ID 原文 译文
1273 宽带压缩频谱检测存在依赖稀疏度先验信息和信号重构时延较高的问题。 Wideband compressed spectrum sensing has the problem of relying on sparsity prior information and high signal reconstruction delay.
1274 因此，本文提出了一种高效可靠的宽带压缩频谱检测方案。 Therefore, this paper proposes an efficient and reliable wideband compressed spectrum sensingscheme.
1275 首先，推导出了基于二项分布精确置信区间改进的稀疏度估计模型。 Firstly, the sparsity estimation model based on the improved confidence interval of binomial distribution is derived.
1276 其次，利用稀疏度估计上下界改进了稀疏度自适应匹配追踪算法。 Secondly, using the sparsity estimation upper and lower bounds improves the sparsity adaptive matching pursuit algorithm.
1277 最后，提出了一种宽带压缩频谱检测方案。 Finally, a wideband compressed spectrum sensing scheme is proposed.
1278 仿真结果表明，本文所提出方法可以同时精确的估计信号稀疏度的上下界，提高了频谱检测的效率和可靠性，加快了算法的收敛速度。 The simulation results show that the proposed methodcan accurately estimate the upper and lower bounds of signal sparsity at the same time, improve the efficiency and reliabilityof spectrum sensing, and accelerate the convergence speed of the algorithm.
1279 为了缓解 Web 服务推荐中存在的冷启动和数据稀疏问题，以及满足用户个性化的需求，本文提出了基于混杂社会网络的 Web 服务推荐框架及算法。 To ease cold start and data sparsity problems in web service recommendation, and satisfy user's personal-ized requirements, we propose a web service recommendation framework and algorithms based on heterogeneous social net-work.
1280 该网络加入了服务提供者这一元素，可提供更多的真实信息，有助于缓解冷启动问题。 Web service provider, as an element in the network, could provide more real information to help relieve cold start.
1281 根据提出的服务推荐框架，设计了用户-候选服务信任值预测算法(Computing Trust Value，CTV)，以及服务推荐算法(Recommend Queue，RQ)。 Based on the proposed recommendation framework, we design CTV (Computing Trust Value)algorithm to predict trust val-ue of user to candidate service and RQ (Recommend Queue)algorithm to recommend services.
1282 在真实数据集上建立实验，结果表明本文提出的方法在预测准确率 MAE、RMSE，推荐准确率 MAP、NDCG，以及填充率和覆盖率上都有所提高，有助于提升个性化推荐的性能。 At last, we conduct a seriesof experiments based on real data set. The results indicate that the proposed method outperforms the existing methods at themetrics of MAE, RMSE for predictive accuracy, MAP, NDCG for recommendation accuracy, and filling ratio and coverageratio, and it is helpful to improve personalized recommendation performance.