Search Results (16)

Classical covert wireless communication is commonly formulated under a noise-only null hypothesis, in which a warden detects the presence of a transmission. In shared-spectrum settings with persistent legitimate traffic, however, a warden may already observe legitimate traffic and may therefore test whether an observation is statistically consistent with a legitimate signal class. Motivated by this regime, this paper studies mimicry covert communication in the post-demodulation OFDM resource-grid domain. A normalizing flow is trained on legitimate IEEE 802.11a NonHT-Data resource-grid observations, and covert bits are embedded by shared-key latent sign modulation, whose inner coordinatewise sign-flip rule preserves the standard Gaussian prior and thus the learned legitimate distribution under the ideal flow model. To improve message recovery under observation-domain perturbations, the framework further combines this inner embedding with a two-stage, two-state robustness-aware coordinate selector and a CRC-Polar outer code with reliability-weighted soft decoding. Experiments show that the coded design substantially improves message recovery over an uncoded repeated-sign baseline while keeping Willie-side discriminability low under both classifier-based and flow-density typicality tests. The study focuses on the learned post-demodulation resource-grid observation domain and leaves full over-the-air RF-chain validation for future work. Full article

Modulation and signal classification are two highly correlated core tasks in wireless communications and are the core foundation of intelligent spectrum management in Future Internet and 6G networks. Although their objectives differ, the two tasks often share a substantial amount of underlying information in the feature space. However, focusing solely on their commonalities while neglecting their intrinsic differences may lead to suboptimal model performance. Therefore, by taking into account both the correlation and inherent differences between the two tasks, we propose TAMTNet, a task-adaptive multi-task network for edge deployment in Future Internet. TAMTNet introduces Extremely Efficient Spatial Pyramid (EESP) into the shared layer to efficiently extract multi-scale temporal information. In addition, a multi-gate mixture-of-experts (MMoE) mechanism is employed after the shared layer to enhance the modeling capability of task-specific features. Furthermore, to address the difficulty of deploying deep models on resource-constrained edge devices, a joint lightweight framework combining quantization-aware training and knowledge distillation is proposed, which significantly reduces model complexity while maintaining performance. Extensive experiments conducted on the simulation and real-world over-the-air transmission datasets demonstrate that the TAMTNet model achieves excellent performance on both modulation and signal classification tasks across a wide range of signal-to-noise ratios and radio transmit gain conditions. Meanwhile, the low-bitwidth lightweight models are able to maintain classification performance comparable to the full-precision model while significantly reducing model storage and computational complexity. Full article

To address the growing congestion of the radio frequency (RF) spectrum, Cognitive Radio (CR) systems employ Automatic Modulation Classification (AMC) to dynamically optimize spectrum utilization without introducing protocol overhead. In modern Orthogonal Frequency Division Multiplexing (OFDM) standards, effective AMC requires advanced signal-processing techniques capable of accurately identifying modulation schemes under dynamic channel conditions. Therefore, maintaining robust performance under realistic environments remains a fundamental challenge. This paper evaluates how dataset scale, synthetic impairments, and hardware-induced signal impairments affect the cross-domain generalization of a Convolutional Neural Network (CNN) architecture for OFDM Automatic Modulation Classification (AMC), using 2D amplitude-phase histograms for signal representation. To assess these effects, the CNN is trained on five distinct datasets, encompassing both synthetically generated signals with varying scales and synchronization impairments, as well as a conducted hardware dataset. The cross-domain generalization of the trained models is assessed by evaluating them on a completely unseen indoor Over-The-Air (OTA) dataset collected across 13 distinct positions. Statistical analysis demonstrates that the large-scale synchronization-impaired synthetic dataset achieves the best generalization performance, reaching a mean indoor OTA accuracy of 93.36% and outperforming the limited-size conducted hardware dataset. Overall, this study demonstrates the critical role of data-generation strategies and establishes a robust baseline for achieving reliable cross-domain generalization of CNN-based AMC. Full article

The evolution toward 6G communications requires integrating Tiny Machine Learning (TinyML) principles to enable intelligent, energy-efficient, and adaptable signal processing at the network edge. However, current receiver architectures face a fundamental trade-off: classical model-driven designs, while naturally efficient due to their basis in communication theory, lack the flexibility to adapt to varying channel conditions. Meanwhile, fully data-driven deep-learning-based approaches break the stringent resource constraints of TinyML. This paper introduces the tiny neural receiver (TNR), a pioneering architecture that bridges these paradigms by integrating model-based signal processing with lightweight neural optimization to overcome this challenge. The TNR’s primary contribution is its unique hybrid design, which combines the efficiency and interpretability of traditional theory-based receivers with the ability to adapt to different contexts using trainable neural components. This integration occurs within resource budgets that align with TinyML specifications. Experimental results show that the TNR achieves a 5 dB SNR reduction at a target block error rate of ${10}^{-4}$. The reported 5 dB SNR gain is a direct result of our resource-aware design framework, which selectively applies lightweight neural optimization to only the most impactful receiver blocks (channel estimation and decoding) to maximize gain without exceeding TinyML complexity limits. This achievement is further supported by an end-to-end training protocol that uses 15,000 iterations of over-the-air data to fine-tune these parameters for the specific static 3.5 GHz propagation channel and OFDM configuration evaluated. Furthermore, the TNR’s modular design enables flexible deployment across a range of 6G scenarios, from mobile broadband to mission-critical IoT. This establishes the TNR as a promising framework for AI-native 6G receivers. Full article

Over-the-air federated learning (AirFL) enables distributed model training across wireless edge devices, preserving data privacy and minimizing bandwidth usage. However, challenges such as channel noise, non-identically distributed data, limited computational resources, and small local datasets lead to distorted model updates, inconsistent global models, increased training latency, and overfitting, all of which reduce accuracy and efficiency. To address these issues, we propose the Semantic Anti-Interference Aggregation (SAIA) framework, which integrates a semantic autoencoder, component-wise median aggregation, validation accuracy weighting, and data augmentation. First, a semantic autoencoder compresses model parameters into low-dimensional vectors, maintaining high signal quality and reducing communication costs. Second, component-wise median aggregation minimizes noise and outlier impact, ideal for AirFL as it avoids mean-based aggregation’s noise sensitivity and complex methods’ high computation. Third, validation accuracy weighting aligns updates from non-identically distributed data to ensure consistent global models. Fourth, data augmentation doubles dataset sizes, mitigating overfitting and reducing variance. Experiments on MNIST demonstrate that SAIA achieves an accuracy of approximately 96% and a loss of 0.16, improving accuracy by 3.3% and reducing loss by 39% compared to conventional federated learning approaches. With reduced computational and communication overhead, SAIA ensures efficient training on resource constrained IoT devices. Full article

As IoT (internet of things) devices grow in prominence, safeguarding them from cyberattacks is becoming a pressing challenge. To bootstrap IoT security, device identification or authentication is crucial for establishing trusted connections among devices without prior trust. In this regard, radio frequency fingerprinting (RFF) is gaining attention because it is more efficient and requires fewer computational resources compared to resource-intensive cryptographic methods, such as digital signatures. RFF works by identifying unique manufacturing defects in the radio circuitry of IoT devices by analyzing over-the-air signals that embed these imperfections, allowing for the identification of the transmitting hardware. Recent studies on RFF often leverage advanced classification models, including classical machine learning techniques such as K-Nearest Neighbor (KNN) and Support Vector Machine (SVM), as well as modern deep learning architectures like Convolutional Neural Network (CNN). In particular, CNNs are well-suited as they use multidimensional mapping to detect and extract reliable fingerprints during the learning process. However, a significant limitation of these approaches is that they require large datasets and necessitate retraining when new devices not included in the initial training set are added. This retraining can cause service interruptions and is costly, especially in large-scale IoT networks. In this paper, we propose a novel solution to this problem: RFF using Siamese networks, which eliminates the need for retraining and allows for seamless authentication in IoT deployments. The proposed Siamese network is trained using in-phase and quadrature (I/Q) samples from 10 different Software-Defined Radios (SDRs). Additionally, we present a new algorithm, the Similarity-Based Embedding Classification (SBEC) for RFF. We present experimental results that demonstrate that the Siamese network effectively distinguishes between malicious and trusted devices with a remarkable 98% identification accuracy. Full article

Over-the-air federated learning (Air-FL) has emerged as a promising paradigm that integrates communication and learning, which offers significant potential to enhance model training efficiency and optimize communication resource utilization. This paper addresses the challenge of interference management in multi-cell Air-FL systems, focusing on parallel multi-task scenarios where each cell independently executes distinct training tasks. We begin by analyzing the impact of aggregation errors on local model performance within each cell, aiming to minimize the cumulative optimality gap across all cells. To this end, we formulate an optimization framework that jointly optimizes device transmit power and denoising factors. Leveraging the Pareto boundary theory, we design a centralized optimization scheme that characterizes the trade-offs in system performance. Building upon this, we propose a distributed power control optimization scheme based on interference temperature (IT). This approach decomposes the globally coupled problem into locally solvable subproblems, thereby enabling each cell to adjust its transmit power independently using only local channel state information (CSI). To tackle the non-convexity inherent in these subproblems, we first transform them into convex problems and then develop an analytical solution framework grounded in Lagrangian duality theory. Coupled with a dynamic IT update mechanism, our method iteratively approximates the Pareto optimal boundary. The simulation results demonstrate that the proposed scheme outperforms baseline methods in terms of training convergence speed, cross-cell performance balance, and test accuracy. Moreover, it achieves stable convergence within a limited number of iterations, which validates its practicality and effectiveness in multi-task edge intelligence systems. Full article

Drivers’ facial expression recognition systems play a pivotal role in Advanced Driver Assistance Systems (ADASs) by monitoring emotional states and detecting fatigue or distractions in real time. However, deploying such systems in resource-constrained environments like vehicles requires lightweight architectures to ensure real-time performance, efficient model updates, and compatibility with embedded hardware. Smaller models significantly reduce communication overhead in distributed training. For autonomous vehicles, lightweight architectures also minimize the data transfer required for over-the-air updates. Moreover, they are crucial for their deployability on hardware with limited on-chip memory. In this work, we propose a novel Dual Attention Lightweight Deep Learning (DALDL) approach for drivers’ facial expression recognition. The proposed approach combines the SqueezeNext architecture with a Dual Attention Convolution (DAC) block. Our DAC block integrates Hybrid Channel Attention (HCA) and Coordinate Space Attention (CSA) to enhance feature extraction efficiency while maintaining minimal parameter overhead. To evaluate the effectiveness of our architecture, we compare it against two baselines: (a) Vanilla SqueezeNet and (b) AlexNet. Compared with SqueezeNet, DALDL improves accuracy by 7.96% and F1-score by 7.95% on the KMU-FED dataset. On the CK+ dataset, it achieves 8.51% higher accuracy and 8.40% higher F1-score. Against AlexNet, DALDL improves accuracy by 4.34% and F1-score by 4.17% on KMU-FED. Lastly, on CK+, it provides a 5.36% boost in accuracy and a 7.24% increase in F1-score. These results demonstrate that DALDL is a promising solution for efficient and accurate emotion recognition in real-world automotive applications. Full article

In this paper, we present a multi-sensor platform for predictive maintenance featuring hybrid long-range (LoRa) and 5G connectivity. This hybrid approach combines LoRa’s low-power transmission for energy efficiency with 5G’s real-time data capabilities. The hardware platform integrates multiple sensors to monitor machine health parameters, with data analyzed on the device using pre-trained AI models to assess the machine’s condition. Inferences are transmitted via LoRa to the operator for maintenance scheduling, while a cloud application tracks and stores sensor data. Periodic sensor data bursts are sent via 5G to update the AI model, which is then delivered back to the platform through over-the-air (OTA) updates. We provide a comprehensive overview of the hardware architecture, along with an in-depth analysis of the data generated by the sensors, and its processing methodology. However, the data analysis and the software for ventilation control and its predictive capabilities are not the focus of this paper and are not presented. Full article

Although the U.S. makes up only 5% of the global population, it accounts for approximately 31% of public mass shootings. Gun violence and mass shootings not only result in loss of life and injury but also inflict lasting psychological trauma, cause property damage, and lead to significant economic losses. We recently developed and published an embedded system prototype for detecting gunshots in an indoor environment. The proposed device can be attached to the walls or ceilings of schools, offices, clubs, places of worship, etc., similar to smoke detectors or night lights, and they can notify the first responders as soon as a gunshot is fired. The proposed system will help to stop the shooter early and the injured people can be taken to the hospital quickly, thus more lives can be saved. In this project, a new custom dataset of blank gunshot sounds is recorded, and a deep learning model using both time and frequency domain features is trained to classify gunshot and non-gunshot sounds with 99% accuracy. The previously developed system suffered from several security and privacy vulnerabilities. In this research, those vulnerabilities are addressed by implementing secure Message Queuing Telemetry Transport (MQTT) communication protocols for IoT systems, better authentication methods, Wi-Fi provisioning without Bluetooth, and over-the-air (OTA) firmware update features. The prototype is implemented in a Raspberry Pi Zero 2W embedded system platform and successfully tested with blank gunshots and possible false alarms. Full article

In trainable wireless communications systems, the use of deep learning for over-the-air training aims to address the discontinuity in backpropagation learning caused by the channel environment. The primary methods supporting this learning procedure either directly approximate the backpropagation gradients using techniques derived from reinforcement learning, or explicitly model the channel environment by training a generative channel model. In both cases, over-the-air training of transmitter and receiver requires a feedback channel to sound the channel environment and obtain measurements of the learning objective. The use of continuous feedback not only demands extra system resources but also makes the training process more susceptible to adversarial attacks. Conversely, opting for a feedback-free approach to train the models over the forward link, exclusively on the receiver side, could pose challenges to reliably end the training process without intermittent testing over the actual channel environment. In this article, we propose a novel method for the over-the-air training of wireless communication systems that does not require a feedback channel to train the transmitter and receiver. Random samples are transmitted through the channel environment to train a mixture density network to approximate the channel distribution on the receiver side of the network. The transmitter and receiver models are trained with the resulting channel model, and the transmitter can be deployed after training. We show that the block error rate measurements obtained with the simulated channel are suitable for monitoring as a stopping criterion during the training process. The resulting method is demonstrated to have equivalent performance to the end-to-end autoencoder training on small message sequences. Full article

Wireless communications systems are traditionally designed by independently optimising signal processing functions based on a mathematical model. Deep learning-enabled communications have demonstrated end-to-end design by jointly optimising all components with respect to the communications environment. In the end-to-end approach, an assumed channel model is necessary to support training of the transmitter and receiver. This limitation has motivated recent work on over-the-air training to explore disjoint training for the transmitter and receiver without an assumed channel. These methods approximate the channel through a generative adversarial model or perform gradient approximation through reinforcement learning or similar methods. However, the generative adversarial model adds complexity by requiring an additional discriminator during training, while reinforcement learning methods require multiple forward passes to approximate the gradient and are sensitive to high variance in the error signal. A third, collaborative agent-based approach relies on an echo protocol to conduct training without channel assumptions. However, the coordination between agents increases the complexity and channel usage during training. In this article, we propose a simpler approach for disjoint training in which a local receiver model approximates the remote receiver model and is used to train the local transmitter. This simplified approach performs well under several different channel conditions, has equivalent performance to end-to-end training, and is well suited to adaptation to changing channel environments. Full article

The emergence of Industry 4.0 has revolutionized the industrial sector, enabling the development of compact, precise, and interconnected assets. This transformation has not only generated vast amounts of data but also facilitated the migration of learning and optimization processes to edge devices. Consequently, modern industries can effectively leverage this paradigm through distributed learning to define product quality and implement predictive maintenance (PM) strategies. While computing speeds continue to advance rapidly, the latency in communication has emerged as a bottleneck for fast edge learning, particularly in time-sensitive applications such as PM. To address this issue, we explore Federated Learning (FL), a privacy-preserving framework. FL entails updating a global AI model on a parameter server (PS) through aggregation of locally trained models from edge devices. We propose an innovative approach: analog aggregation over-the-air of updates transmitted concurrently over wireless channels. This leverages the waveform-superposition property in multi-access channels, significantly reducing communication latency compared to conventional methods. However, it is vulnerable to performance degradation due to channel properties like noise and fading. In this study, we introduce a method to mitigate the impact of channel noise in FL over-the-air communication and computation (FLOACC). We integrate a novel tracking-based stochastic approximation scheme into a standard federated stochastic variance reduced gradient (FSVRG). This effectively averages out channel noise’s influence, ensuring robust FLOACC performance without increasing transmission power gain. Numerical results confirm our approach’s superior communication efficiency and scalability in various FL scenarios, especially when dealing with noisy channels. Simulation experiments also highlight significant enhancements in prediction accuracy and loss function reduction for analog aggregation in over-the-air FL scenarios. Full article

Multi-task learning (MTL) is a paradigm to learn multiple tasks simultaneously by utilizing a shared network, in which a distinct header network is further tailored for fine-tuning for each distinct task. Personalized federated learning (PFL) can be achieved through MTL in the context of federated learning (FL) where tasks are distributed across clients, referred to as personalized federated MTL (PF-MTL). Statistical heterogeneity caused by differences in the task complexities across clients and the non-identically independently distributed (non-i.i.d.) characteristics of local datasets degrades the system performance. To overcome this degradation, we propose FedGradNorm, a distributed dynamic weighting algorithm that balances learning speeds across tasks by normalizing the corresponding gradient norms in PF-MTL. We prove an exponential convergence rate for FedGradNorm. Further, we propose HOTA-FedGradNorm by utilizing over-the-air aggregation (OTA) with FedGradNorm in a hierarchical FL (HFL) setting. HOTA-FedGradNorm is designed to have efficient communication between the parameter server (PS) and clients in the power- and bandwidth-limited regime. We conduct experiments with both FedGradNorm and HOTA-FedGradNorm using MT facial landmark (MTFL) and wireless communication system (RadComDynamic) datasets. The results indicate that both frameworks are capable of achieving a faster training performance compared to equal-weighting strategies. In addition, FedGradNorm and HOTA-FedGradNorm compensate for imbalanced datasets across clients and adverse channel effects. Full article

With the development of ship intelligence, the frequency of upgrading the marine engine room simulator, which is essential for crew training, has increased. Traditionally, the data processing unit (DPU) of the marine engine room simulator is upgraded by manually downloading the firmware. This makes the hardware maintenance high-cost. In this paper, we first propose a WAN-based firmware upgrade system to enable secure over-the-air upgrades of DPUs and reduce operation and maintenance costs. A distributed hardware structure is given to manage DPU in the simulator via the Internet. We have designed two methods of firmware upgrades, automatic upgrades and remote upgrades. In automatic upgrades, the DPU can download new firmware upgrades from the web server through the router. By designing a series of mechanisms including code rollback, code backup and code confirmation, the In-Application Programming (IAP) technique is realized through the Internet. Firmware upgrades have good fault tolerance mechanisms to ensure that the emulator can still work in the event of an upgrade error. In remote upgrades, we upgrade the DPU firmware through the remote control center. We assessed the performance of the system by measuring the success rate of DPU upgrades, upgrade time and performance after the upgrade. The results show that the DPU upgrade success rate is close to 100% and performance is as good as expected. The results show that the remote firmware upgrade system proposed in this paper is reliable and practical. Full article