ID 原文 译文
44406 针对现有的拟态控制器防御成本过高的问题，研究了能够抵抗未知攻击且防御成本相对较低的拟态控制器。 Since the defense cost of current mimic controller is relatively high, a novel mimic controller with a lower defense cost and good defensive performance was researched.
44407 首先，定义信誉度与相异度表征执行体集的脆弱程度与异构程度，并从三大模块进行创新。 First, reputation indicator was introduced to describe the vulnerability of performers and a dissimilarity dictator was introduced to describe the heterogeneity of the performers.
44408 执行体选择模块基于相异度与信誉度选择脆弱程度最低且异构程度最大的执行体集。然后，利用信誉度指标优化现有的多模裁决。 The performer selection module used the dissimilarity and reputation to obtain an optimized performer set featuring most reliable and heterogeneous.
44409 最后，通过引入负反馈模块动态更新各执行体信誉度，实现执行体集选择策略与多模裁决策略的动态更新。 Second, the ruling module was designed reduce the negative effect of unreliable performers on the ruling result by using the reputation of performers. Besides, by interacting with the performer selection module and the multi-strategic ruling module, the negative feedback controller updated the reputation of performers according to the ruling result and determined the attacked heterogeneous objects need to be cleaned.
44410 为提高日常行为识别准确度的同时使应用具有更强的便捷性，提出基于智能手机中 4 种无需许可传感器数据对 5 种日常行为进行识别的方法。 To improve the accuracy and make it more convenient in the use of human behavior identification at the sametime, a method using the date of four no-permission-imposed sensors in Android smartphone to recognize five kinds of daily activities was proposed.
44411 在分析 Android 系统传感器框架的基础上开发集成了一个小型应用程序进行数据采集处理，然后利用机器学习算法实现手机用户的行为特征识别，目标是实现个人行为准确及时且长期有效的动态监督或预测。 After analyzing the framework of sensors in Android system, an application was integrated for data collection and processing. Then machine learning algorithms were used to extract the features for activity recognition, which aimed at dynamic supervision or predict individual behavior accurately, timely, chronically and effectively.
44412 实验结果表明，改进马尔可夫链算法与 SVM 分类器结合使用结果最优，测试识别准确率可接近 95%，精确度、召回率等其他指标均呈现很好的效果。 The result shows that the combined use of the improved Markov chain algorithm and SVM classifier have the best result,and the accuracy is close to 95%, the accuracy, recall rate and other indicators are also very good.
44413 现有软件定义网络中多控制器部署可靠性方面的研究均主要考虑链路故障对于交换机节点和控制器之间连通性上的影响，忽略了链路故障对控制时延的影响。 Most of the current researches on the reliability of multi-controller placement in software-defined networking(SDN) mainly consider the impact of link failure on the connectivity between the switch node and the controller, while ignoring the link failure versus control delay.
44414 针对此不足，建立了一种针对链路故障时控制时延变动的SDN 控制网络可靠性模型，提出了一种控制器部署算法，以提升控制网络可靠性。 An SDN control network reliability model was established, which considering the control delay variation caused by link failure, and a controller placement algorithm was proposed to optimize the control network reliability. In order to test the performance of the algorithm, the actual network topology and data were selected for verification.
44415 仿真结果表明，该算法能够减少链路故障对控制时延产生的影响，获得更高的控制网络可靠性。 The results show that the controller placement algorithm can reduce the impact of link failure on control delay and make the control network more reliable.