ID 原文 译文
46906 根据多移动 agent 协作规划技术特点，设计融合 Pareto 最优解多目标离散群集蜘蛛算法（MDSSO）， According to the multi mobile agent collaborative planning technical features, the multi-objective dis-crete social spider optimization algorithm (MDSSO) with Pareto optimal solutions was designed.
46907 重新定义插值学习和变异交换粒子更新策略，并动态调整最优解集规模，以提高 MDSSO 算法多目标求解精度。 The interpolationlearning and exchange variations particle updating strategy was redefined, and the optimal set size was adjusted dynami-cally, which helps to improve the accuracy of MDSSO.
46908 实验仿真结果表明，该方法能够快速合理给出 WSN 多移动 agent 规划路径，而且与其他传统算法相比，网络总能耗降低了约 15%，生存期提高了约 23%。 Simulation results show that the proposed algorithm can quicklygive the WSN multi mobile agent path planning scheme, and compared with other schemes, the network total energyconsumption has reduced by 15%, and the network lifetime has increased by 23%.
46909 因特网中时延敏感应用和高吞吐量应用的流行使路由器和交换机中的缓存越来越大，导致网络流量极易出现高时延和高抖动率。 The popularity of delay sensitive applications and high throughput applications in the Internet made the cachesof routers and switches larger, resulting in the high latency and high jitter rate of network traffic.
46910 基于高带宽非响应流的移动应用的普及使网络瓶颈资源利用愈加失衡，整个网络的资源分配公平性难以得到保证。 With the growth of mo-bile applications based on the high bandwidth non-response flows, the network bottleneck resource utilization becomesmore unbalanced, and the resources distribution of the whole network was difficult to be guaranteed.
46911 为了缓解这 2 个问题，从时延控制和抑制高带宽非响应流抢占资源的角度，基于Sample-Match、L-LRU 缓存和按概率分组丢失机制，提出了兼顾公平和低时延的主动队列管理（FLDA）算法。 In order to alleviatethese problems, considering the delay control and suppression of high bandwidth non-response flow, an active queuemanagement algorithm focusing on fairness and low delay named FLDA was proposed based on Sample-Match, L-LRUcache and probabilistic packets dropping.
46912 实验结果表明，在高带宽非响应流的干扰下，FLDA 能够较好地维持队列稳定性、瓶颈链路资源利用的公平性和低时延性。 Experimental results show that under the interference with high bandwidthnon-responsive flows, FLDA can better maintain the queue stability, the fairness of resource utilization of the bottlenecklink and the low delay.
46913 提出一种新的基于 APK 签名信息反馈的 Android 恶意应用检测方法（SigFeedback）。 A new malware detection method based on APK signature of information feedback (SigFeedback) was pro-posed.
46914 该方法在 SVM 分类算法的基础上采用启发式规则学习的方式对特征值进行提取，并对检测集中的 APK 签名信息进行验证筛选，实现了启发式反馈，达到更加准确地检测恶意应用的目的。 Based on SVM classification algorithm, the method of eigenvalue extraction adoped heuristic rule learning to sigAPK information verify screening, and it also implemented the heuristic feedback, from which achieved the purpose ofmore accurate detection of malicious software.
46915 SigFeedback 检测算法具有检测率高、误报率低的特点。 SigFeedback detection algorithm enjoyed the advantage of the high detec-tion rate and low false positive rate.