ID 原文 译文
23115 该文共采集 39 名健康被试的实验数据，通过对数据的特征值提取等预处理，结合随机森林算法对最优特征子集进行选择，采用支持向量机(SVM)分类算法对 3 种压力状态进行分类预测。 Features are extracted from the data and the random forest is used to select the optimal stress-related feature combination, which is used to train and test the Support Vector Machine (SVM) classifier.
23116 实验结果表明，通过随机森林特征选择优化后的 SVM 分类，与通用的单一 SVM 分类算法相比，具有更好的分类识别效果，对 3 种压力状态的分类准确率可从 78%提高至 84%。 Finally, the results show that the combination of random forest feature selection and SVM achieves a better performance. The accuracy is improved from 78% to 84% in the three states' detection.
23117 显著性检测是指自动提取未知场景中符合人类视觉习惯的兴趣目标的方法。 Saliency detection is to find the most important object automatically according to the human visual in the unknown scene.
23118 为了进一步提高检测的准确性，该文提出了利用鲁棒前景种子的流形排序进行显著性检测的算法。 For improving the precision of saliency detection, the saliency detection based on robust foreground seeds via manifold ranking is proposed in this paper.
23119 首先利用角点检测和边缘连接算法得到两个不同的凸包，用它们的交集初步确立目标区域的大致位置； Firstly, the two different convex hulls are got by the Harris corner and boundary connectivity algorithm. And the original object region is defined by the intersection about the above convex hulls.
23120 然后利用凸包外边缘作为标准对凸包内的超像素进行相似度检测，将与大部分外边缘相似的超像素去除，得到更准确的目标样本作为前景种子； Secondly, the superpixels in convex hull are done the similarity detection with the outer edge of the convex hull. The superpixels are removed when they are similar to most of the outer edge, and the more precision foreground seeds are got.
23121 利用锚点图构建新的图结构表示数据节点之间的关系； Using the anchor graph, a novel graph construction is built to express the relationship between data nodes.
23122 接着通过基于前景和背景种子的流形排序算法对图像所有区域进行排序，并得到两种不同的显著性检测图； And then, two different kinds of salient results will be got based on ranking on manifolds using foreground and background seeds respectively.
23123 最后借助代价函数对显著性图进行优化，得到最终的显著性检测结果。 Finally, the saliency map is got through optimizing a novel cost function.
23124 经实验表明，与几种经典算法对比，该文方法可以进一步提高显著性算法的精确度和召回率。 Experimental results prove that the proposed algorithm improves the performance evaluation of precision and recall rate further.