The health management of railway vehicles is crucial to secure safety and efficiency in the long-term operation of high-speed trains. Meanwhile, complex components put forward a higher requirement for the robustness of condition monitoring systems, especially abilities to identify unexpected faults. The misidentification of infrequent faults could lead to unpredictable consequences to the vehicle's safety. This paper proposes a novel method for detecting unexpected faults of high-speed train bogie based on Bayesian deep learning. First, a Monte Carlo-Based perturbation is imposed on input samples, which can magnify the difference between unexpected faults and known ones. Then, through dropout-based Bayesian deep learning, the diagnosis result can be obtained as well as a Bayesian indicator of whether the anomalies belong to known classes. The proposed method can capture the uncertainty of model outputs and identify unexpected faults, with only a few samples of unexpected anomalies for calibration. Also, it is compatible with most existing neural network structures. The experiments compare the proposed method with existing methods on two real-world applications, which demonstrates the effectiveness and superiority of the proposed scheme.

The unmanned aerial vehicle (UAV) technique combined with the cellular network is a promising and reliable technique to provide a low-cost, flexible, and easy-to-expandable network. In this article, we propose a UAV-assisted cooperative transmission network (UCTN), where UAVs and the base station (BS) transmit data jointly through the cooodination of the software-defined network (SDN). As the UAV has limited on-board energy, we aim to maximize the network energy efficiency (EE) by jointly optimizing the UAV–user association, UAV location, BS resource allocation, and the load allocation between the two systems. The formulated problem is a mixed-integer nonconvex optimization problem, which is intractable. To solve it, alternative optimization (AO) and Dinkelbach’s method are adopted to recast the original problem into a tractable form. After that, the corresponding problem is divided into three subproblems and can be solved iteratively. An energy-constrained coalition game is proposed to solve the UAV–user association problem, and the UAV hovering point is carefully designed to balance the coalition serving time. Furthermore, the successive convex approximation (SCA) technique is adopted to optimize the BS transmit power and bandwidth allocation. Numerical experiments demonstrate that the proposed algorithm achieves significant performance gains over other benchmark schemes.

Licensed Assisted Access (LAA) is considered one of the latest groundbreaking innovations to provide high performance in future 5G. Coexistence schemes such as Listen Before Talk (LBT) and Carrier Sensing and Adaptive Transmission (CSAT) have been proven to be good methods to share spectrums, and they are WiFi friendly. In this paper, a modified LBT-based CSAT scheme is proposed which can effectively reduce the collision at the moment when Long Term Evolution (LTE) starts to transmit data in CSAT mode. To make full use of the valuable spectrum resources, the throughput of both LAA and WiFi systems should be improved. Thus, a two-layer Coalition-Auction Game-based Transaction (CAGT) mechanism is proposed in this paper to optimize the performance of the two systems. In the first layer, a coalition among Access Points (APs) is built to balance the WiFi stations and maximize the WiFi throughput. The main idea of the devised coalition forming is to merge the light-loaded APs with heavy-loaded APs into a coalition; consequently, the data of the overloaded APs can be offloaded to the light-loaded APs. Next, an auction game between the LAA and WiFi systems is used to gain a win–win strategy, in which, LAA Base Station (BS) is the auctioneer and AP coalitions are bidders. Thus, the throughput of both systems are improved. Simulation results demonstrate that the proposed scheme in this paper can improve the performance of both two systems effectively.

This work studies a practical scenario where the unmanned aerial vehicle (UAV) is dispatched from the data center to collect the data from the Internet of Things (IoT) devices and return to the data center. These IoT devices with different amounts of data and are sparsely located in an untraveled area. In this scenario, we consider minimizing the UAV's cruise time by jointly optimizing the clustering strategy of the IoT devices, the association strategy between the UAV and the IoT devices, the UAV's trajectory, and the bandwidth allocation strategy. Traditionally, the minimal cruise time is obtained by visiting all IoT devices one by one and this will lead to huge cost. To address this problem, affinity propagation (AP) algorithm is proposed to cluster all these IoT devices first of all. Then, to avoid visiting all devices one by one and realize parallel computation of data collection time, the entire UAV's flying process is divided into two phases, namely, the inter-cluster phase and the intra-cluster phase. For the inter-cluster phase, the minimal cruise time is formulated to minimize total distance among clusters using the traveling salesman problem with a neighborhood (TSPN)-based algorithm. Subsequently, for the intra-cluster phase, we formulate the collecting time minimization problem in each cluster as a mix-integer non-convex optimization problem. To address these issues, we design a two-loop algorithm involving the bisection search, the altering optimization (AO), and the successive convex approximation (SCA) methods. Simulation results validate the effectiveness of our proposed scheme.