ID 原文 译文
47446 该算法的实现方法为：在以往相关研究基础上，设置粉丝关注比、平均发布微博数、互相关注数、综合质量评价、收藏数和阳光信用这 6 个特征属性来设计微博水军识别分类器，并基于贝叶斯模型和遗传智能优化算法。 By analyzing the previous research, the ratio of followers, total number of blog posts, the number of friends, com-prehensive quality evaluation and favorites according to latest data set, the Weibo spammers’ identification algorithm wasrealized based on Bayesian model and genetic algorithm.
47447 利用新浪微博真实数据对算法性能进行了验证，实验结果表明，提出的贝叶斯水军识别算法能够在不牺牲非水军识别率的情况下，保证水军识别的准确率，而且提出的阈值优化算法能显著提升水军识别的准确率。 The experiment result based on the real-time data of Sina Weiboverify that the Bayesian model recognition algorithm can ensure spammers recognition accuracy without sacrificing rec-ognition rate of non-spammers, and the proposed threshold value matrix proposed optimization can significantly improverecognition accuracy navy.
47448 无线网络虚拟化技术是 5G 研究的热点，其中虚拟网络映射问题是关键技术之一。 Wireless network virtualization has become one of the promising techniques in fifth generation mobile net-works (5G), and the virtual network embedding plays a very important role.
47449 对无线网络虚拟化映射问题进行介绍，针对现有映射算法不能完全适应网络动态变化的不足， A model was formulated to describe theproblem and a wireless virtual network embedding algorithm based on joint bandwidth and power allocation(WVNEA-JBP) was put forward, which selected the suitable node and path to serve the data transmission from virtualnetworks.
47450 以最小化映射成本为目标，提出一种新的网络中带宽和功率资源的联合映射算法（WVNEA-JBP, wireless virtual network embedding algorithm based onjoint bandwidth and power），同时考虑无线链路之间的干扰对映射性能的影响和路径分离。 In order to minimize the overhead while satisfy the higher capacity request, this algorithm considered the im-pact of interference of wireless links and supports path splitting. A case study was introduced to show how WVNEA-JBPto work.
47451 实验结果表明，该算法在实现资源高效利用的同时，提高了无线虚拟网络映射成功的概率。 Furthermore, simulation results show that WVNEA-JBP is able to accomplish the efficient utilization of networkresources and improve the accept rate of virtual network requests.
47452 针对单幅图像去雾中边缘区域去雾不彻底及黑斑现象，提出了一种结合最小颜色通道图与传播滤波的图像去雾算法。 To solve the challenging problem that the edge regions of image have some remained hazes and blackspots, anovel image dehazing algorithm was proposed based on the minimal color channel and propagated filtering.
47453 该方法首先基于双区域滤波实现大气透射率的初始估计，然后引入最小颜色通道图作为参考图像，采用传播滤波优化初始透射率， Firstly, aninitial atmospheric transmission map was obtained by double-area filtering, then a minimal channel color was introducedas a reference image, and the propagated filtering was combined to optimize the initial atmospheric transmission map.
47454 优化后的透射图因与参考图像具有相似的边缘特性，能有效避免图像景深突变边缘像素点透射率估值出现偏差的问题，同时去除了初始透射图中冗余的纹理信息， Optimized transmission have the similar edge characteristics as the referenced image, so the deviation of transmission es-timation can be effectively avoided for the edge pixels in the depth mutated regions, and the redundant texture informa-tion were removed in the initial transmission map.
47455 最后利用 L-BFGS 自适应恢复大气光矢量，基于大气散射模型复原无雾图像。 Finally, L-BFGS was used to restore atmospheric light, and the haze-freeimage can be recovered based on the atmospheric scattering model.