Federated learning (FL) enables collaborative training of a shared model on edge devices while maintaining data privacy. FL is effective when dealing with independent and identically distributed (iid) datasets, but struggles with non-iid datasets. Various personalized approaches have been proposed, but such approaches fail to handle underlying shifts in data distribution, such as data distribution skew commonly observed in real-world scenarios (e.g., driver behavior in smart transportation systems changing across time and location). Additionally, trust concerns among unacquainted devices and security concerns with the centralized aggregator pose additional challenges. To address these challenges, this paper presents a dynamically optimized personal deep learning scheme based on blockchain and federated learning. Specifically, the innovative smart contract implemented in the blockchain allows distributed edge devices to reach a consensus on the optimal weights of personalized models. Experimental evaluations using multiple models and real-world datasets demonstrate that the proposed scheme achieves higher accuracy and faster convergence compared to traditional federated and personalized learning approaches.

With the rapid popularity of mobile devices (MDs), mobile edge computing (MEC) networks and wireless power transmission (WPT) will receive more attention. Naturally, by integrating these two technologies, the inherent energy consumption during task execution can be effectively reduced, and the collected energy can be provided to charge the MD. In this article, our research focuses on extending the battery time of MDs by maximizing the harvested energy and minimizing the consumed energy in the MEC–WPT system, which is formulated as a residual energy maximization problem and also a non-convex optimization problem. On the basis of study on maximizing the residual energy under multi-users and multi-time blocks, we propose an effective jointly optimization method (i.e., jointly optimize the energy harvesting time, task-offloading time, task-offloading size and the MDs’ CPU frequency), which combines the convex optimization method and the augmented Lagrangian to solve the residual energy maximum problem. We leverage Time Division Multiple Access (TMDA) mode to coordinate computation offloading. Simulation results show that our scheme has better performance than the benchmark schemes on maximizing residual energy. In particular, our proposed scheme is outstanding in the failure rate of multiple MDs and can adapt to the task size to minimize the failure rate.

Federated learning (FL) is a distributed framework for machine learning that enables collaborative training of a shared model across data silos while preserving data privacy. However, the FL aggregation server faces a challenge in waiting for a large volume of model parameters from selected nodes before generating a global model, which leads to inefficient communication and aggregation. Although transmitting only the signs of stochastic gradient descent (SignSGD) reduces the transmission load, it decreases model accuracy, and the time waiting for local model collection remains substantial. Moreover, the security of FL is severely compromised by prevalent poisoning, backdoor, and DDoS attacks, causing ineffective and inaccurate model training. To overcome these challenges, this paper proposes a B lockchain-based A synchronous S ign S GD (BASS) architecture for efficient and secure federated learning. By integrating a blockchain-based semi-asynchronous aggregation scheme with sign-based gradient compression, BASS considerably improves communication and aggregation efficiency, while providing resistance against attacks. Besides, a novel node-summarized sign aggregation algorithm is developed for the blockchain leaders to ensure the convergence and accuracy of the global model. An open-source prototype is developed, on top of which extensive experiments are conducted. The results validate the superiority of BASS in terms of efficiency, model accuracy, and security.

Our work focuses on the exploration of the internal relationships of signals in an individual sensor. In particular, we address the problem of not being able to evaluate such intrasensor relationships due to missing rich and explicit feature representation. To solve this problem, we propose GraphSensor, a graph attention network, with a shared-weight convolution feature encoder to generate the signal segments and learn the internal relationships between them. Furthermore, we enrich the representation of the features by utilizing a multi-head approach when creating the internal relationship graph. Compared with traditional multi-head approaches, we propose a more efficient convolution-based multi-head mechanism, which only requires $56\%$ of model parameters compared with the best multi-head baseline as demonstrated in the experiments. Moreover, GraphSensor is capable of achieving state-of-the-art performance in the electroencephalography dataset and improving the accuracy by $13.8\%$ compared to the best baseline in an inertial measurement unit (IMU) dataset.

Unmanned aerial vehicles (UAVs) have the characteristics of portability, safety, and strong adaptability. In the case of a maritime disaster, they can be used for personnel search and rescue, real-time monitoring, and disaster assessment. However, the power, computing power, and other resources of UAVs are often limited. Therefore, this paper combines a UAV and mobile edge computing (MEC), and designs a deep reinforcement learning-based online task offloading (DOTO) algorithm. The algorithm can obtain an online offloading strategy that maximizes the residual energy of the UAV by jointly optimizing the UAV’s time and communication resources. The DOTO algorithm adopts time division multiple access (TDMA) to offload and schedule the UAV computing task, integrates wireless power transfer (WPT) to supply power to the UAV, calculates the residual energy corresponding to the offloading action through the convex optimization method, and uses an adaptive $K$ method to reduce the computational complexity of the algorithm. The simulation results show that the DOTO algorithm proposed in this paper for the energy-saving goal of maximizing the residual energy of UAVs in MEC can provide the UAV with an online task offloading strategy that is superior to other traditional benchmark schemes. In particular, when an individual UAV exits the system due to insufficient power or failure, or a new UAV is connected to the system, it can perform timely and automatic adjustment without manual participation, and has good stability and adaptability.