ID 原文 译文
20315 使用拍卖方式来进行资源分配可以使得资源提供商获得更大的收益，是云计算领域近年来研究的重点之一。 Auction based resource allocation can make resource provider get more profit, which is a major challenging problem for cloud computing.
20316 但资源分配问题是NP难的，无法在多项式时间内求解， However, the resource allocation problem is NP-hard and can not besolved in polynomial time.
20317 现有研究主要通过近似算法或启发式算法来实现资源分配，但存在算法耗时长，与最优解相比准确度低的缺点。 Existing studies mainly use approximate algorithms or heuristic algorithms to implement resource allocation in auction, but these algorithms have the disadvantages of low computational efficiency or low allocate accuracy.
20318 监督学习中分类及回归思想可对多维云资源分配问题进行建模和分析， In this paper, the classification and regression of supervised learning is used to model and analyze multi-dimensional cloud resource allocation.
20319 针对不同问题规模，该文提出基于线性回归、逻辑回归、支持向量机的3种资源分配算法，并且基于临界值理论设计了支付价格算法，从而确保拍卖机制的可信性。在社会福利、分配准确率、算法执行时间、资源利用率等多个方面进行测试分析，取得了很好的效果。 For the different scale of problem, three resource allocation predict algorithms based on linear regression, logistic regression and Support VectorMachine (SVM) are proposed. Through the learning of the small-scale training set, the predict model can guarantee that the social welfare, allocation accuracy, and resource utilization in the feasible solution are very close to the optimal allocation solution.
20320 为解决传统遥感图像分类方法特征提取过程复杂、特征表现力不强等问题，该文提出一种基于深度卷积神经网络和多核学习的高分辨率遥感图像分类方法。 To solve the problems of complex feature extraction process and low characteristic expressiveness oftraditional remote sensing image classification methods, a high resolution remote sensing image classificationmethod based on deep convolution neural network and multi-kernel learning is proposed.
20321 首先基于深度卷积神经网络对遥感图像数据集进行训练，学习得到两个全连接层的输出将作为遥感图像的两种高层特征； Firstly, the deepconvolution neural network is constructed to train the remote sensing image data set to learn the outputs oftwo fully connected layers, which are taken as two high-level features of remote sensing images.
20322 然后采用多核学习理论训练适合这两种高层特征的核函数，并将它们映射到高维空间，实现两种高层特征在高维空间的自适应融合； Then, the multi-kernel learning is used to train the kernel functions for these two high-level features, so that they can be mapped to the high dimensional space, where these two features are fused adaptively.
20323 最后在多核融合特征的基础上，设计一种基于多核学习-支持向量机的遥感图像分类器，对遥感图像进行精确分类。 Finally, with the combined features, a remote sensing image classifier based on Multi-Kernel Learning-Support Vector Machine(MKL-SVM) is designed for remote sensing image classification.
20324 实验结果表明，与目前已有的基于深度学习的遥感图像分类方法相比，该算法在分类准确率、误分类率和Kappa系数等性能指标上均有所提升， Experimental results show that compared with the existing deep learning based remote sensing classification methods, the proposed algorithm achieves improved results in terms of classification accuracy, error, and Kappa coefficient.