Self-supervised learning, which leverages unlabeled data to learn useful feature representations by constructing auxiliary tasks, has been widely explored in few-shot scene classification to improve the feature representation and generalization capabilities of deep models in scarce data. However, most of the current related work adopts specific self-supervised auxiliary tasks (SSATs) for combinatorial improvement, and does not explore the intrinsic connection between different pretext tasks. In practice, the linkage of SSATs is complex, and the optimization of task-sharing parameters by minimizing linear combinations of losses can be conflicting. In addition, although a single combination of SSAT can improve certain performance on the baseline, it is not the personalized optimal solution on various remote sensing datasets with diverse properties. In this article, we propose a collaborative self-supervised evolution (so-called CSENet) framework for few-shot remote sensing scene classification to automatically search for appropriate weights in balancing the task conflicts. In contrast to most existing methods, which consider all SSATs to be equally efficacious or fixed-weighted for the few-shot main task, CSENet achieves autonomous co-evolutionary optimization by encoding arbitrary self-supervised weights. Specifically, the complex self-supervised combinations for different remote sensing data are transformed into an evolutionary optimization problem, where chromosomes with weighting variables obtain the optimal combination with genetic operators. Based on the transfer learning few-shot training paradigm, CSENet first efficiently searches for optimal self-supervised combinations with potential by the proposed automatic collaborative evolution strategy and automatically adjusts the weights without manual settings. Importantly, CSENet provides both inductive and transductive inference, and supports the embedding of arbitrary SSATs. The effectiveness of the proposed framework is demonstrated by state-of-the-art (SOTA) results on three benchmark datasets.

Self-supervised learning is an effective way to solve model collapse for few-shot remote sensing scene classification (FSRSSC). However, most self-supervised contrastive learning auxiliary tasks perform poorly on the high interclass similarity problem in FSRSSC. Furthermore, it is time-consuming and computationally expensive to obtain the best combination among numerous self-supervised auxiliary tasks. In practical applications, we may encounter difficulties in remote sensing data acquisition and labeling, while most FSRSSC studies only focus on the former. To alleviate the above problems, we propose a multiform ensemble self-supervised learning (MES2L) framework for FSRSSC in this article. Based on the transfer learning-based few-shot scheme, we design a novel global–local contrastive learning auxiliary task to solve the low interclass separability problem. The self-attention mechanism is designed in the local contrast features to investigate the intrinsic associations between different remote sensing scene objectives. We also present a multiform ensemble enhancement (MEE) training method. Ensemble enhancement involves the concatenation of features extracted from different backbones trained by a combination of multiform self-supervised auxiliary tasks. MEE can not only be regarded as a more straightforward alternative to knowledge distillation but also can achieve an effective compromise between expensive computational cost and classification accuracy. In addition, we provide two scene classification schemes of inductive and transductive settings, corresponding to solving the difficulties of remote sensing data acquisition and labeling. The proposed network achieves state-of-the-art results on three benchmark FSRSSC datasets. The potential of the MES2L framework is also demonstrated in combination with classical metalearning-based and metric learning-based few-shot algorithms.

With the continuous advancement of computer network communication technology, traditional wired and wireless networks are limited by cables and base stations, and are not applicable in some application scenarios. Therefore, mobile wireless communication methods have attracted more and more attention. Due to its dynamic topology and self-organizing without center, the self-organizing network can form a mobile temporary multi-hop mobile communication network through multiple wireless communication devices, which can well meet the above requirements. At present, research on self-organizing networks mainly focuses on routing protocols. The main types are based on network topology information and location information. This paper designs a routing algorithm based on link reliability. The algorithm fully considers the self-organizing network link information, and models the node's sending and receiving work as a Markov decision process, and uses Q-learning to demodulate. This article used NS2 for network simulation and analysis and comparison of performance indicators with traditional routing algorithms.

In Named Data Networking (NDN), the processing of the packet is based on the data rather than the communication endpoint. It's very suitable for the core demand of content sharing on the internet today. However, there are still some problems to be dealt with, including mobility support of the producer. By analyzing existing solutions, we put forward a solution finding MCS (Mobile Content Source) passively by HR(Home Repository) and leading interest packets to find MCS actively in the local scope at the same time to speed up to search MCS and to support NDN producer mobility. Triangle routing problem in single HR and low efficiency problem can be based on this solution. Experimental results show that our scheme does better in reducing delay with low handoff cost than other typical solutions.

The reliability of the power communication network is important to the stable operation of the power grid. Existing studies on the reliability evaluation of power communication networks rarely consider the factors of environmental changes. In fact, changes in the working environment of power service routing will affect the normal operation of the network. This paper studies the reliability evaluation method of power communication network based on environmental factors. The normal cloud model method is used to model the multiple environmental factors in the power communication network, and a controlled hybrid stochastic petri network is used to model and analyze the power transmission system with backup route. In simulation experiments, we compare our algorithm with the contrast algorithm that not considering the impact of environmental factors. The results show that our algorithm can well reflect the impact of changes in environmental factors on the reliability of the system, and more in line with the actual reliability changes of the power service transmission system.

Anchor user identification across social networks is a classification task which determines whether a pair of accounts from different social networks belong to the same user. It is a fundamental research of information dissemination across social networks. Based on the observation that users prefer to use similar or identical display names in different social network, some researchers utilized the similarity between display names to build models. However, due to Chinese social network setting and pronunciation and font characteristics of Chinese display names, these methods do not perform well in Chinese social network datasets. To address this problem, we analyze the display name pairs of Chinese anchor users which are obtained by a crawler build in this paper. Then we define 4 special features to extract the pronunciation and font similarities. Finally, we use Gradient Boosting to establish the identification model. The experiments based on the ground-truth datasets we obtained show that these features can improve the performance of display name-based anchor user identification between Chinese social networks.

With the development of Internet of Vehicles, vehicles establish the social relationships with other vehicles and road side units for exchanging information, which is called Social Internet of Vehicles (SIoV). Making use of the relationships, we propose a QoS-based opportunistic routing mechanism to guarantee the QoS requirement and route reliable of information transmission in this paper. First, we establish a mathematical model for QoS evaluation considering the transmission correct ratio and delay, which can accurately estimate the QoS of road section. Then, we propose the QoS-based opportunistic routing mechanism, which aims to form a reliable and robust route path. Finally, the obtained simulation results validate the accuracy and correctness of our approach.

In order to ensure users enjoying the services continuously and steadily, we need an efficient service recovery strategy to quickly recover the failed links and reconstruct the device set. In this paper, we introduce a service recovery strategy based on recovery node which can save and maintain service data flexibly. First, we give the definition of recovery node and the selection mechanism for it. Then we describe our recovery strategy in detail. At last, we make a simulation by NS-3. The effectiveness of the proposed methods is demonstrated by simulation results.

In the area of social network, bioinformatics, e-commerce and so on, the graph model is widely used to present the certain objects and the relations among them. Taking such graph model as the source data, it is significant to extract the compact informative subgraph which can best explain how the given query points are connected. Existing work considers only the connection between individual objects and the returned subgraph is unfavorable when the given query points are far distant each other in the initial graph. In the paper, we will first simplify and present the initial graph by the PeakGraph model in which the graph nodes are divided into different groups based on the density of linkages. Based on the PeakGraph model, we further extract the informative subgraph by two steps, namely local search and global search. In the former step, the local optimal subgraph is extracted for each group; in the latter step, we connect these local optimal subgraphs by some heuristic rules. Our experiments show that our algorithm achieves good performance in both accuracy and efficiency for all kinds of queries.

A significant number of applications on graph require the key relations among a group of query nodes. Given a relational graph such as social network or biochemical interaction, an informative subgraph is urgent, which can best explain the relationships among a group of given query nodes. Based on Particle Swarm Optimization (PSO), a new framework of SISP (Searching the Informative Subgraph based on PSO) is proposed. SISP contains three key stages. In the initialization stage, a random spreading method is proposed, which can effectively guarantee the connectivity of the nodes in each particle; In the calculating stage of fitness, a fitness function is designed by incorporating a sign function with the goodness score; In the update stage, the intersection-based particle extension method and rule-based particle compression method are proposed. To evaluate the qualities of returned subgraphs, the appropriate calculating of goodness score is studied. Considering the importance and relevance of a node together, we present the PNR method, which makes the definition of informativeness more reliable and the returned subgraph more satisfying. At last, we present experiments on a real dataset and a synthetic dataset separately. The experimental results confirm that the proposed methods achieve increased accuracy and are efficient for any query set.