1 January 2021 in Wireless Communications and Mobile Computing
Signal modulation recognition is widely utilized in the field of spectrum detection, channel estimation, and interference recognition. With the development of artificial intelligence, substantial advances in signal recognition utilizing deep learning approaches have been achieved. However, a huge amount of data is required for deep learning. With increasing focus on privacy and security, barriers between data sources are sometimes difficult to break. This limits the data and renders them weak, so that deep learning is not sufficient. Federated learning can be a viable way of solving this challenge. In this article, we will examine the recognition of signal modulation based on federated learning with differential privacy, and the results show that the recognition rate is acceptable while data protection and security are being met.
4 September 2025 in IEEE Internet of Things Journal
With the rapid expansion of the Internet of Things (IoT) and the increasing unmanned devices, data transmission and sharing between unmanned agents in the Internet of Unmanned Agents (IUA) face significant challenges. Mobile Edge Computing (MEC), which extends computing power from the cloud to the network edge, has become a key technology for enabling efficient, low-latency communication services. However, with the surge in the number of terminal devices and the diversification of service requirements, traditional MEC deployment methods face challenges such as inflexible resource allocation and limited service coverage. This paper mainly researches an unmanned aerial vehicle(UAV)-assisted ground-to-air communication and computing system, constructs a multi-UAV network communication model and a computing model, and proposes a joint optimization problem of system task processing delay and energy consumption based on the total system delay and the energy consumption of the UAV. For the path planning and resource allocation problems of the multi-UAV network, an improved double-delay deep deterministic policy gradient algorithm is proposed to jointly optimize the trajectory planning, user association and task offloading strategies of the multi-agent UAV. Finally, the performance of the proposed algorithm is verified and analyzed through simulation experiments.
13 November 2025 in IEEE Internet of Things Journal
The integration of sixth-generation (6G) networks with the industrial Internet of Things (IIoT) promises unprecedented connectivity and intelligence for industrial applications. However, the massive scale of device deployment and dynamic spectrum requirements in 6G-IIoT systems pose significant challenges for reliable and trustworthy resource allocation. This article proposes a multiobjective optimization (MOO) approach that leverages cognitive radio (CR) technology and energy harvesting (EH) capabilities to ensure trustworthy resource allocation while maximizing data transmission and minimizing energy consumption. The framework incorporates imperfect spectrum sensing and interference constraints to guarantee reliable coexistence between primary and secondary networks, aligning with the reliability requirements of 6G-IIoT applications. This article proposes a multiobjective artificial hummingbird optimization algorithm based on constraint patching strategy (CPS-MOAHA) that effectively handles the complex constraints and provides Pareto optimal solutions. Simulation results demonstrate the superiority of the proposed algorithm in achieving better tradeoffs between data transmission and energy efficiency compared to existing approaches.
3 June 2026 in IEEE Transactions on Computational Social Systems
Signal emitter identification (SEI) has significant practical value in both military and civilian domains. In the military domain, it is used for target tracking and identification, while in civilian applications, it plays a crucial role in spectrum management and radio security. Current SEI technologies mainly focus on closed-set classification. However, in real-life scenarios, the electromagnetic environment is usually open and nonstatic. Existing algorithms suffer significant performance degradation when confronted with a large number of unknown class data. In the context of cyber–physical–social systems, SEI is required to break through the traditional single-node analysis model. Therefore, this article proposes an open-set recognition method based on collaborative learning of knowledge and data and distributed attention networks (CoDiNet). This method achieves robust recognition in complex electromagnetic environments through three-stage optimization involving collaborative learning of knowledge and data, distributed residual attention networks, and socialized dynamic decision-making. To validate the proposed methodology, empirical evaluations were performed on the ADS-B dataset, demonstrating that the CoDiNet framework achieves effective discrimination of both registered and emergent emitter categories under open-set conditions. The false alarm rate is significantly reduced, and the risk of misclassifying known classes as unknown classes is lowered. The method achieves a more balanced and stable performance, while also enhancing the robustness and reliability of the system. Overall, CoDiNet outperforms existing algorithms.