ID 原文 译文
16645 首先，融合影像组学特征和通过卷积神经网络提取的高阶特征构造分析CT征象所需的特征集; Firstly, features sets are extracted of CT signs by combing the radiomics features with the higher-orderfeatures extracted by convolutional neural network.
16646 接着，在混合特征集的基础上利用进化搜索机制优化集成学习分类器，实现对7种肺结节征象的识别和量化打分; Then, the ensemble classifier is optimized by the evolutionarysearch mechanism based on the mixed feature sets, and it is used to realize quantitative scores for 7 CT signs.
16647 最后，将7种CT征象的量化打分输入到一个利用差分进化算法优化产生的多分类器，实现肺结节恶性度的分级计算。 Finally, 7 quantitative scores are input to the optimized multi-classifier to achieve the grading of malignant nodules in the lung.
16648 在实验研究中使用LIDC-IDRI数据集中的2000个肺结节样本进行进化集成学习器和恶性度分级器的训练和测试。 In the experience, 2000 samples of lung nodules in LIDC-IDRI data set are used to trainand test the proposed method.
16649 实验结果显示对7种CT征象的识别准确率可达0.9642以上，肺结节恶性度分级的准确率为0.8618，精确率为0.8678，召回率为0.8617，F1指标为0.8627。 The results show that the recognition accuracy of the 7 CT signs can reach morethan 0.9642, the grading accuracy reaches 0.8618, the precision reaches 0.8678, the recall reaches 0.8617, andthe F1 index reaches 0.8627.
16650 与多个典型算法的比较显示，该文方法不但具有较高的准确率，而且可对相关CT征象进行量化分析，使得对恶性度的分级结果更具可解释性。 With respect to typical algorithms, the proposed method not only has highaccuracy, but also can quantitatively analyze the CT signs that make the grade result of malignancy more interpretive.
16651 针对频谱短缺、基站负荷过高、通信系统功耗较大等问题，考虑不完美的信道状态信息，该文提出一种基于非正交多址接入的无线携能(SWIPT)D2D网络鲁棒能效(EE)最大化资源分配算法(SREA)。 In order to resolve the problems of spectrum shortage, large power consumption, and excessive loadat base stations, a Simultaneous Wireless Information and Power Transfer (SWIPT)-based Robust EnergyEfficiency (EE) Algorithm (SREA) with imperfect channel state information is proposed to maximize the totalEE in Non-Orthogonal Multiple Access (NOMA) assisted Device-to-Device (D2D) networks.
16652 考虑用户的服务质量约束以及最大发射功率约束，基于随机信道不确定性建立鲁棒能效最大化资源分配模型。 Considering theusers' Quality of Service (QoS) constraints and maximum transmit power constraints, a robust EEmaximization-based resource allocation model is established based on random channel uncertainties.
16653 利用Dinkelbach和变量替换方法，将原NP-hard问题转换为确定性的凸优化问题，通过拉格朗日对偶理论求得解析解。 Moreover,the original NP-hard problem is transformed into a deterministic convex optimization problem by usingDinkelbach’s method and the variable substitution method. And the analytical solutions are obtained through Lagrange dual theory.
16654 仿真结果表明，所提算法在保证蜂窝用户通信质量的同时，能够有效提高D2D用户的能效性和鲁棒性能。 Simulation results demonstrated that the proposed algorithm can effectively improve thesystem EE and the robustness of D2D users while ensuring the communication quality of cellular users.