility and optimality of TL. We verify our proposed model in the context of the wireless channel selection problem using contextual multi-armed bandits. Experimental results show optimal TL decisions can be made, and Extra Action is an efficient technique for TL in channel selection.

In IoT applications, the sensors usually have limited bandwidth and power resources. Therefore, the sensed data should be mapped to a low-bit representation by means of compression and quantization before being transmitted to a central node, called the fusion center (FC). At the FC, a global decision is inferred from this data. In many cases, this data is intended for machine consumption, not for human perception. However, the compression techniques are mainly designed for reconstruction fidelity. The accuracy of the inferred decision at the FC is less considered. In this work, we present an end-to-end framework for learning a 1-bit representation of correlated-sensors data. We also propose a novel loss function and a three-stage training algorithm for learning discriminative binary features at each sensor. Extensive experiments show the proposed framework achieves high compression ratios with a marginal loss in the inferred decision accuracy. Comparatively, the obtained results outperform other benchmark models in the literature.

A key challenge facing any channel selection technique is the dynamic nature of wireless channels. To address this issue, reinforcement learning techniques have widely been used, e.g., contextual multi-armed bandit (CMAB) theory. In fact, prior works solved the problem at each individual node. However, they did not consider the cooperative learning techniques, e.g., transfer learning. In communication systems, the advantage of transfer learning comes with computation and communication costs. Therefore, the decision of transferring the knowledge between agents should be optimized. In this paper, we develop a model to evaluate the feasibility and optimality of transfer learning for CMAB-based channel selection in communication systems. To this end, we introduce a utility model for evaluating these economical aspects. Leveraging Best Approximation Theory, we propose a new similarity concept and a transfer rule applied in the context of channel selection. Experimental results show that Extra Action is an efficient technique for transfer learning in a channel selection regime. More importantly, our proposed utility and optimization model is shown to be a powerful framework for deciding when transfer learning is feasible, and when it is optimal.

The problem of selecting the modulation and coding scheme (MCS) that maximizes the system throughput, known as link adaptation, has been investigated extensively, especially for IEEE 802.11 (WiFi) standards. Recently, deep learning has widely been adopted as an efficient solution to this problem. However, in failure cases, predicting a higher-rate MCS can result in a failed transmission. In this case, a retransmission is required, which largely degrades the system throughput. To address this issue, we model the adaptive modulation and coding (AMC) problem as a multi-label multi-class classification problem. The proposed modeling allows more control over what the model predicts in failure cases. We also design a simple, yet powerful, loss function to reduce the number of retransmissions due to higher-rate MCS classification errors. Since wireless channels change significantly due to the surrounding environment, a huge dataset has been generated to cover all possible propagation conditions. However, to reduce training complexity, we train the CNN model using part of the dataset. The effect of different subdataset selection criteria on the classification accuracy is studied. The proposed model adapts the IEEE 802.11ax communications standard in outdoor scenarios. The simulation results show the proposed loss function reduces up to 50% of retransmissions compared to traditional loss functions.