ID 原文 译文
53737 而且所提方法还可以提供在规避危险气象过程中关于航空器的航速和航向的变化情况供飞行员参考。 Moreover, The proposed method can also provide information on the changes of the aircraft's speed and course during the process of avoiding dangerous weather for pilots' reference.
53738 为了提高雾无线接入网( Fog-Radio Access Networks,F-RAN) 的边缘缓存效率,提出一种基于用户偏好预测和内容流行度预测的协作式内容缓存策略。 In order to improve the edge caching efficiency of Fog-Radio Access Network ( F-RAN) , a collaborative contentcaching strategy based on user preference prediction and content popularity prediction is proposed in this paper.
53739 首先,利用主题模型中隐含狄利克雷分布( Latent Dirichlet Alloca tion,LDA) 模型动态地预测用户偏好; Firstly, theLatent Dirichlet Allocation ( LDA) model in the subject model is used to dynamically predict user preferences.
53740 其次,利用网络中不同设备之间的拓扑关系和已预测的用户偏好以在线的方式预测内容流行度的变化, Secondly, the topological relationships between different devices in the network and the obtained predicted user preferences are utilizedto predict the changes of content popularity in an online fashion.
53741 并且结合基站之间的相关度,以减少缓存内容文件的重复率; Combining with correlation between the base station to re duce the repetition rate of cache content files.
53742 最后,以最大化缓存命中率为目标,利用强化学习中的 Q-learning 算法获得了最优的内容缓存策略。 Finally, with the aim of maximizing the cache hit ratio, the Q-learning algo rithm in reinforcement learning is used to obtain the optimal content caching strategy.
53743 仿真结果表明,与其他内容缓存策略相比,该内容缓存策略能有效的提高缓存命中率。 Simulation results show that the pro posed content caching strategy can effectively improve the cache hit ratio compared with existing content caching strategies.
53744 基于深度神经网络的多源图像内容自动分析与目标识别方法近年来不断取得新的突破,并逐步在智能安防、医疗影像辅助诊断和自动驾驶等多个领域得到广泛部署。 Recently deep neural networks have achieved great success in various multiple source digital image analysis and interpretation tasks. They have been gradually deployed in many applications such as smart surveillance, medical image analysis and autonomous driving.
53745 然而深度神经网络的对抗脆弱性给其在安全敏感领域的部署带来巨大安全隐患。 However, they are vulnerable to adversarial attacks.
53746 对抗鲁棒性的有效提升方法是采用最大化网络损失的对抗样本重训练深度网络, One of the most effective method for adversarial robustness enhancement is to retrain deep neural network using adversarial examples which maximize the loss function of the deep model.