融合课程思政的“自动化综合实验”教学探索

为将思政教育融入课程教学中,培养德能兼备的自动化专业优秀人才。在《自动化综合实验》课程中,首先明确提出了教学的专业目标和思政目标,然后将教学环节分为课程介绍、选题汇报、学生实践以及项目展示和答辩环节,挖掘出丰富的思政元素并融入到课程教学的每个环节,并选取典型案例,通过思维导图法剖析了课程思政的融入策略,最后介绍了课程思政考核模式和取得的初步成效。该课程思政教学模式可以为“专业实验课程-思政教育体系”的打造提供参考。     

基于关系强度理论与反馈机制的信息传播动态网络表示

现有多数网络表示学习方法不能很好地贴合真实世界的信息传播网络,且无法对信息传播动态网络的时间特性与动力学演化特征进行有效建模。提出一种新的信息传播动态网络表示模型,基于关系强度将信息传播动态网络划分为关系网络与传播网络,并分别计算变化节点对的概率密度和邻接矩阵。通过更新节点注意力强度矩阵,聚合节点邻域变化信息,并融合节点邻域变化信息、自身历史信息以及外部影响因素,对信息传播动态网络进行归纳式表示学习。引入反馈机制,将最新的节点表示反馈到邻居节点,解决网络表示不及时的问题,提升网络表示性能。实验结果表明,与Know-Evolve、DyRep、LDG等模型相比,该模型的命中率和平均排名提升显著,与LDG模型相比,其时间效率在Social Evolution数据集和Github数据集上分别提升了91.8%、87.2%。     

面向时间感知的知识超图链接预测

知识超图是一种使用多元关系表示现实世界的异构图,但无论在通用领域还是垂直领域,现有的知识超图普遍存在不完整的情况.因此,如何通过知识超图中已有的链接推理缺失的链接是一个具有挑战性的问题.目前大多数研究使用基于多元关系的知识表示学习方法完成知识超图的链接预测任务,但这些方法仅从时间未知的超边中学习实体与关系的嵌入向量,没有考虑时间因素对事实动态演变的影响,导致在动态环境中的预测性能较差.首先,根据本文首次提出的时序知识超图定义,提出时序知识超图链接预测模型,同时从实体角色、位置和时序超边的时间戳中学习实体的静态表征和动态表征,以一定比例融合后作为实体嵌入向量用于链接预测任务,实现对超边时序信息的充分利用.同时,从理论上证明模型具有完全表达性和线性空间复杂度.此外,通过上市公司的公开经营数据构建时序知识超图数据集CB67,并在该数据集上进行了大量实验评估.实验结果表明:模型能够在时序知识超图数据集上有效地执行链接预测任务.     

基于One-Shot聚合自编码器的图表示学习

自编码器（AE）是一种高效的图数据表示学习模型,但大多数图自编码器（GAE）为浅层模型,其效率会随着隐藏层的增加而降低。针对上述问题,提出基于One-Shot聚合（OSA）和指数线性（ELU）函数的GAE模型OSA-GAE和图变分自编码器模型OSA-VGAE。首先,利用多层图卷积网络（GCN）构建编码器,并引入OSA和ELU函数;然后,在解码阶段使用内积解码器恢复图的拓扑结构;此外,为了防止模型训练过程中的参数过拟合,在损失函数中引入正则化项。实验结果表明,OSA和ELU函数可以有效提高深层GAE的性能,改善模型的梯度信息传递。在使用6层GCN时,基准引文数据集PubMed的链接预测任务中,深层OSA-VGAE相较于原始的VGAE在ROC曲线下的面积（AUC）和平均精度（AP）上分别提升了8.67和6.85个百分点,深层OSA-GAE相较于原始的GAE在AP和AUC上分别提升了6.82和4.39个百分点。     

基于社团多特征融合嵌入表示的时序链路预测方法

时序动态网络在静态网络基础上综合了时间属性的概念,包含了网络结构的复杂性、动态性等内涵,是研究复杂网络链路预测问题的较优思维对象,因在现实世界中具有较高应用价值而备受关注。目前大部分传统方法研究对象仍局限于静态网络,存在对网络时域演化信息利用不充分、时间复杂度较高等问题。结合社会学理论,提出一种基于社团多特征融合嵌入表示的时序链路预测方法,该方法的核心思想是通过分析网络动态演化特性,在社团范围内学习节点的嵌入表示向量,融合多特征以衡量节点间连边的生成概率。利用网络集体影响力的方法对节点和连边的权值进行计算,基于集体影响的连边权值进行社团划分,将网络划分为若干个社团子图,得到基于集体影响的相似性指标。在社团范围内,利用有偏的随机游走,结合梯度优化的Skip-gram方法获取所有节点的嵌入表示向量,得到基于社团范围游走的相似性指标。融合节点的集体影响、社团范围节点的多个中心性特征和学习到的节点表示向量,得到多特征融合的相似性指标,3 种新指标都可以用于衡量节点之间形成连边的概率。对比基于移动平均、嵌入表示、图神经网络等经典时序链路预测方法,在 6 个真实数据集上的实验结果表明,所提基于社团多特征融合的方法在 AUC评价标准下取得更优的预测性能。     

A simple decision tree-based disturbance monitoring system for VSC-based HVDC transmission link integrating a DFIG wind farm

Fault detection and classification is a key challenge for the protection of High Voltage DC (HVDC) transmission lines. In this paper, the Teager–Kaiser Energy Operator (TKEO) algorithm associated with a decision tree-based fault classi f ier is proposed to detect and classify various DC faults. The Change Identification Filter is applied to the average and differential current components, to detect the first instant of fault occurrence (above threshold) and register a Change Identified Point (CIP). Further, if a CIP is registered for a positive or negative line, only three samples of currents (i.e., CIP and each side of CIP) are sent to the proposed TKEO algorithm, which produces their respective 8 indices through which the, fault can be detected along with its classification. The new approach enables quicker detection allowing utility grids to be restored as soon as possible. This novel approach also reduces computing complexity and the time required to identify faults with classification. The importance and accuracy of the proposed scheme are also thor oughly tested and compared with other methods for various faults on HVDC transmission lines.     

基于四元数胶囊网络的知识图谱补全模型

知识图谱采用RDF三元组的形式描述现实世界中的关系和头、尾实体,即（头实体,关系,尾实体）或（主语,谓语,宾语）。为补全知识图谱中缺失的事实三元组,将四元数融入胶囊神经网络模型预测缺失的知识,并构建一种新的知识图谱补全模型。采用超复数嵌入取代传统的实值嵌入来编码三元组结构信息,以尽可能全面捕获三元组全局特性,将实体、关系的四元数嵌入作为胶囊网络的输入,四元数结合优化的胶囊网络模型可以有效补全知识图谱中丢失的三元组,提高预测精度。链接预测实验结果表明,与CapsE模型相比,在数据集WN18RR中,该知识图谱补全模型的Hit@10与正确实体的倒数平均排名分别提高3.2个百分点和5.5%,在数据集FB15K-237中,Hit@10与正确实体的倒数平均排名分别提高2.5个百分点和4.4%,能够有效预测知识图谱中缺失的事实三元组。     

ACO–EEOLSR: enhanced energy model based link stability routing protocol in mobile ad hoc networks

A mobile ad hoc network (MANET) has abundant mobile nodes that are free to communicate independently in many locations. Many existing energy models address the inadequacy of resources based on Ad hoc On-demand Multipath Distance Vector and Optimized Link State Protocol (OLSP) routing protocols for MANET along with various parameters. The architecture of energy-efficient routing mechanisms is a challenging problem in a MANET. In this work, a novel energy-aware routing model is introduced for MANET comprising an ant colony optimization (ACO) enhanced approach to energy-efficient-optimized link state routing (named ACO–EEOLSR). Initially, the route discovery is progressed by means of neighbor estimation and also with the authentication of link stability. Parameters such as energy, distance, and hop count are employed as willingness nodes, where both the energy and distance are entrenched through the OLSP. Consequently, the hop count is applied via the ACO system that is beneficial for link stability. After the acceptance of an acknowledgement, the hop count is authorized for further performance analysis. This approach increases the Quality of Service and also uses less energy compared to other energy models. The accomplished simulation upshot depicts that the ACO–EEOLSR outperforms the EEOLSR scheme with respect to the performance metrics of energy consumption, packet delivery ratio, total remaining time, average network lifetime, and a variance of energy.     

Correction on link relative based approach to CUSUM chart

Link relative-based approach was used in an article (see reference 1) to enhance the performance of the cumulative sum (CUSUM) control chart. This technique involves the use of firstly, the link relative variable to convert the process observations in a relative to the mean form and secondly, optimal constants to define a new variable which is used as the plotting statistic of the link relative CUSUM chart. In this article, it is proven through simulation study that the optimal constants with fixed values, as reported in the aforementioned article, give different results. Instead, if the regression technique is used, then the same results will be obtained.     

自动测试系统中的仪器设备驱动通用封装研究

在目前的自动测试系统软件开发中,虚拟仪器设备指令的非通用性会导致系统开发繁琐、无法集成等问题,针对这些问题提出了一种适合大部分仪器设备的封装方法;这种封装方法,通过动态链接库的形式将事件处理机制嵌入到仪器驱动封装里,拥有跨平台、适用面广、开发速度快和仪器可互换等特点;经过在实际雷达射频模块自动测试系统项目中的应用,结果表明该方法能够实现跨平台操作、具有仪器互换和封装简便等特点,并且表现出极强的通用性,具有一定的实用性和推广价值.