ID 原文 译文
5344 将认知无线电中的频谱分配技术应用到星地一体化网络中，能够实现卫星与地面通信网络的频谱共享，提高卫星通信系统的频谱利用率。 By using spectrum allocation technology of cognitive radio into integrated satellite and terrestrial networks, the satellite communication network can share spectrum with the terrestrial network and improve utilization efficiency offrequency spectrum in the satellite communication system.
5345 首先，建立一种星地一体化频谱资源共享模型，分析认知卫星下行链路使用地面网络空闲频谱的场景。 Firstly, a spectrum resource sharing model in integrated satel-lite and terrestrial networks was introduced, and the scenery that cognitive satellite downlinks use the vacant spectrum of terrestrial network was analyzed.
5346 然后，对干扰模型和信号模型进行推导及分析。 Then, the interference and signal model was analyzed.
5347 最后，考虑卫星地面终端的不同优先级类型，提出一种基于优先级的频谱分配方案，在保证下行卫星通信总吞吐量的同时，增加高优先级地面终端的吞吐量。 Finally, considering different priority types of satellite terrestrial terminals, a spectrum allocation scheme based on priority was proposed, which could ensure the total throughput in satellite downlink communication and increase the throughput of high-priority terrestrial terminals.
5348 针对目前民航运输业对机场延误预测高精度的要求，提出一种基于区域残差和长短时记忆（RR-LSTM）网络的机场延误预测模型。 Nowadays, the civil aviation industry has a high precision requirement of airport delay prediction, so an airportdelay prediction model based on the RR-LSTM network was proposed.
5349 首先，将机场的属性信息、气象信息和相关运行航班信息进行融合； Firstly, the airport information, meteorological in-formation and related flight information were integrated.
5350 然后，利用RR-LSTM 网络对融合后的机场数据集进行特征提取； Then, the RR-LSTM network was used to extract the features of thefused airport data set.
5351 最后，构建 Softmax 分类器对机场延误分类预测。 Finally, the Softmax classifier was adopted to classify and predict the airport delay.
5352 所提RR-LSTM 网络模型既能有效提取机场延误数据的时间相关性，又能避免深层 LSTM 网络的梯度消失问题。 The proposedRR-LSTM network model can not only extract the time correlation of airport delay data effectively, but also avoid the gradi-ent disappearance problem of deep LSTM network.
5353 实验结果表明，RR-LSTM 网络模型预测准确率可达 95.52%，取得了比传统网络模型更好的预测效果。 The experimental results indicate that the RR-LSTM network model hasa prediction accuracy of 95.52%, which achieves better prediction results than the traditional network model.