Edge computing provides off-load computing and application services close to end-users, greatly reducing cloud pressure and communication overhead. However, wireless edge networks still face the risk of network attacks. To ensure the security of wireless edge networks, we present Federated Learning-based Attention Gated Recurrent Unit (FedAGRU), an intrusion detection algorithm for wireless edge networks. FedAGRU differs from current centralized learning methods by updating universal learning models rather than directly sharing raw data among edge devices and a central server. We also apply the attention mechanism to increase the weight of important devices, by avoiding the upload of unimportant updates to the server, FedAGRU can greatly reduce communication overhead while ensuring learning convergence. Our experimental results show that, compared with other centralized learning algorithms, FedAGRU improves detection accuracy by approximately 8%. In addition, FedAGRU's communication cost is 70% less than other federated learning algorithms, and it exhibits strong robustness against poisoning attacks. INDEX TERMS wireless edge, intrusion detection, federated learning, gated recurrent unit

Solving wireless packet retransmission problems (WPRTPs) using network coding (NC) approach is increasingly attracting research efforts. However, existing researches are almost all focused on solutions in Galois field GF(2), and consequently, the solutions found by these schemes are usually less optimal. In this paper, we focus on optimal NC‐based scheme for perfect WPRTPs (P‐WPRTPs) where, with respect to each receiver, a packet is either requested by or already known to it. The number of retransmitted packets in optimal NC‐based solutions to P‐WPRTPs is firstly analyzed and proved. Then, random network coding‐based optimal scheme (RNCOPT) is proposed for P‐WRPTPs. RNCOPT is optimal in the sense that it guarantees to obtain a valid solution with minimum number of packet retransmissions. Furthermore, in RNCOPT, each coding vector is generated using a publicly known pseudorandom function with a randomly selected seed. The seed, instead of the coding vector, is used as decoding information to be retransmitted together with the coded packet. Thus, packet overhead of RNCOPT is reduced further. Extensive simulations show that RNCOPT distinctively outperforms some previous typical schemes for P‐WPRTPs in saving the number of retransmitted packets. Copyright © 2011 John Wiley & Sons, Ltd.

No abstract

Flooding is one of the most fundamental functions in wireless sensor networks (WSNs) and has been investigated extensively. Existing flooding schemes in duty-cycle WSNs can be categorized into two categories: synchronous ones and asynchronous ones. In practice asynchronous schemes are preferable since synchronous ones introduce more complexity and overhead for necessary clock synchronization. Existing asynchronous approaches are however imperfect for reliable flooding in duty-cycle WSNs. For example, opportunistic flooding is less flexible and Asynchronous Duty-cycle Broadcasting (ADB) suffers unsatisfactory flooding latency. We propose Constructive Interferencebased Reliable Flooding (CIRF) in this paper, a novel design for reliable flooding in asynchronous duty-cycle WSNs. CIRF is integrated with the MAC protocol Receiver-Initiated MAC (RI-MAC) to improve the utilization of wireless medium and guarantee one-hop reliable transmission. The key idea of CIRF is to exploit the constructive interference feature when concurrent transmission occurs, which can be common in RI-MAC based WSNs. Simulation results indicate that CIRF achieves reliable flooding with reduced flooding latency, higher energy efficiency and delivery ratio compared to existing schemes.

Vesicoureteral reflux (VUR) is one of the most common congenital anomalies in the kidney and the urinary tract. Endoscopic subureteral injection of a bulking agent has become popular in VUR treatment due to its high success rates, few complications, and a straightforward procedure. In this study, a novel magnetic bulking agent was prepared by embedding Fe3O4 magnetic nanoparticles in cross-linked agarose microspheres with diameters of 80–250 μm and dispersing the magnetic microspheres in a hyaluronic acid hydrogel. The bulking agent has good biocompatibility and biosecurity validated by the tests of cytotoxicity, in vitro genotoxicity, animal irritation, skin sensitization, acute systemic toxicity, and pathological analysis after the injection of the bulking agent extract solution into healthy mice as well as injection of the bulking agent into VUR rabbits. The VUR rabbits were created by incising the roof of the intravesical ureter to enlarge the ureteral orifice. The success rate of the bulking agent in treating VUR rabbits using a subureteral transurethral injection technique was 67% (4/6) or 80% (4/5, excluding the unfinished rabbit), and no migrated particles were found in the organs of the rabbits. The transverse relaxation rate of the bulking agent was 104 mM−1s−1. After injection, the bulking agent was long-term trackable through magnetic resonance imaging that can help clinicians to inspect the VUR treatment effect. For the first time, this study demonstrates that the bulking agent with a long-term stable tracer is promising for endoscopic VUR treatment.