CXChunmei Xu

Chunmei Xu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Chunmei Xu has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Data-Importance-Aware Power Allocation for Adaptive Real-Time Communication in Computer Vision Applications

    by Chunmei Xu, Yi Ma, Rahim Tafazolli, Jiangzhou Wang

    Life-transformative applications such as immersive extended reality are revolutionizing wireless communications and computer vision (CV). This paper presents a novel framework for importance-aware adaptive data transmissions, designed specifically for real-time CV applications where task-specific fidelity is critical. A novel importance-weighted mean square error (IMSE) metric is introduced as a task-oriented measure of reconstruction quality, considering sub-pixel-level importance (SP-I) and semantic segment-level importance (SS-I) models. To minimize IMSE under total power constraints, data-importance-aware waterfilling approaches are proposed to optimally allocate transmission power according to data importance and channel conditions, prioritizing sub-streams with high importance. Simulation results demonstrate that the proposed approaches significantly outperform margin-adaptive waterfilling and equal power allocation strategies. The data partitioning that combines both SP-I and SS-I models is shown to achieve the most significant improvements, with normalized IMSE gains exceeding 7 dB and 10 dB over the baselines at high SNRs (> 10 dB). These substantial gains highlight the potential of the proposed framework to enhance data efficiency and robustness in real-time CV applications, especially in bandwidth-limited and resource-constrained environments.


  • Top Cited Papers

    Generative Semantic Communications With Foundation Models: Perception-Error Analysis and Semantic-Aware Power Allocation

    by Chunmei Xu, Mahdi Boloursaz Mashhadi, Yi Ma, Rahim Tafazolli, Jiangzhou Wang

    Generative foundation models can revolutionize the design of semantic communication (SemCom) systems by enabling high fidelity exchange of semantic information at ultra-low rates. In this work, a generative SemCom framework utilizing pre-trained foundation models is proposed, where both uncoded forward-with-error and coded discard-with-error schemes are developed for the semantic decoder. Using the rate-distortion-perception theory, the relationship between regenerated signal quality and transmission reliability is characterized, which is proven to be non-decreasing. Based on this, semantic values are defined to quantify the semantic similarity between multimodal semantic features and the original source. We also investigate semantic-aware power allocation problems that minimize power consumption for ultra-low rate and high fidelity SemComs. Two semantic-aware power allocation methods are proposed by leveraging the non-decreasing property of the perception-error relationship. Based on the Kodak dataset, perception-error functions and semantic values are obtained for image tasks. Simulation results show that the proposed semantic-aware method significantly outperforms conventional approaches, particularly in the channel-coded case (up to 90% power saving).


  • Joint AP Clustering and Beamforming Design for RIS-Aided Cell-Free Networks

    by Chunmei Xu, Yuanqi Jia, Youjia Chen, Wei Huang

    Cell-free networks and reconfigurable intelligent surfaces (RIS) are two promising techniques for future wireless communications. The integration of RIS into cell-free networks, termed RIS-aided cell-free networks, offers the potential to significantly enhance network performance. However, the realization of this potential is constrained by the limited capacities of the fronthaul links. To address this challenge, we investigate the joint design of access point (AP) clustering, transmit and passive beamforming in RIS-aided cell-free networks. The objective is to maximize the weighted sum-rate performance while minimizing the number of clustered APs to alleviate the fronthaul overhead. The problem is formulated in a group sparse manner, employing a mixed zero-norm/two-norm term to represent the number of the clustered APs. To solve this problem, we first approximate the mixed zero-norm/two-norm term by the mixed one-norm/two-norm term and provide its equivalent formulation by introducing receive beamforming vectors and weight parameters. Then, an iterative method is proposed based on the block coordinate descent (BCD) technique, which is guaranteed to converge to a stationary point. Simulation results demonstrate the effectiveness of the proposed method.


  • Leakage-Based Precoder Optimization and Deep Unfolding for User-Centric Cell-Free Massive MIMO

    by Chunmei Xu, Cheng Zhang, Yongming Huang, Yi Wu, Zhaohua Lu

    This paper investigates the leakage-based precoder design for user-centric cell-free massive MIMO systems. Given the clustered APs for each UE, the problem is formulated as a group sparse optimization to maximize the leakage rate under per-AP power constraints. Its equivalent formulation is derived by introducing two auxiliary variables. An iterative optimization method (IOM) is proposed based on block coordinate descent and bisection search techniques, which converges to a stationary solution. To reduce the required computations, a deep unfoldingbased method (DUBM) is developed to unfold the iterative procedure of IOM via the proposed neural network layer. Simulation results demonstrate the competitive performance of the proposed methods, with IOM achieving higher sum-rates while DUBM providing higher computational efficiency compared to the reference methods.

  • Random Aggregate Beamforming for Over-the-Air Federated Learning in Large-Scale Networks

    by Chunmei Xu, Cheng Zhang, Yongming Huang, Dusit Niyato

    Currently, there is a growing trend in deploying ubiquitous artificial intelligence (AI) applications at the network edge. As a promising framework that enables secure edge intelligence, federated learning (FL) has been paid attention, where the over-the-air computing technique has been adopted to enhance the communication efficiency. In this study, we focus on over-the-air FL over a large-scale network with numerous edge devices. Joint device selection and aggregate beamforming design is investigated under two different objectives, i.e., minimizing the aggregate error and maximizing the number of selected devices. Two combinatorial problems are formulated, which are demanding to solve especially in the large-scale network. To reduce the computational complexity, a random aggregate beamforming scheme is proposed, which employs random sampling instead of optimization to determine the aggregator beamforming vector. Notably, the implementation of the proposed scheme does not necessitate the full channel estimation. Asymptotic analysis reveals that the aggregate error asymptotically follows a Gaussian distribution, and the number of selected devices approximates a symmetrical distribution. The distribution parameters are explicitly expressed by the transmit power, the numbers of devices and selected devices. Simulation results confirm the theoretical analysis and demonstrate the effectiveness of the proposed random aggregate beamforming scheme.


  • Joint User Scheduling, Base Station Clustering, and Beamforming Design Based on Deep Unfolding Technique

    by Chunmei Xu, Yuanqi Jia, Shiwen He, Yongming Huang, Dusit Niyato

    In this paper, we investigate joint user (UE) scheduling, base station (BS) clustering and beamforming design in a dense network. To reduce the computation burden, we propose a deep unfolding UE scheduling, BS clustering and beamforming (DU-USBCB) method based on the iterative weighted minimum mean square error (WMMSE) algorithm, where the UE scheduling and BS clustering are represented by the group sparsity of the transmit beamforming vectors. The proposed DU-USBCB neural network layer comprises receive coefficient, weight and transmit beamforming vector modules, the former two of which have closed-form expressions. For the third module, the group sparse transmit beamforming vectors are obtained by multiple steps of projected gradient descent and nonlinear sparsification, where the step-sizes are learned through unsupervised learning. We also propose a distributed UE selection (DUS) algorithm, which helps reduce the computation workload. Simulation results verify the effectiveness of the proposed DU-USBCB and DUS methods. The learned step-sizes are directly applied in the testing scenarios with different numbers of UEs, BSs and antennas as well as incomplete channel state information. Besides, our proposed methods can achieve comparable performance but with about 53% and 89% computation reduction compared to the RSRP-WMMSE and SWMMSE methods respectively.


  • Open Access

    Explainable AI over the Internet of Things (IoT): Overview, State-of-the-Art and Future Directions

    by Senthil Kumar Jagatheesaperumal, Quoc-Viet Pham, Rukhsana Ruby, Zhaohui Yang, Chunmei Xu, Zhaoyang Zhang

    Explainable Artificial Intelligence (XAI) is transforming the field of Artificial Intelligence (AI) by enhancing the trust of end-users in machines. As the number of connected devices keeps on growing, the Internet of Things (IoT) market needs to be trustworthy for the end-users. However, existing literature still lacks a systematic and comprehensive survey work on the use of XAI for IoT. To bridge this lacking, in this paper, we address the XAI frameworks with a focus on their characteristics and support for IoT. We illustrate the widely-used XAI services for IoT applications, such as security enhancement, Internet of Medical Things (IoMT), Industrial IoT (IIoT), and Internet of City Things (IoCT). We also suggest the implementation choice of XAI models over IoT systems in these applications with appropriate examples and summarize the key inferences for future works. Moreover, we present the cutting-edge development in edge XAI structures and the support of sixth-generation (6G) communication services for IoT applications, along with key inferences. In a nutshell, this paper constitutes the first holistic compilation on the development of XAI-based frameworks tailored for the demands of future IoT use cases.

  • Open Access

    Hybrid Precoding for Broadband Millimeter-Wave Communication Systems With Partial CSI

    by Chunmei Xu, Riping Ye, Yongming Huang, Shiwen He, Cheng Zhang

    Millimeter-wave (mm-wave) communication systems can provide significantly higher throughput thanks to its larger bandwidth. However, due to the hardware cost and power consumptions, the hybrid analog/digital implementation tends to be more practical than the conventional full-digital one. In this paper, we propose a novel hybrid multiuser precoding design for the orthogonal frequency-division multiplexing (OFDM)-based broadband mm-wave systems with a fully connected structure and partial channel state information (CSI). Specifically, the joint analog/digital hybrid precoding design is first transformed into a sparse digital precoding problem with a given analog codebook and corresponding effective CSI. In addition, two approaches, i.e., subcarrier grouping and equal power allocation, are proposed to reduce the computational complexity. Finally, a limited feedback strategy via exploiting the dominant channel subspace is proposed to reduce the feedback overhead. Simulation results show that the proposed designs can achieve near-optimal performance of the considered hybrid mm-wave systems.