ID 原文 译文
25515 另一方面引入各向异性全变差空间正则化促进图像同质区域的平滑性，以提高解混的准确性。 On the other hand, the total vari-ation based spatial regularization is employed to reinforce the smoothness within the homogenous regions, hence improving the accuracy of unmixing．
25516 通过交替方向乘子法求解该模型，通过迭代，利用内外部双循环迭代方法对光谱加权因子和丰度系数进行优化。 The model is solved by the well-known alternating direction method of multiplier, in which the spectral factor based weights and the abundance coefficients are iteratively optimized using both the internal and external loops．
25517 模拟和真实的高光谱数据实验结果均表明本文提出的算法与现有同类算法相比能大幅提高混合像元分解的精度，在稀疏解混方面展现出了巨大的潜力。 The experimental results obtained from the simulated and the real datasets indicate that the proposed method could significantly improve the performance of unmixing compared to the other state-of-the-art methods．
25518 癫痫是一种常见的脑部疾病，通过脑电图能非侵入地定位人脑中的致痫区域。 Epilepsy is a recurrent cerebral disease, and electro encephalogram (EEG) provides a non-invasive way toidentify epileptogenic sites in the brain．
25519 为了辨别病灶性和非病灶性癫痫脑电信号，文章提出一种基于变分模态分解的癫痫脑电信号自动检测方法，首先将原信号分割成多个子信号，并对各子信号进行变分模态分解，然后从分解后的不同变分模态函数中提取精细复合多尺度散布熵和精细复合多尺度模糊熵两个特征并利用支持向量机进行分类。 In order to distinguish focal and non-focal epilepsy EEG signals, this paper proposes an automated epileptic EEG detection method based on variational mode decomposition． Firstly, the original signals are divided into several sub-signals, which are decomposed into intrinsic mode functions by using the variational mode decomposition (VMD). Furthermore, refined composite multiscale dispersion entropy (RCMDE) and refined composite multiscale fuzzy entropy (RCMFE) are extracted from each intrinsic mode function. Finally, the support vector machine (SVM ) isused to classify characteristics.
25520 针对癫痫脑电的公共数据集，最终的实验结果表明，准确率、灵敏度和特异度三个性能指标分别达到 94. 24% ，95. 58% 和 90. 64% ，ROC 曲线下面积达 0. 978。 For an epilepsy EEG signals' public data set, the final experimental performance measures of accuracy, sensitivity, and specificity reach 94. 24% , 95. 58% and 90. 64% respectively, and the area under the ROC curve is 0. 978.
25521 鉴于 Single Shot Multibox Detector (SSD)算法对中小目标检测时会出现漏检甚至错检的情况，提出一种改进的 SSD 目标检测算法，以提高中小目标检测的准确性。 Considering that the single shot multibox detector (SSD) algorithm will be missed or even false when it isused to detect the small and medium-sized objects, an improved SSD object detection algorithm is proposed to improve the accuracy of small and medium-sized objects detection．
25522 运用 Gradient-weighted Class Activation Mapping (Grad-CAM)技术对检测过程中的细节作可视化处理，并以类激活图的形式呈现各检测层细节，分析各检测层的类激活图发现 SSD 算法中待检测目标的错检以及中小目标的漏检现象与回归损失函数相关。 The details in the detection process are visualized with gradient-weighted class activation mapping (Grad-CAM) technology, and the details of each detection layer are shown in the form of class activation maps. Then it is noted that the phenomenon of the false or missed detection of the objects to be detected onsmall and medium-sized objects in the SSD algorithm is related to the regression loss function.
25523 据此，采用 Kullback-Leibler (KL)边框回归损失策略，利用 Non Maximum Suppression (NMS)算法输出最终预测框。 Accordingly, Kullback-Leibler (KL) border regression loss strategy is adopted and non- maximum suppression (NMS) algorithm is used to output the final prediction boxes．
25524 实验结果表明，改进算法相较于已有检测算法具有更高的准确率以及稳定性。 Experimental results show that compared with the existing detection algorithms, the improved algorithm in this paper has higher accuracy and stability．