查看更多>>摘要：Machine learning (ML) for wireless communications and networking requires abundant, high-quality radio frequency (RF) data, yet collecting this data is often challenging and costly. To address this, we propose RF-ACCLDM (Activity Class Conditional Latent Diffusion Model), a framework designed to generate synthetic RF data for human activity sensing. Operating in latent domains, RF-ACCLDM produces RF data conditioned on activity class labels, supporting various RF technologies and modalities, including Radio Frequency Identification (RFID), WiFi Channel State Information (CSI), and Frequency-Modulated Continuous Wave (FMCW) radar. Training of the framework is universal and achieves consistent quality. This approach outperforms plain diffusion on raw RF data in terms of quality, computational efficiency, and scalability. Using the Frechet Inception Distance (FID) metric, we measure and demonstrate the fidelity of the generated data. Through extensive ablation studies, we demonstrate the effects of varying latent dimensions, noise schedules, and training configurations, validating the robustness of RF-ACCLDM. Furthermore, we evaluate the performance of our model in downstream tasks such as RF-based 3D human pose tracking and human activity recognition (HAR), where it can match or even outperform counterparts trained solely on real data. Our approach offers a scalable and cost-effective solution for enhancing ML-based schemes in wireless sensing and communications.
查看更多>>摘要：End-to-end image transmission has recently become a crucial trend in intelligent wireless communications, driven by the increasing demand for high bandwidth efficiency. However, existing methods primarily optimize the trade-off between bandwidth cost and objective distortion, often failing to deliver visually pleasing results aligned with human perception. In this paper, we propose a novel rate-distortion-perception (RDP) jointly optimized joint source-channel coding (JSCC) framework to enhance perception quality in human communications. Our RDP-JSCC framework integrates a flexible plug-in conditional Generative Adversarial Networks (GANs) to provide detailed and realistic image reconstructions at the receiver, overcoming the limitations of traditional rate-distortion optimized solutions that typically produce blurry or poorly textured images. Based on this framework, we introduce a distortion-perception controllable transmission (DPCT) model, which addresses the variation in the perception-distortion trade-off. DPCT uses a lightweight spatial realism embedding module (SREM) to condition the generator on a realism map, enabling the customization of appearance realism for each image region at the receiver from a single transmission. Furthermore, for scenarios with scarce bandwidth, we propose an interest-oriented content-controllable transmission (CCT) model. CCT prioritizes the transmission of regions that attract user attention and generates other regions from an instance label map, ensuring both content consistency and appearance realism for all regions while proportionally reducing channel bandwidth costs. Comprehensive experiments demonstrate the superiority of our RDP-optimized image transmission framework over state-of-the-art engineered image transmission systems and advanced perceptual methods.
查看更多>>摘要：Semantic Communication (SC) is an emerging technology aiming to surpass the Shannon limit. Traditional SC strategies often minimize signal distortion between the original and reconstructed data, neglecting perceptual quality, especially in low Signal-to-Noise Ratio (SNR) environments. To address this issue, we introduce a novel Generative AI Semantic Communication (GSC) system for single-user scenarios. This system leverages deep generative models to establish a new paradigm in SC. Specifically, At the transmitter end, it employs a joint source-channel coding mechanism based on the Swin Transformer for efficient semantic feature extraction and compression. At the receiver end, an advanced Diffusion Model (DM) reconstructs high-quality images from degraded signals, enhancing perceptual details. Additionally, we present a Multi-User Generative Semantic Communication (MU-GSC) system utilizing an asynchronous processing model. This model effectively manages multiple user requests and optimally utilizes system resources for parallel processing. Simulation results on public datasets demonstrate that our generative AI semantic communication systems achieve superior transmission efficiency and enhanced communication content quality across various channel conditions. Compared to CNN-based DeepJSCC, our methods improve the Peak Signal-to-Noise Ratio (PSNR) by 17.75% in Additive White Gaussian Noise (AWGN) channels and by 20.84% in Rayleigh channels.
查看更多>>摘要：Semantic communication (SC), regarded as a next-generation communication architecture that breaks through the Shannon paradigm, is considered a key technology for realizing future sixth-generation wireless networks and cognitive communications. Instead of focusing on the bit error rate, SC is dedicated to extracting abstract semantic information from original data to enhance communication efficiency for specific tasks. However, current SC systems mostly rely on symmetric architectures based on convolutional neural networks, which not only severely limits the capacity of the network but also leads to a high degree of coupling between the encoder and decoder. Additionally, it also lacks robustness in noise reference. The emergence of generative artificial intelligence (GAI) breaks this bottleneck. In this paper, we propose an asymmetric end-to-end SC architecture based on GAI, named masked joint source-channel coding (M-JSCC). In our model, the encoder serves as a universal semantic extractor, while the decoder is tailored to specific tasks. During the model training, we introduce a masking mechanism that improves the performance of M-JSCC to extract semantic information and enhances the robustness under various channel conditions. Moreover, it also endows M-JSCC with remarkable data generation abilities. Benefiting from the asymmetric architecture, the decoder no longer depends on the encoder, which allows it to be switched according to the specific requirements to better adapt to different task-oriented scenarios. Finally, comprehensive experiments demonstrate the excellent semantic understanding and communication robustness of M-JSCC.
查看更多>>摘要：Intelligent transceivers and wireless channels form an autoencoder (AE) structure, demonstrating a significant improvement in communication performance through end-to-end (E2E) learning. Recently, when the wireless channel is unknown, a residual generative adversarial network (GAN) has been utilized to simulate the real channels, thus facilitating the transmitter training. The quality of these simulated channels directly affects the adaptability of the intelligent transceiver to real-world situations. However, the training instability and the use of fully connected layers limit the residual GAN’s ability to capture effective features of real channels. To address these limitations, we propose an attention-aided residual GAN (AAR-GAN) model. This approach utilizes a convolutional neural network (CNN) to construct the GAN model and applies a squeeze-and-excitation channel attention block to CNN to automatically determine the significance of the feature channel. Furthermore, we employ a residual CNN (RCNN) to construct the transceiver, enabling smoother and more consistent learning, thus improving the communication performance. Simulation results demonstrate that our RCNN-based intelligent transceiver with the AAR-GAN model as an unknown channel significantly improves the bit error rate and block error rate for various bit lengths in the AWGN, Rayleigh fading and real DeepMIMO channels.
查看更多>>摘要：The collaboration among multiple agents demands for efficient communication. However, the observational data in the multi-agent systems are typically voluminous and redundant and pose substantial challenges to the communication system when transmitted directly. To address this issue, this paper introduces a multi-agent communication scheme based on large language model (LLM), referred to as GPT-based semantic information extraction for multi-agent communication (GMAC). This scheme utilizes an LLM to extract semantic information and leverages the generative capabilities to predict subsequent actions, thereby enabling agents to make more informed decisions. The GMAC approach significantly reduces signaling expenditure exchanged among agents by extracting key semantic data via LLM. This method not only simplifies the communication process but also effectively reduces the communication overhead by approximately 53% compared to the baseline methods. Experimental results indicate that GMAC not only improves the convergence speed and accuracy of decision-making but also substantially decreases the signaling expenditure among agents. Consequently, GMAC offers a straightforward and effective method to achieve efficient and economical communication in the multi-agent systems.
查看更多>>摘要：Radio map (RM) is a promising technology that can obtain pathloss based on only location, which is significant for 6G network applications to reduce the communication costs for pathloss estimation. However, the construction of RM in traditional is either computationally intensive or depends on costly sampling-based pathloss measurements. Although the neural network (NN)-based method can efficiently construct the RM without sampling, its performance is still suboptimal. This is primarily due to the misalignment between the generative characteristics of the RM construction problem and the discrimination modeling exploited by existing NN-based methods. Thus, to enhance RM construction performance, in this paper, the sampling-free RM construction is modeled as a conditional generative problem, where a denoised diffusion-based method, named RadioDiff, is proposed to achieve high-quality RM construction. In addition, to enhance the diffusion model’s capability of extracting features from dynamic environments, an attention U-Net with an adaptive fast Fourier transform module is employed as the backbone network to improve the dynamic environmental features extracting capability. Meanwhile, the decoupled diffusion model is utilized to further enhance the construction performance of RMs. Moreover, a comprehensive theoretical analysis of why the RM construction is a generative problem is provided for the first time, from both perspectives of data features and NN training methods. Experimental results show that the proposed RadioDiff achieves state-of-the-art performance in all three metrics of accuracy, structural similarity, and peak signal-to-noise ratio. The code is available at https://github.com/UNIC-Lab/RadioDiff.
NETL
NSTL
IEEE