结构正则化多视图非负矩阵分解

现存非负矩阵分解（non-negative matrix factorization,NMF）研究多考虑单一视图分解数据,忽略了数据信息的全面性。此外,NMF限制其获取数据的内在几何结构。针对以上问题,提出一个结构正则化多视图非负矩阵分解算法（structure regularized multi-view nonnegative matrix factorization,SRMNMF）。首先,通过主成分分析来对数据进行全局结构的判别式学习;其次,利用流形学习来捕获数据的局部结构;然后,通过利用多视图数据的多样性和差异性来学习表征。模型提升了算法聚类的整体性能,更加有效地挖掘数据的结构信息。此外,采用高效的交替迭代算法优化目标函数得到最优的因子矩阵。在六个数据集上与现存的代表性方法比较,所提出的SRMNMF的准确率、NMI和Purity分别最大提高4.4%、6.1%和4.05%。     

基于时空图卷积网络的多变量时间序列预测方法

为了扩大时空图卷积网络的预测范围,将它应用在关联关系未知场景下的多变量时间序列预测问题,提出一种附加图学习层的时空图卷积网络预测方法（GLB-STGCN）。图学习层借助余弦相似度从时间序列中学习图邻接矩阵,通过图卷积网络捕捉多变量之间的相互影响,最后通过多核时间卷积网络捕捉时间序列的周期性特征,实现对多变量的精准预测。为验证GLB-STGCN的有效性,使用天文、电力、交通和经济四个领域的公共数据集和一个工业场景生产数据集进行预测实验,结果表明GLB-STGCN优于对比方法,在天文数据集上的表现尤为出色,预测误差分别降低了6.02%、8.01%、6.72%和5.31%。实验结果证明GLB-STGCN适用范围更广,预测效果更好,尤其适合自然周期明显的时间序列预测问题。     

CoGCN: Combining co‐attention with graph convolutional network for entity linking with knowledge graphs

Entity linking is a fundamental task in natural language processing. The task of entity linking with knowledge graphs aims at linking mentions in text to their correct entities in a knowledge graph like DBpedia or YAGO2. Most of existing methods rely on hand‐designed features to model the contexts of mentions and entities, which are sparse and hard to calibrate. In this paper, we present a neural model that first combines co‐attention mechanism with graph convolutional network for entity linking with knowledge graphs, which extracts features of mentions and entities from their contexts automatically. Specifically, given the context of a mention and one of its candidate entities' context, we introduce the co‐attention mechanism to learn the relatedness between the mention context and the candidate entity context, and build the mention representation in consideration of such relatedness. Moreover, we propose a context‐aware graph convolutional network for entity representation, which takes both the graph structure of the candidate entity and its relatedness with the mention context into consideration. Experimental results show that our model consistently outperforms the baseline methods on five widely used datasets.     

A Network Security Risk Assessment Method Based on a B_NAG Model

Computer networks face a variety of cyberattacks. Most network attacks are contagious and destructive, and these types of attacks can be harmful to society and computer network security. Security evaluation is an effective method to solve network security problems. For accurate assessment of the vulnerabilities of computer networks, this paper proposes a network security risk assessment method based on a Bayesian network attack graph (B_NAG) model. First, a new resource attack graph (RAG) and the algorithm E-Loop, which is applied to eliminate loops in the B_NAG, are proposed. Second, to distinguish the confusing relationships between nodes of the attack graph in the conversion process, a related algorithm is proposed to generate the B_NAG model. Finally, to analyze the reachability of paths in B_NAG, the measuring indexs such as node attack complexity and node state transition are defined, and an iterative algorithm for obtaining the probability of reaching the target node is presented. On this basis, the posterior probability of related nodes can be calculated. A simulation environment is set up to evaluate the effectiveness of the B_NAG model. The experimental results indicate that the B_NAG model is realistic and effective in evaluating vulnerabilities of computer networks and can accurately highlight the degree of vulnerability in a chaotic relationship.     

Towards sustainable industry 4.0: A green real-time IIoT multitask scheduling architecture for distributed 3D printing services

As the keystones of the personalized manufacturing, the Industrial Internet of Things (IIoT) consolidated with 3D printing pave the path for the era of Industry 4.0 and smart manufacturing. By resembling the age of craft manufacturing, Industry 4.0 expedites the alteration from mass production to mass customization. When distributed 3D printers (3DPs) are shared and collaborated in the IIoT, a promising dynamic, globalized, economical, and time-effective manufacturing environment for customized products will appear. However, the optimum allocation and scheduling of the personalized 3D printing tasks (3DPTs) in the IIoT in a manner that respects the customized attributes submitted for each model while satisfying not only the real-time requirements but also the workload balancing between the distributed 3DPs is an inevitable research challenge that needs further in-depth investigations. Therefore, to address this issue, this paper proposes a real-time green-aware multi-task scheduling architecture for personalized 3DPTs in the IIoT. The proposed architecture is divided into two interconnected folds, namely, allocation and scheduling. A robust online allocation algorithm is proposed to generate the optimal allocation for the 3DPTs. This allocation algorithm takes into consideration meeting precisely the customized user-defined attributes for each submitted 3DPT in the IIoT as well as balancing the workload between the distributed 3DPs simultaneously with improving their energy efficiency. Moreover, meeting the predefined deadline for each submitted 3DPT is among the main objectives of the proposed architecture. Consequently, an adaptive real-time multi-task priority-based scheduling (ARMPS) algorithm has been developed. The built ARMPS algorithm respects both the dynamicity and the real-time requirements of the submitted 3DPTs. A set of performance evaluation tests has been performed to thoroughly investigate the robustness of the proposed algorithm. Simulation results proved the robustness and scalability of the proposed architecture that surpasses its counterpart state-of-the-art architectures, especially in high-load environments.     

多频段脑功能网络融合的阿尔茨海默病分类

将图论与机器学习方法相结合的阿尔茨海默病计算机辅助中,脑网络的构建大多是基于滤波去噪后的全频段BOLD信号匹配,忽略了不同脑活动信息的差异.因此,本文提出了一种多频段脑功能网络融合模型.首先将离散小波变换应用于BOLD信号中,得到不同频域下的体素信号,而后计算同频信号的相关性,获取不同频段下相关矩阵.而后计算所有矩阵的网络特征,在特征选择后基于SVM对患者进行分类.从实验结果可以看出,分频下的脑功能网络特征与未分频网络相比能在一定程度上提高分类的准确性;体素级网络由于可以更加详细的表达脑网络的变化,其分类效果要优于脑区级.     

融合知识图谱的网络安全违法行为识别系统

《网络安全法》是我国第一部关于网络安全的综合立法,与大众的互联网生活息息相关.因此,一款面向大众的《网络安全法》智能违法行为识别系统有助于规范互联网行为.然而,现有智能违法行为识别系统构建方法难以适应《网络安全法》,这是由于:首先,现有方法需要专业司法语言进行交互,不适应普通大众的语言体系.其次,现有方法需要大量的案例训练模型,不适应案例匮乏的《网络安全法》.针对这些问题,本文提出了一个面向《网络安全法》的智能违法行为识别系统.该系统主要利用知识图谱技术解决上述问题,在构建网络安全法知识图谱的基础上,通过将普通用户的自然语言与知识图谱中的违法事件实体和违法主体实体进行实体链接的方式获得更强的特征,提高违法行为识别系统在训练集较为匮乏的条件下的准确度.通过在真实数据集上的实验,表明了提出的系统的准确度有明显提高.     

一种基于图卷积网络的文本多标签学习方法

多标签学习广泛应用于文本分类、标签推荐、主题标注等.最近,基于深度学习技术的多标签学习受到广泛关注,针对如何在多标签学习中有效挖掘并利用高阶标签关系的问题,提出一种基于图卷积网络探究标签高阶关系的模型TMLLGCN.该模型采用GCN的映射函数从数据驱动的标签表示中生成对象分类器挖掘标签高阶关系.首先,采用深度学习方法提取文本特征,然后以数据驱动方式获得基础标签关联表示矩阵,为更好地建模高阶关系及提高模型效果,在基础标签关联表示矩阵上考虑未标记标签集对已知标签集的影响进行标签补全,并以此相关性矩阵指导GCN中标签节点之间的信息传播,最后将提取的文本特征应用到学习高阶标签关系的图卷积网络分类器进行端到端训练,综合标签关联和特征信息作为最终的预测结果.在实际多标签数据集上的实验结果表明,提出的模型能够有效建模标签高阶关系且提升了多标签学习的效果.     

一种基于有向二分图模型和贝叶斯网络的入侵检测方法

针对入侵检测中存在的非确定性推理问题,文章提出一种基于二分图模型和贝叶斯网络的入侵检测方法,该方法利用二分有向图模型表示入侵和相关特征属性之间的因果拓扑关系,利用训练数据中获取模型的概率参数,最后使用最大可能解释对转化后的推理问题进行推理,并通过限定入侵同时发生的数目来提高检测效率。实验表明,该方法具有较高的检测率和很好的鲁棒性。     

基于软测量的化工精馏过程推断控制策略

针对化工精馏过程产品成分无法在线检测及其用温度间接控制产品成分的常规控制策略存在着控制精度低的问题,提出基于软测量的精馏过程成分非线性串级推断控制策略。该控制策略首先提出核岭回归的实时软测量方法,即利用满足Mercer条件的核函数改进线性岭回归算法,实现精馏过程产品成分的在线检测;然后在此基础上,提出一种新的非线性串级推断控制策略,即副环采用常规的温度间接控制,主环采用基于核岭回归软测量的推断控制策略。通过Mejedell等建立的精馏塔动态模型分别对单端和双端成分非线性串级推断控制策略性能进行分析,仿真结果表明,与传统控制方案比较,新控制策略的控制质量有了较大提高,控制结构简单,易于实施。