Cheng Guo

With the rapid advancement of wireless communication technologies and the growing demand for accurate location-based services, the localization accuracy of mobile devices in 6G networks has become increasingly important. Existing single-feature fingerprint localization methods face several limitations, such as susceptibility to multipath effects, non-line-of-sight propagation, and the complexity of diverse environments. To address these challenges, this paper proposes a novel multi-feature hierarchical weighted K-Nearest Neighbor (HWKNN) regression algorithm for 6G localization, leveraging base station data. This method optimizes the Weighted K-Nearest Neighbor (WKNN) algorithm by assigning different weights to multiple signal features, improving robustness and accuracy. In addition to signal data limitations caused by sparse and expensive field measurements, this research introduces a Conditional Generative Adversarial Network (CGAN) to generate synthetic fingerprint data, incorporating base station coordinates as conditional inputs. Experimental results demonstrate that using CGAN-generated data reduces localization error from 31m to 15m, showcasing the method's superior performance. The key findings of the study include that multi-feature localization significantly enhances robustness compared to single-feature methods, the HWKNN algorithm effectively adapts to signal fluctuations by assigning feature-specific weights, and the integration of CGAN-generated data improves localization accuracy while reducing the need for extensive field data collection. This research makes a significant contribution to 6G localization by combining advanced machine learning techniques with optimized fingerprint localization methods, offering both practical and engineering value for future networks.

In this paper, we study a multiple-input-multiple-output (MIMO) non-orthogonal multiple access (NOMA) downlink system, where a base station employs beamforming to transmit multiple data streams simultaneously to a central user and a cell-edge user. Over each beam, the orthogonal frequency division multiplexing (OFDM) modulated signals intended for both users are superimposed and then transmitted. Because of beamforming and OFDM modulation, the central user may have weaker beams compared with the cell-edge user. This causes the unsuccessful successive interference cancellation (SIC). To solve this problem, we derive the necessary and sufficient conditions to ensure the successful SIC for arbitrary beamforming matrices. Based on these conditions, we design a specialized beamforming structure where signals over weak beams can be orthogonally separated from those over strong ones. We propose that joint encoding and decoding are applied to signals over weak beams and similarly to those over strong ones. To optimize the beamforming matrices, we propose a constrained convex concave procedure based algorithm and a matrix fractional programming based algorithm. It is verified through simulation results that the proposed scheme performs better than the conventional OFDM-NOMA scheme.

Non-orthogonal multiple access (NOMA) is considered as an important enabling technique for the sixth generation wireless network. In this paper, we study a secure orthogonal frequency division multiplexing (OFDM)-NOMA downlink system, which combines OFDM modulation and NOMA technique. In the system, the central user (CU) is an entrusted user and the cell-edge user (EU) is a potential eavesdropper. Due to the use of OFDM modulation, the CU may have weak subcarriers and the EU may have strong subcarriers. Our objective is to maximize both the achievable secrecy rate of CU and achievable rate of EU through power allocation optimization. For the non-convex optimization problem, we propose a sequential parametric convex approximation (SPCA)-based algorithm, a Lagrangian dual transformation (LDT)-based algorithm, and a prime decomposition-based algorithm. Simulation results demonstrate that the proposed LDT-based and prime decomposition-based algorithms, while have much lower computation complexity than the SPCA-based algorithm, achieve the same performance as the latter. Furthermore, it is found that our proposed OFDM-NOMA system outperforms the conventional OFDM-orthogonal multiple access system.

Mobile edge computing (MEC)-assisted non-orthogonal multiple access (NOMA) network has great potential to support real-time computing with the lower power consumption and network latency, since it leverages the computation capacities at the access point and power domain multiplexing technique. However, with the explosive growth of users in massive access, the power consumption and network latency for data offloading will inevitably increase. Conventional network ignoring the specific service requirement from different levels of users could severely jeopardize quality of service for the massive access NOMA network. To fill this gap, this work adopts the layered-division-multiplexing (LDM) structure, and jointly optimizes the beamforming, computation frequency, and power allocation to minimize the system power consumption under the alternating minimization framework. Simulation results demonstrate the convergence behavior of the proposed algorithm, and the performance gains from the proposed MEC-assisted NOMA network with LDM technique over the other benchmark networks.

In this paper, we propose a novel semantic digital analog converter (sDAC) for the compatibility between semantic and digital communications. Most of the current semantic communication systems rely primarily on analog modulation, limiting their integration with digital communication systems, which are more common in practice. In fact, traditional quantization methods are unsuitable for semantic communication because they do not account for semantic information within symbols. These factors block the wide application of the semantic communication. To address these challenges, sDAC is proposed. It is a simple yet efficient and generative module used to realize digital and analog bi-directional conversion. The entire process is independent of any specific semantic model, modulation methods, or channel conditions. In the experiment section, the performance of sDAC is tested across different semantic models, semantic tasks, modulation methods, channel conditions and quantization orders. Test results show that the proposed sDAC has great generative properties and channel robustness.

This article investigates deploying semantic edge inference systems for performing a common image clarification task. In particular, each system consists of multiple Internet of Things (IoT) devices that first locally encode the sensing data into semantic features and then transmit them to an edge server for subsequent data fusion and task inference. The inference accuracy is determined by efficient training of the feature encoder/decoder using labeled data samples. Due to the difference in sensing data and communication channel distributions, deploying the system in a new environment may induce high costs in annotating data labels and retraining the encoder/decoder models. To achieve cost-effective transferable system deployment, we propose an efficient domain adaptation method for semantic edge inference systems (DASEIN) that can maintain high inference accuracy in a new environment without the need for labeled samples. Specifically, DASEIN exploits the task-relevant data correlation between different deployment scenarios by leveraging the techniques of unsupervised domain adaptation and knowledge distillation. It devises an efficient two-step adaptation procedure that sequentially aligns the data distributions and adapts to the channel variations. Numerical results show that, under a substantial change in sensing data distributions, the proposed DASEIN outperforms the best-performing benchmark method by 7.09% and 21.33% in inference accuracy when the new environment has similar or 25 dB lower channel signal to noise power ratios (SNRs), respectively. This verifies the effectiveness of the proposed method in adapting both data and channel distributions in practical transfer deployment applications.

This paper investigates deploying semantic edge inference systems for performing a common image clarification task. In particular, each system consists of multiple Internet of Things (IoT) devices that first locally encode the sensing data into semantic features and then transmit them to an edge server for subsequent data fusion and task inference. The inference accuracy is determined by efficient training of the feature encoder/decoder using labeled data samples. Due to the difference in sensing data and communication channel distributions, deploying the system in a new environment may induce high costs in annotating data labels and re-training the encoder/decoder models. To achieve cost-effective transferable system deployment, we propose an efficient Domain Adaptation method for Semantic Edge INference systems (DASEIN) that can maintain high inference accuracy in a new environment without the need for labeled samples. Specifically, DASEIN exploits the task-relevant data correlation between different deployment scenarios by leveraging the techniques of unsupervised domain adaptation and knowledge distillation. It devises an efficient two-step adaptation procedure that sequentially aligns the data distributions and adapts to the channel variations. Numerical results show that, under a substantial change in sensing data distributions, the proposed DASEIN outperforms the best-performing benchmark method by 7.09% and 21.33% in inference accuracy when the new environment has similar or 25 dB lower channel signal to noise power ratios (SNRs), respectively. This verifies the effectiveness of the proposed method in adapting both data and channel distributions in practical transfer deployment applications.

Semantic communication is an effective technological approach for the integration of intelligence and communication, enabling more efficient and context-aware data transmission. In this paper, we propose a bit-conversion-based semantic communication transmission framework to ensure compatibility with existing wireless systems. Specifically, a series of physical layer processing modules in end-to-end transmission are designed. Additionally, we develop a semantic communication simulator to implement and evaluate this framework. To optimize the performance of this framework, we introduce a novel physical layer metric, termed Integer Error Rate (IER), which provides a more suitable evaluation criterion for semantic communication compared to the conventional bit error rate (BER). On the basis of the IER, a minimum Manhattan distance constellation mapping scheme is proposed, which can improve the transmission quality of semantic communication under the same BER condition. Furthermore, we propose a hybrid joint source–channel coding (JSCC) and separate source–channel coding (SSCC) transmission scheme. This scheme decouples the semantic quantization output from the modulation order by segmenting the bits to be transmitted. Simulation results demonstrate that the hybrid JSCC/SSCC transmission scheme can improve the semantic performance, such as the Peak Signal-to-Noise Ratio (PSNR), in low Signal-to-Noise Ratio (SNR) environments while reducing bandwidth usage by up to 50% compared to the benchmark scheme.

Semantic communication is an effective technological approach for the integration of intelligence and communication, enabling more efficient and context-aware data transmission. In this paper, we propose a bit-conversion-based semantic communication transmission framework to ensure the compatibility with existing wireless system. Specifically, a series of physical-layer processing modules in the end-to-end transmission are designed. Additionally, we develop a semantic communication simulator to implement and evaluate this framework. To optimize the performance of this framework, we introduce a novel physical-layer metric, termed Integer Error Rate (IER), which provides a more suitable evaluation criterion for semantic communication compared to the conventional Bit Error Rate (BER). On the basis of IER, a minimum Manhattan distance constellation mapping scheme is proposed, which can improve the transmission quality of semantic communication under the same BER condition. Furthermore, we propose a hybrid Joint Source-Channel Coding (JSCC) and Separate Source-Channel Coding (SSCC) transmission scheme. This scheme decouples the semantic quantization output from the modulation order by segmenting the bits to be transmitted. Simulation results demonstrate that the hybrid JSCC/SSCC transmission scheme can improve the semantic performance such as Peak Signal-to-Noise Ratio (PSNR) at the low Signal-to-Noise Ratio (SNR) environment while reducing bandwidth usage by up to 50% compared to the benchmark scheme.

To combine the orthogonal frequency division multiplexing (OFDM) modulation with non-orthogonal multiple access (NOMA) technique, it is required to ensure the successful successive interference cancellation procedure. Because of the fast Fourier transform (FFT) and inverse FFT employed at the OFDM transceivers, the central user may have weak subcarriers and the cell-edge user may have strong subcarriers. In this paper, we propose that for the central or cell-edge user, signals over the weak (strong) subcarriers are jointly encoded and decoded. Our objective is to maximize the weighted sum average achievable rates at both the central and cell-edge users through power allocation optimization. To solve the optimization problem, we propose a constrained convex-concave procedure (CCCP) based locally optimal solution, a Lagrangian dual transformation based locally optimal solution, and a prime decomposition based near-optimal solution. The prime decomposition based algorithm, which solves the problem based on water-filling, has extremely low computational complexity. It is shown through simulation results that the proposed scheme outperforms the conventional OFDM-NOMA scheme. Furthermore, it is found that the results obtained by the CCCP based solution, Lagrangian dual transformation based solution, and prime decomposition based solution match one another.