ID 原文 译文
18155 通过网络攻击实验证明，AUTH-VRF模型可以为数控网络中工业生产数据提供有效的安全认证和资源完整性保护， The network attack experiments prove that the AUTH-VRF model can provide effective security certificationand integrity protection for industrial production data in CNC networks.
18156 为满足我国关键基础设施“国内、国外工业控制系统产品共同安全可控”和“安全技术深入工业控制系统各个层级”的需求提供了实际可行的技术参考方案。 It also provides a practical technicalapproach to meet the requirements of ‘secure and controllable both for domestic and foreign products’, as well as ‘applying security technique to all layers of Industrial Control Systems’ for protecting the criticalinfrastructure.
18157 心律失常等慢性心血管疾病严重影响人类健康，采用心电信号(ECG)实现心律失常自动分类可有效提高该类疾病的诊断效率，降低人工成本。 Chronic cardiovascular diseases such as arrhythmia seriously affect human health. The automaticclassification of ElectroCardioGram(ECG) signals can effectively improve the diagnostic efficiency of suchdiseases and reduce labor costs.
18158 为此，该文基于1维心电信号，提出一种改进的长短时记忆网络(LSTM)方法实现心律失常自动分类。 To tackle this problem, an improved Long-Short Term Memory (LSTM)method is proposed to achieve automatic classification of one dimensional ECG signals.
18159 该方法首先设计深层卷积神经网络(CNN)对心电信号进行深度编码，提取心电信号形态特征。 Firstly, deepConvolutional Neural Network (CNN) is designed to deeply encode the ECG signal, and ECG signalmorphological features are extracted.
18160 其次，搭建长短时记忆分类网络实现基于心电信号特征的心律失常自动分类。 Secondly, the LSTM classification network is used to realize automaticclassification of arrhythmia of ECG signal features.
18161 基于MIT-BIH心律失常数据库进行的实验结果表明，该方法显著缩短分类时间，并获得超过99.2%的分类准确率，灵敏度等评价参数均得到不同程度的提高，满足心电信号自动分类实时高效的要求。 Experimental studies based on the MIT-BIH arrhythmiadatabase show that the training duration is significantly shortened and more than 99.2% classification accuracyis obtained. Sensitivity and other evaluation parameters are improved to meet the real-time and efficientrequirements for automatic classification of ECG signals.
18162 僵尸网络已成为网络空间安全的主要威胁之一，虽然目前可通过逆向工程等技术来对其进行检测，但是使用了诸如fast-flux等隐蔽技术的僵尸网络可以绕过现有的安全检测并继续存活。 Botnets have become one of the main threats to cyberspace security. Although they can be detectedby techniques such as reverse engineering, botnets using covert technologies such as fast-flux can successfullybypass existing security detection and continue to survive.
18163 现有的fast-flux僵尸网络检测方法主要分为主动和被动两种，前者会造成较大的网络负载，后者存在特征值提取繁琐的问题。 The existing fast-flux botnet detection methods aremainly divided into active and passive, the former will cause a large network load, and the latter has theproblem of cumbersome feature value extraction.
18164 因此为了有效检测fast-flux僵尸网络并解决传统检测方法中存在的问题，该文结合卷积神经网络和循环神经网络，提出了基于流量时空特征的fast-flux僵尸网络检测方法。 In order to effectively detect fast-flux botnets and alleviatethe problems in traditional detection methods, a fast-flux botnet detection method based on spatiotemporalfeatures of network traffic is proposed, combined with convolutional neural networks and recurrent neuralnetwork models, the fast-flux botnet is detected from both spatial and temporal dimensions.