ID 原文 译文
58348 针对常用协同过滤推荐算法存在计算性能瓶颈的问题，提出了在 Spark 上并行化实现协同过滤推荐算法ＲLPSO_KM_CF. In order to solve the computational performance bottleneck of the commonly used collaborativefiltering recommendation algorithm，a parallel collaborative filtering recommendation algorithm ＲLPSO_KM_CF on Spark is proposed.
58349 首先，通过具备反向学习和局部学习能力的粒子群优化( ＲLPSO) 算法寻找粒子群最优解，输出优化后的聚类中心; Firstly，the reverse-learning and local-learning particle swarm optimization( ＲLPSO) algorithm is used to find the optimal solution of the particle swarm and the output clusteringcenter is optimized.
58350 然后，运用 ＲLPSO_KM 算法对用户信息进行聚类; Then，the ＲLPSO_KM algorithm is used to cluster the user information.
58351 最后，将传统协同过滤推荐算法与 ＲLPSO_KM聚类结合，从而对目标用户进行有效推荐. Finally，thetraditional cooperative filtering recommendation algorithm is combined with the ＲLPSO_KM cluster to effectively recommend the target user.
58352 实验结果显示，ＲLPSO_KM_CF 算法在推荐准确度方面有显著提高，具有较高的加速比，稳定性也得到了一定提升. The experimental results show that the improved algorithm has a significant improvement in the recommended accuracy，and has a higher speedup and stability.
58353 为适应动态信道条件，提高传输可靠性，基于增量冗余混合自动重传请求和码率兼容低密度奇偶校验码( ＲC-LDPC) ，研究了多中继选择的速率自适应中继协作传输体制. In order to adapt to dynamical channel conditions and improve the transmission reliability，rate-adaptive cooperative relay transmission schemes are investigated under multi-relay selection in combination with incremental redundancy hybrid automatic repeat request and rate-compatible low density paritycheck code ( ＲC-LDPC) .
58354 针对中继节点的随机分布和特定分布，提出 2种不同的中继选择协作方案，并给出了系统中断概率和吞吐量性能的表达式. With respect to random and specific distributions of relay nodes，two differentmulti-relay selection protocols are proposed with deriving the expressions for the outage probability andthroughput performances of the system.
58355 数值分析和仿真结果表明，在中继节点的特定分布下引入中继之间的相互协作，可同时显著提高系统的中断概率和吞吐量性能. Both numerical and simulation results show that introducing a cooperation between the relays can significantly improve the system performance in both outage probabilityand throughput under the considered specific relay distribution.
58356 针对域名系统( DNS) 中存在异常查询的问题，提出了一种基于日志信息的 DNS 查询异常检测算法，以检测异常的互联网协议地址( IP) . Point at the anomaly queries existing in domain name system ( DNS) ，an anomaly detectionalgorithm based on DNS query logs is proposed to detect suspicious and abnormal internet protocol addresses ( IP) .
58357 通过分析 DNS 正常与异常请求行为的区别，提取了 DNS 日志中多个维度的信息来表征源 IP; First，multiple dimensions of information in the DNS logs are extracted to characterize thesource IPs after analyzing the difference between normal DNS query behaviors and the abnormal ones.