ID	原文	译文
53927	论文采用梯度下降法推导出乘法迭代规则，为验证所提出的算法的有效性，利用Japser Ridge数据集和Urban数据集进行实验，并与其他经典方法进行对比，结果显示该方法具有更好的解混效果。	In this paper, the iterative rule of multiplication was derived by gradient descent method. In order to verify the effectiveness of the proposed algorithm, Japser Ridge data set and Urban data set were used for experiments, and compared with other classical methods, the results showed that this method had better unmixing effect.
53928	品质因数(FOM)是描述地基增强系统(GBAS)定位服务性能的重要参数，其适航符合性是指该参数达到相应适航标准。	The figures of merit(FOM) is an important parameter describing the positioning service performance of ground-based augmentation system(GBAS). Its airworthiness compliance means that the parameter meets the corresponding airworthiness standards.
53929	本文基于航空无线电技术委员会(RTCA)等的相关标准，深入分析研究了FOM的含义及解算过程，	Based on the relevant standards of the Radio Technical Commission for Aeronautics(RTCA), the meaning and calculation process of FOM are deeply analyzed and studied.
53930	在此基础上，结合中国民航GBAS适航的技术标准规定，给出了该参数适航符合性验证的方法、原理和流程，	On this basis, combined with the technical standards order of China Civil Aviation GBAS airworthiness, the method, principle and process of airworthiness compliance verification of this parameter are given.
53931	并基于相应动力学环境和X-Plane采集的飞行数据，对A类机载GBAS接收机的FOM进行了符合性验证仿真。	And in accordance with the corresponding dynamic environment and the flight data collected by X-Plane, the FOM of Class A airborne GBAS receiver is simulated for compliance verification.
53932	仿真结果及数据统计和分析表明，A类接收机的FOM满足适航性要求，与A类接收机有关FOM的适航标准吻合，证明所给品质因数适航符合性验证理论和方法的正确性。	The simulation results and data statistics and analysis show that the FOM of Class A receiver meets the airworthiness requirements and is consistent with the airworthiness standards of the Class A receiver related to the FOM, which proves the correctness of the given airworthiness compliance verification theory and method of figures of merit.
53933	研究成果可为我国机载GBAS接收机的适航审定提供相应的理论和方法支持。	The research results can provide corresponding theoretical and methodological support for the airworthiness certification of Chinese airborne GBAS receivers.
53934	目前，人脸美丽预测研究面临模型泛化能力欠佳、数据量不足、以及易于过拟合等问题。	At present, there exist some problems such as poor model generalization ability, insufficient data, and easy over-fitting in Facial Beauty Prediction research.
53935	十字绣网络(Cross-Stitch Network)通过激活多个网络，进行端到端的学习，自动决定共享层，但忽略了图像信息主次问题。	Cross-Stitch Network automatically determines the shared layer by activating multiple networks for end-to-end learning, but it ignores the issue of image information priority.
53936	因此，本文对十字绣网络进行改进，将其部分层网络更换为自注意力(Self-Attention)模块与长短时记忆(Long Short Term Memory，LSTM)模块，从而实现层与层之间、模块与模块之间的参数共享。	Therefore, this paper improves the Cross-Stitch Network, replacing part of its layer network with Self-Attention module and Long Short Term Memory(LSTM) module, to realize the parameter sharing between layers and between modules.