ID 原文 译文
903 (2)隐层单元中使用批归一化，减少数据协方差漂移及加速网络训练; Second, we use batch normalization before each hidden layer unit to reduce covariance drift of data and accelerate the network training procedure.
904 (3)隐层单元间构建稠密连接，缓解梯度消失问题并实现特征复用。 Finally, a direct connection between every two units isadopted to reuse hierarchical features, and solve the problem of gradient vanishing.
905 通过 Indian Pines、Pavia University 与 Salinas 数据集进行综合测评，表明该方法优于若干最新深度学习方法，特别在小规模样本下具有优异的分类性能。 The comprehensive evaluation of experi-ments on different datasets such as Indian Pines, Pavia University and Salinas are conducted to show the performance of the SSCDenseNet, and the results show that the proposed method outperforms several state-of-the-art deep learning based meth-ods in terms of classification performance, especially under small-scale samples.
906 为了辅助医生规划非小细胞肺癌(Non-Small Cell Lung Cancer，NSCLC)患者治疗和复查方案，提出了一种基于 CT 影像组学的 NSCLC 预后分析方法。 In order to assist doctors in planning treatment and review programs for non-small cell lung cancer(NSCLC)patients, a prognostic survival analysis method based on CT radiomics was proposed.
907 首先，对患者肺部 CT 影像中的肿瘤区域进行分割; First, we segmented the tumorareas in the lung CT images.
908 然后，对肿瘤区域进行影像组学特征提取、优化; Then, we extracted and optimized the radiomics features.
909 最后，将优化后的特征数据与患者的预后生存情况作为输入，利用机器学习的方法构建预后分析模型，预测患者的预后生存时间范围。 Finally, the optimized features and the patients'prognosis survival were taken as input, and the prognostic analysis model was constructed by using machine learning method to predict the prognosis survival time range of the patients.
910 选用 124 例 NSCLC 患者数据进行实验，以具有临床意义的 3 年生存期为预测界限，对患者预后生存时间范围进行预测。 The data of 124 NSCLC patients were selected and the clin-ical significance of 3-year survival was used as the predictive limit to predict the prognosis survival time range.
911 实验结果表明，预后分析模型的预测准确率达到 91.9% ，可以有效地辅助医生对非小细胞肺癌患者的预后情况进行更加精准的评估，制定出更具个性化的治疗与复查方案。 The experimen-tal results showed the prediction accuracy of the model reached 91. 9% , which could effectively assist doctors to carry out moreaccurate assessment and develop more personalized treatment and review programs for NSCLC patients.
912 在无线片上网络中，无线通信拥塞和故障对整个片上网络的通信效率具有严重影响。 In wireless networks-on-chip, wireless communication congestion and fault have a severe impact on thecommunication efficiency of the entire network-on-chip.