ID 原文 译文
19695 此外，基于迁移学习策略可以将训练好的深度网络模型迁移到其他识别任务上，有助于推动脑电信号在驾驶疲劳检测系统中的应用。 Moreover, based on the transfer learning strategy, this model can also be used for other recognition tasks, which is helpful for promoting the application of EEG signals to the driver fatigue detection system.
19696 网络安全态势要素识别的基础是对态势数据集进行有效的特征提取。 The basis of the identification of network security situation element is to perform the feature extraction of situation data effectively.
19697 针对反向传播(BP)神经网络对海量安全态势信息数据学习时过度依赖数据标签的问题，该文提出一种结合深度堆栈编码器和反向传播算法的网络安全态势要素识别方法，通过无监督学习算法逐层训练网络，在此基础上堆叠得到深度堆栈编码器，利用编码器提取数据集特征，实现了网络的无监督训练。 Considering the problem that the Back Propagation(BP) neural networks have excessive dependence on data labels when it has a learning of massive security situation information data, a network security situation element identification method is proposed, which combines deep stack encoder and BP algorithm. It trains the network layer by layer through unsupervised learning algorithm. On this basis the deep track encoder by stacking can be obtained. The unsupervised training of the network is realized when using the encoder to extract the characteristic of the data sets.
19698 仿真实验验证了该方法能有效提升安全态势感知的效能和准确度。 It is verified by simulation experiments that the method can improve the performance and accuracy of situational awareness effectively.
19699 网络多告警信息融合处理是有效实施网络动态威胁分析的主要手段之一。 Network multi-alarm information fusion processing is one of the most important methods to implement effectively network dynamic threat analysis.
19700 基于此该文提出一种利用网络系统多告警信息进行动态威胁跟踪与量化分析的机制。 Focusing on this, a mechanism for dynamic threattracking and quantitative analysis by using network system multi-alarm information is proposed.
19701 该机制首先利用攻击图理论构建系统动态威胁属性攻击图； Firstly, theattack graph theory is used to construct the system dynamic threat attribute attack graph.
19702 其次基于权限提升原则设计了前件推断算法(APA)、后件预测算法(CPA)和综合告警信息推断算法(CAIIA)进行多告警信息的融合与威胁分析，生成网络动态威胁跟踪图进行威胁变化态势的可视化展示。 Secondly, based on the privilege escalation principle, Antecedent Predictive Algorithm(APA), the Consequent Predictive Algorithm(CPA) and the Comprehensive Alarm Information Inference Algorithm(CAIIA) are designed to integrate the multi-alarm information fusion and do threat analysis. Then, the network dynamic threat trackinggraph is generated to visualize the threat change situation.
19703 最后通过实验验证了该机制和算法的有效性。 Finally, the effectiveness of the mechanism and algorithm is validates through experiments.
19704 近年来，Siamese网络由于其良好的跟踪精度和较快的跟踪速度，在视觉跟踪领域引起极大关注，但大多数Siamese网络并未考虑模型更新，从而引起跟踪错误。 In recent years, the Siamese networks has drawn great attention in visual tracking community due toits balanced accuracy and speed. However, most Siamese networks model are not updated, which causestracking errors.