12 August 2025 in Knowledge-Based Systems
10 October 2025 in IEEE Transactions on Wireless Communications
Accurate channel state information (CSI) prediction is essential for 6G massive multiple-input multiple-output (m-MIMO) IoT systems. Deep learning models, such as Transformers, exhibit quadratic computational complexity, resulting in significant efficiency bottlenecks when processing high-dimensional, long sequences channel data in high-mobility scenarios. The Mamba architecture, distinguished by its unique selective state-space model (SSM), presents a promising solution which combines linear computational complexity with robust capabilities for modeling long-range dependencies. Building on this foundation, we propose ChannelMamba, an end-to-end model specifically designed for channel prediction. First, the model employs a dual-domain input module that captures comprehensive channel features by concurrently processing frequency-domain CSI and delay-domain channel impulse response (CIR) data. Sub-sequently, we develop a cross-path parameter-sharing strategy for the Mamba modules to efficiently capture temporal channel dynamics while enhancing model generalization. Furthermore, to address the multi-dimensional dependencies and global context inherent in channel data, we design a bidirectional Mamba module for cross-feature modeling, enhanced with a lightweight attention mechanism. Finally, extensive experimental evaluations across various standard scenarios demonstrate the significant advantages of ChannelMamba over baseline methods in terms of prediction accuracy, robustness, generalization and computational efficiency, achieving new state-of-the-art performance in channel prediction tasks.
4 June 2025 in Neurocomputing
22 September 2025 in IEEE Sensors Journal
Unmanned Aerial Vehicles (UAVs) possess high maneuverability and wide viewing angles, rendering them ideal as flying base stations for resource-constrained Internet of Things (IoT) sensors. For real-time information acquisition and sustainable energy support for numerous IoT devices, an appropriate number of UAVs are required to efficiently deployed for data and energy transfer tasks. However, existing methods face challenges in minimizing the average Age of Information (AoI) due to the complex coupling between trajectory planning and transmission scheduling decisions and the need for efficient coordination in resource-constrained UAV networks. These domain-specific challenges require specialized solutions that effectively balance information freshness and energy efficiency. To address these challenges, we first decompose the scheduling problem into two subproblems: trajectory optimization and transmission optimization. Based on this decomposition, we propose a Hierarchical Trajectory Optimization and Transmission Scheduling (HTOTS) algorithm based on hierarchical reinforcement learning. The HTOTS algorithm employs Deep Reinforcement Learning to sense environmental states in real-time and dynamically adjusts UAV flight trajectories and information acquisition, ensuring an effective balance between data and energy transfer. These subproblems are solved alternately through hierarchical reinforcement learning, which significantly reduces the complexity of each subproblem and improves convergence efficiency. Simulation results show that the proposed HTOTS algorithm outperforms existing methods in terms of average AoI and energy efficiency for various network scales and energy constraints.
2 July 2025 in IEEE Transactions on Cognitive Communications and Networking
In the context of Industry 4.0, industrial wireless communication faces significant challenges due to the complex and dynamic nature of the channel and the stringent requirements for real-time performance. Existing channel prediction methods exhibit inherent limitations in maintaining prediction accuracy and prediction task latency in heterogeneous environments characterized by both Line-of-Sight (LoS) and Non-Line-of-Sight (NLoS) scenarios. To address these concerns, we propose a Multi-Time-Scale Attention (MTSA) model for channel prediction and implement it within a novel collaborative cloud-edge architecture. Specifically, the cloud prediction model leverages a multi-task learning framework which simultaneously optimizes multiple prediction objectives, enabling high-precision heterogeneous modeling of LoS and NLoS channels. The edge prediction model incorporates a cross-layer parameter sharing mechanism and a dynamic updating strategy in response to environmental changes. To fully exploit the benefits of cloud-edge collaboration, we propose a Multi-Objective Dynamic Task Scheduling (MODTS) algorithm based on double deep Q-network, which effectively optimizes the trade-off between prediction accuracy and prediction task latency. Experimental results demonstrate that the proposed architecture significantly outperforms existing works in terms of channel prediction accuracy, real-time performance, and model robustness.