An Intrusion Alarming System Based on Self-Similarity of Network Traffic

Intrusion detection system ean make effective alarm for illegality of networkusers, which is absolutely necessarily and important to build security environment of communicationbase service According to the principle that the number of network traffic can affect the degree ofself-similar traffic, the paper investigates the variety of self-similarity resulted fromunconventional network traffic. A network traffic model based on normal behaviors of user isproposed and the Hursl parameter of this model can be calculated. By comparing the Hurst parameterof normal traffic and the self-similar parameter, we ean judge whether the network is normal or notand alarm in time.

Load Reduction Test Method of Similarity Theory and BP Neural Networks of Large Cranes

Static load tests are an important means of supervising and detecting a crane＇s lift capacity. Due to space restrictions, however, there are difficulties and potential danger when testing large bridge cranes. To solve the loading problems of large-tonnage cranes during testing, an equivalency test is proposed based on the similarity theory and BP neural networks. The maximum stress and displacement of a large bridge crane is tested in small loads, combined with the training neural network of a similar structure crane through stress and displacement data which is collected by a physics simulation progressively loaded to a static load test load within the material scope of work. The maximum stress and displacement of a crane under a static load test load can be predicted through the relationship of stress, displacement, and load. By measuring the stress and displacement of small tonnage weights, the stress and displacement of large loads can be predicted, such as the maximum load capacity, which is 1.25 times the rated capacity. Experimental study shows that the load reduction test method can reflect the lift capacity of large bridge cranes. The load shedding predictive analysis for Sanxia 1200 t bridge crane test data indicates that when the load is 1.25 times the rated lifting capacity, the predicted displacement and actual displacement error is zero. The method solves the problem that lifting capacities are difficult to obtain and testing accidents are easily possible when 1.25 times related weight loads are tested for large tonnage cranes.

Mining Social Groups with Weighted Similarity in Campus Wireless Network

With the popularity of wireless networks and the prevalence of personal mobile computing devices, understanding the characteristic of wireless network users is of great significance to the network performance. In this study, system logs from two universities, Dartmouth College and Shanghai Jiao Tong University(SJTU), were mined and analyzed. Every user's log was represented by a user profile. A novel weighted social similarity was proposed to quantify the resemblance of users considering influence of location visits. Based on the similarity, an unsupervised learning method was applied to cluster users. Though environment parameters are different, two universities both form many social groups with Pareto distribution of similarity and exponential distribution of group sizes. These findings are very important to the research of wireless network and social network .

INTS-MFS:A novel method to predict microRNA-disease associations by integrating network topology similarity and microRNA function similarity

Identifying associations between microRNAs(miRNAs)and diseases is very important to understand the occurrence and development of human diseases.However,these existing methods suffer from the following limitation:first,some disease-related miRNAs are obtained from the miRNA functional similarity networks consisting of heterogeneous data sources,i.e.,disease similarity,protein interaction network,gene expression.Second,little approaches infer disease-related miRNAs depending on the network topological features without the functional similarity of miRNAs.In this paper,we develop a novel model of Integrating Network Topology Similarity and MicroRNA Function Similarity(INTS-MFS).The integrated miRNA similarities are calculated based on miRNA functional similarity and network topological characteristics.INTS-MFS obtained AUC of 0.872 based on five-fold cross-validation and was applied to three common human diseases in case studies.As a results,30 out of top 30 predicted Prostatic Neoplasm-related miRNAs were included in the two databases of dbDEMC and PhenomiR2.0.29 out of top 30 predicted Lung Neoplasm-related miRNAs and Breast Neoplasm-related miRNAs were included in dbDEMC,PhenomiR2.0 and experimental reports.Moreover,INTS-MFS found unknown association with hsa-mir-371a in breast cancer and lung cancer,which have not been reported.It provides biologists new clues for diagnosing breast and lung cancer.

A weight's agglomerative method for detecting communities in weighted networks based on weight's similarity

This paper proposes the new definition of the community structure of the weighted networks that groups of nodes in which the edge＇s weights distribute uniformly but at random between them. It can describe the steady connections between nodes or some similarity between nodes＇ functions effectively. In order to detect the community structure efficiently, a threshold coefficient t~ to evaluate the equivalence of edges＇ weights and a new weighted modularity based on the weight＇s similarity are proposed. Then, constructing the weighted matrix and using the agglomerative mechanism, it presents a weight＇s agglomerative method based on optimizing the modularity to detect communities. For a network with n nodes, the algorithm can detect the community structure in time O（n2 log~）. Simulations on networks show that the algorithm has higher accuracy and precision than the existing techniques. Furthermore, with the change of t~ the algorithm discovers a special hierarchical organization which can describe the various steady connections between nodes in groups.

Coarse Graining Method Based on Noded Similarity in Complex Network

Coarse graining of complex networks is an important method to study large-scale complex networks, and is also in the focus of network science today. This paper tries to develop a new coarse-graining method for complex networks, which is based on the node similarity index. From the information structure of the network node similarity, the coarse-grained network is extracted by defining the local similarity and the global similarity index of nodes. A large number of simulation experiments show that the proposed method can effectively reduce the size of the network, while maintaining some statistical properties of the original network to some extent. Moreover, the proposed method has low computational complexity and allows people to freely choose the size of the reduced networks.

Functional Brain Network Learning Based on Spatial Similarity for Brain Disorders Identification

Functional brain network (FBN) measures based on functional magnetic resonance imaging (fMRI) data, has become important biomarkers for early diagnosis and prediction of clinical outcomes in neurological diseases, such as Alzheimer’s diseases (AD) and its prodromal state (i.e., Mild cognitive impairment, MCI). In the past decades, researchers have developed numbers of approaches for FBN estimation, including Pearson’s correction (PC), sparse representation (SR), and so on. Despite their popularity and wide applications in current studies, most of the approaches for FBN estimation only consider the dependency between the measured blood oxygen level dependent (BOLD) time series, but ignore the spatial relationships between pairs of brain regions. In practice, the strength of functional connection between brain regions will decrease as their distance increases. Inspired by this, we proposed a new approach for FBN estimation based on the assumption that the closer brain regions tend to share stronger relationships or similarities. To verify the effectiveness of the proposed method, we conduct experiments on a public dataset to identify the patients with MCIs from health controls (HCs) using the estimated FBNs. Experimental results demonstrate that the proposed approach yields statistically significant improvement in seven performance metrics over using the baseline methods.

The Role and Place of Artificial Neural Network Architectures Structural Redundancy in the Input Data Prototypes and Generalization Development

Neural Networks (NN) are the functional unit of Deep Learning and are known to mimic the behavior of the human brain to solve complex data-driven problems. Whenever we train our own neural networks, we need to take care of something called the generalization of the neural network. The performance of Artificial Neural Networks (ANN) mostly depends upon its generalization capability. In this paper, we propose an innovative approach to enhance the generalization capability of artificial neural networks (ANN) using structural redundancy. A novel perspective on handling input data prototypes and their impact on the development of generalization, which could improve to ANN architectures accuracy and reliability is described.

基于Triplet Network的小样本轴承、齿轮故障诊断方法

针对小样本条件下,深度神经网络在机械设备典型部件中(轴承、齿轮)故障诊断精度不高这一问题,提出了一种基于Triplet Network的机械设备典型部件(轴承、齿轮)故障诊断方法。首先,利用短时傅里叶变换,将原始时序信号转换为时频信号;然后,采用了基于Triplet Network搭建的模型,从时频信号中提取了同一故障和不同故障样本的特征,通过对比相同故障和不同故障样本特征的相似度,对模型参数进行了优化,达到了提取的同一故障样本特征相似度越来越高,不同故障样本特征相似度越来越低的效果;最后,通过比较未知样本与已知故障样本的特征相似度,实现了对机械设备典型部件(轴承、齿轮)的故障识别,并采用江南大学轴承故障数据集和康涅狄格大学齿轮故障数据集,对该故障诊断方法的有效性进行了实验验证。研究结果表明:基于Triplet Network的方法在每类训练样本只有5个的情况下,轴承故障识别率可以达到68%,齿轮故障识别率为96.8%,均优于传统的深度神经网络方法。

RESEARCH ON ADAPTIVE COMPRESSION CODING FOR NETWORK CODING IN WIRELESS SENSOR NETWORK

Based on the sequence entropy of Shannon information theory, we work on the network coding technology in Wireless Sensor Network (WSN). In this paper, we take into account the similarity of the transmission sequences at the network coding node in the multi-sources and multi-receivers network in order to compress the data redundancy. Theoretical analysis and computer simulation results show that this proposed scheme not only further improves the efficiency of network transmission and enhances the throughput of the network, but also reduces the energy consumption of sensor nodes and extends the network life cycle.

Personalized Recommendation Algorithm Based on Rating System and User Interest Association Network

In most available recommendation algorithms, especially for rating systems, almost all the high rating information is utilized on the recommender system without using any low-rating information, which may include more user information and lead to the accuracy of recommender system being reduced. The paper proposes a algorithm of personalized recommendation (UNP algorithm) for rating system to fully explore the similarity of interests among users in utilizing all the information of rating data. In UNP algorithm, the similarity information of users is used to construct a user interest association network, and a recommendation list is established for the target user with combining the user interest association network information and the idea of collaborative filtering. Finally, the UNP algorithm is compared with several typical recommendation algorithms (CF algorithm, NBI algorithm and GRM algorithm), and the experimental results on Movielens and Netflix datasets show that the UNP algorithm has higher recommendation accuracy.

APPOW:An Advanced Routing Protocol Based on Parameters Optimization in the Weighted Mobile Social Network

Due to the increasing number of wireless mobile devices,the possibility of mobile communications without infrastructure becomes a reality.The Decentralized Mobile Social Network(DMSN) is a paradigm where nodes can move freely and organize themselves arbitrarily.Routing in these environments is difficult for the reason of the rapid changes of the social relationship graph's topology.Meanwhile,the social ties among nodes change overtime.Therefore,an efficient data forwarding mechanism should be considered over the temporal weighted relationship graph.In this paper,an Advanced routing Protocol based on Parameters Optimization in the Weighted mobile social network(APPOW) is proposed to improve the delivery success ratio and reduce the cost of exchanging information.APPOW combines the normalized relative weights of three local social metrics,i.e.,LinkRank,similarity and contact strength,to select the next relay node.The weights of the three metrics are derived by pair-wise learning algorithm.The result shows that APPOW outperforms the state-ofthe-art SimBet Routing in delivering message and significantly reduces the average hops.Additionally,the delivery performance of APPOW is close to Epidemic Routing but without message duplications.

基于相似网络和联合注意力的图嵌入模型

图注意力网络(graph attention network, GAT)将注意力机制与图神经网络融合,但模型只关注节点的一阶邻域节点,缺乏对高阶相似节点的考虑,同时在计算注意力分数时缺乏对节点结构特征的关注.为此提出一种基于相似网络和联合注意力的图嵌入模型.首先计算网络中的节点相似性,并将高相似度且未连接的节点对构建新边以形成相似网络.其次,引入结构相关性和内容相关性的概念,分别用于表征节点之间的结构关系和内容特征.通过融合两种相关性得分计算得到联合注意力分数.最后使用联合注意力分数对节点特征加权聚合,得到最终的节点嵌入表示.将本文所提算法在Cora、Citeseer和Pubmed 3个数据集上进行节点分类任务,准确率分别达到85.70%、74.30%、84.10%,与原始图注意力网络模型相比分别提高了2.70%、3.94%和2.60%.可见,所提出的算法可以得到更好的节点嵌入表示.

METrust: A Mutual Evaluation-based Trust Model for P2P Networks

It is necessary to construct an effective trust model to build trust relationship between peers in peer-to-peer （P2P） network and enhance the security and reliability of P2P systems. The current trust models only focus on the consumers＇ evaluation to a transaction, which may be abused by malicious peers to exaggerate or slander the provider deliberately. In this paper, we propose a novel trust model based on mutual evaluation, called METrust, to suppress the peers＇ malicious behavior, such as dishonest evaluation and strategic attack. METrust considers the factors including mutual evaluation, similarity risk, time window, incentive, and punishment mechanism. The trust value is composed of the direct trust value and the recommendation trust value. In order to inhibit dishonest evaluation, both participants should give evaluation information based on peers＇ own experiences about the transaction while computing the direct trust value. In view of this, the mutual evaluation consistency factor and its time decay function are proposed. Besides, to reduce the risk of computing the recommendation trust based on the recommendations of friend peers, the similarity risk is introduced to measure the uncertainty of the similarity computing, while similarity is used to measure credibility. The experimental results show that METrust is effective, and it has advantages in the inhibition of the various malicious behaviors.

Community detection in signed networks based on discrete-time model

Community detection in signed networks has been studied widely in recent years. In this paper, a discrete difference equation is proposed to imitate the consistently changing phases of the nodes. During the interaction, each node will update its phase based on the difference equation. Each node has many different nodes connected with it, and these neighbors have different influences on it. The similarity between two nodes is applied to describe the influences between them. Nodes with high positive similarities will get together and nodes with negative similarities will be far away from each other.Communities are detected ultimately when the phases of the nodes are stable. Experiments on real world and synthetic signed networks show the efficiency of detection performance. Moreover, the presented method gains better detection performance than two existing good algorithms.

Uncovering offline event similarity of online friends by constructing null models

The emergence of Event-based Social Network(EBSN) data that contain both social and event information has cleared the way to study the social interactive relationship between the virtual interactions and physical interactions. In existing studies, it is not really clear which factors affect event similarity between online friends and the influence degree of each factor. In this study, a multi-layer network based on the Plancast service data is constructed. The the user’s events belongingness is shuffled by constructing two null models to detect offline event similarity between online friends. The results indicate that there is a strong correlation between online social proximity and offline event similarity. The micro-scale structures at multi-levels of the Plancast online social network are also maintained by constructing 0 k–3 k null models to study how the micro-scale characteristics of online networks affect the similarity of offline events. It is found that the assortativity pattern is a significant micro-scale characteristic to maintain offline event similarity. Finally, we study how structural diversity of online friends affects the offline event similarity. We find that the subgraph structure of common friends has no positive impact on event similarity while the number of common friends plays a key role, which is different from other studies. In addition, we discuss the randomness of different null models, which can measure the degree of information availability in privacy protection. Our study not only uncovers the factors that affect offline event similarity between friends but also presents a framework for understanding the pattern of human mobility.

动量余弦相似度梯度优化图卷积神经网络

传统梯度下降算法仅对历史梯度进行指数加权累加,没有利用梯度的局部变化,造成优化过程越过全局最优解,即使收敛到最优解也会在最优解附近震荡,其训练图卷积神经网络会造成收敛速度慢、测试准确度低。利用相邻两次梯度的余弦相似度,动态调整学习率,提出余弦相似度梯度下降(SimGrad)算法。为进一步提升图卷积神经网络训练的收敛速度和测试准确度,减少震荡,结合动量思想提出动量余弦相似度梯度下降(NSimGrad)算法。通过收敛性分析,证明SimGrad算法、NSimGrad算法都具有O(√T)的遗憾界。在构建的三个非凸函数进行测试,并结合图卷积神经网络在四个数据集上进行实验,结果表明SimGrad算法保证了图卷积神经网络的收敛性,NSimGrad算法进一步提高图卷积神经网络训练的收敛速度和测试准确度,SimGrad、NSimGrad算法相较于Adam、Nadam具有更好的全局收敛性和优化能力。

创新联合体潜在合作伙伴选择研究

为研究创新联合体构建过程中如何合理有效地挑选潜在合作伙伴,充分发挥创新联合体在实现高水平科技自立自强中的战略作用,构建了基于专利异构网络和SimRank算法的创新主体技术背景相似度计算方法,借助可视化方法展现潜在合作关系网络,结合谱聚类算法划分创新联合体潜在合作伙伴。在高分子材料领域进行实证分析,实证结果较好地展示了该领域创新主体的潜在合作关系和技术背景高度相似的创新主体聚类结果,证实了研究理论和方法的有效性,为创新联合体伙伴选择提供参考。

基于特征相似性和特征规范化的注意力模块

近年来,注意力机制在图像分类、目标检测和语义分割等领域取得了巨大成功,但现有的注意力机制大多只能在通道或空间维度上实现特征融合,这极大限制了其在通道和空间维度上变化的灵活性,导致无法充分利用特征信息。为此,文中提出一种基于特征相似性和特征规范化的、可同时利用特征图各维度信息的卷积神经网络注意力模块FSNAM。该模块由特征相似性模块(FSM)和特征规范化模块(FNM)两部分组成,FSM利用输入特征图的通道特征信息和局部空间特征信息生成一个二维的特征相似性权重图;FNM利用输入特征图的全局空间特征信息生成一个三维的特征规范化权重图;两个模块生成的权重图融合在一起,生成一个三维的注意力权重图,以此实现通道特征信息和空间特征信息的融合。为证明FSNAM的可行性和有效性,进行了消融实验,结果表明:在图像分类任务方面,FSNAM模块对分类网络在CIFAR数据集上的性能提升明显优于其他主流注意力模块;在目标检测任务方面,使用FSNAM模块的目标检测网络对VOC数据集中的小目标和中等大小目标的检测准确率分别提高了3.9和1.2个百分点;在语义分割任务方面,使用FSNAM模块可以提高HRNet模型的性能,在SBD数据集上模型的平均像素准确率提高了0.58个百分点。