Accidents often occur at sea, so effective maritime search and rescue is essential. In the current process of sea search and rescue, the operation efficiency of large search and rescue equipment is low and it can't provide stable communication link. In this paper, UAVs (Unmanned Aerial Vehicles) and USVs (Unmanned Surface Vehicles) are used to form a cognitive mobile computing network for cooperative search and rescue, and RL (Reinforcement Learning) is used to plan search path and improve communication throughput. Based on the scene of marine search and rescue, the grid method is used to model the search and rescue area. Meanwhile, an intra-group communication architecture based on UAVs and USVs is designed to assist intra-group communication by recognizing the link channel state between UAVs. Search and rescue path planning is carried out through the strategy iteration of MDP (Markov Decision Process). Furthermore, In addition, distributed RL is used to recognize the channel state and perform mobile computing, so as to optimize the data throughput in the communication group. The simulation results show that we have successfully completed the path planning task. Compared with conventional methods, RL based on different reward functions has better throughput performance under the same number of UAV auxiliary communications.

Predicting traffic flow plays an important role in reducing traffic congestion and improving transportation efficiency for smart cities. Traffic Flow Prediction (TFP) in the smart city requires efficient models, highly reliable networks, and data privacy. As traffic data, traffic trajectory can be transformed into a graph representation, so as to mine the spatio-temporal information of the graph for TFP. However, most existing work adopt a central training mode where the privacy problem brought by the distributed traffic data is not considered. In this paper, we propose a Federated Deep Learning based on the Spatial-Temporal Long and Short-Term Networks (FedSTN) algorithm to predict traffic flow by utilizing observed historical traffic data. In FedSTN, each local TFP model deployed in an edge computing server includes three main components, namely Recurrent Long-term Capture Network (RLCN) module, Attentive Mechanism Federated Network (AMFN) module, and Semantic Capture Network (SCN) module. RLCN can capture the long-term spatial-temporal information in each area. AMFN shares short-term spatio-temporal hidden information when it trains its local TFP model by the additive homomorphic encryption approach based on Vertical Federated Learning (VFL). We employ SCN to capture semantic features such as irregular non-Euclidean connections and Point of Interest (POI). Compared with existing baselines, several simulations are conducted on practical data sets and the results prove the effectiveness of our algorithm.

Vehicular content networks (VCNs), which distribute medium-volume contents to vehicles in a fully distributed manner, represent the key enabling technology of vehicular infotainment applications. In VCNs, the road-side units (RSUs) cache replicas of contents on the edge of networks to facilitate the timely content delivery to driving-through vehicles when requested. However, due to the limited storage at RSUs and soaring content size for distribution, RSUs can only selectively cache content replicas. The edge caching scheme in RSUs therefore become a fundamental issue in VCNs. This paper addresses the issue by developing an edge caching scheme in RSUs. Specifically, we first analyze the features of vehicular content requests based on the content access pattern, vehicle's velocity, and road traffic density. A model is then proposed to determine whether and where to obtain the replica of content when the moving vehicle requests it. A cross entropy based scheme is proposed accordingly to cache the efficient content at the edge of VCNs. Lastly, the performance of the proposed scheme is evaluated by extensive simulation experiments.

The upcoming development of 5G network is envisioned to offer various types of services like virtual reality/augmented reality and autonomous vehicles applications with low latency requirements in Internet of Things (IoT) networks. Mobile edge computing (MEC) has become a promising solution for enhancing the computation capacity of mobile devices at the edge of network in 5G wireless network. Additionally, multiple radio access technologies (multi-RATs) have been verified with the potential in lowering the transmission latency and energy consumption, while improving the quality of services (QoS). Benefiting from the cooperation of multi-RATs, large latency-sensitive computing service tasks (L2SC) can be offloaded by different RATs simultaneously, which has great practical significance for data partitioned oriented applications with large task sizes. In this paper, to enhance the L2SC offloading services for satisfying low latency requirements with low energy consumption, we investigate the energy-latency tradeoff problem for partial task offloading in the MEC-enhanced multi-RAT network, considering the limitation of energy and computing in capability-constrained end devices in IoT networks. Specifically, we formulated the L2SC task computation offloading problem to minimize the weighted sum of the latency cost and the energy consumption by jointly optimizing the local computing frequency, task splitting and transmit power, while guaranteeing the stringent latency requirement and the residual energy constraint. Due to the non-smoothness and non-convexity of the formulated problem with high complexity, we convert the tradeoff problem into a smooth biconvex problem, and propose an alternate convex search based algorithm, which can greatly reduce the computational complexity. Numerical simulation results show the effectiveness of the proposed algorithm with various performance parameters.

The ever-increasing growth in maritime activities with large amounts of maritime Internet of Things (M-IoT) devices and the exploration of ocean network leads to a great challenge for dealing with a massive amount of maritime data in a cost-effective and energy-efficient way. However, the resources-constrained maritime users cannot meet the high requirements of transmission delay and energy consumption, due to the excessive traffic and limited resources in maritime networks. To solve this problem, mobile edge computing is taken as a promising paradigm to help mobile devices from edge servers via computation offloading considering the different quality of services (QoS) with the complex ocean environments, resulting in energy saving and increased transmission latency. To investigate the tradeoff between latency and energy consumption in low-cost large-scale maritime communication, we formulate the offloading optimization problem and propose a two-stage joint optimal offloading algorithm, optimizing computation and communication resource allocation under limited energy and sensitive latency. At the first stage, the maritime users make the decision on whether to offload a computation considering their demands and environments. Then, the channel allocation and power allocation problem were proposed to optimize the offloading policy which coordinates with the center cloud servers at the second stage, considering the dynamic tradeoff of latency and energy consumption. Finally, numerical simulation results show the effectiveness of the proposed algorithm.

Heart disease seriously threatens human life due to high morbidity and mortality. Accurate prediction and diagnosis become more critical for early prevention, detection, and treatment. The Internet of Medical Things and artificial intelligence support healthcare services in heart disease monitoring, prediction, and diagnosis. However, most prediction models only predict whether people are sick, and rarely further determine the severity of the disease. In this article, we propose a machine learning based prediction model to achieve binary and multiple classification heart disease prediction simultaneously. We first design a Fuzzy-GBDT algorithm combining fuzzy logic and gradient boosting decision tree (GBDT) to reduce data complexity and increase the generalization of binary classification prediction. Then, we integrate Fuzzy-GBDT with bagging to avoid overfitting. The Bagging-Fuzzy-GBDT for multiclassification prediction further classify the severity of heart disease. Evaluation results demonstrate the Bagging-Fuzzy-GBDT has excellent accuracy and stability in both binary and multiple classification predictions.