ID 原文 译文
3053 仿真结果表明,与现有算法相比,所提算法能有效利用机会频谱资源,进一步提高信道利用率。 The simulation results show that compared with existing algorithms, the proposed al-gorithm can effectively utilize opportunistic spectrum resources and further improve channel utilization.
3054 如今,高精度室内定位服务因成为众多 5G 重大应用场景的关键支撑而受到广泛关注,其实现技术、实现方案不断更新,且各具优缺点及特异性。 Nowadays, high-precision indoor positioning service has witnessed an increasing interest because it has be-come the key support of many 5G major application scenarios, and the implementation technologies and mechanisms are continuously updated with advantages, disadvantages and specificities.
3055 因此,对高精度室内定位服务进行时效的、系统化的总结,并对其演进方向进行分析。 Therefore, a timely and systematic summary ofindoor-positioning was made, and that of prospects for where this domain was heading.
3056 首先,在总结已有的综述类文献的基础上,按定位技术、定位方案 2 种不同维度对室内定位领域进行分类总结; Firstly, based on the analysis of the existing papers, summarization of this domain was proposed from two aspects, such as positioning-techniques and positioning-methods.
3057 其次,提出了基于定位场景的分类,指出了其中蕴含的“隐性要求”; Secondly, a classification model was put forward based on the positioning scenarios and the “hid-den requirements” included were pointed out.
3058 再次,提出了定位系统评价指标体系并对现有高精度定位系统进行评估; Then, the evaluation indices system of positioning-systems was proposedand some of the existing high-accuracy positioning system was evaluated by it.
3059 最后,总结了高精度室内定位领域未来的演进方向,指出了网络一体化发展的趋势,提出了“在线即在位”等重要概念。 Finally, the direction of evolution abouthigh-precision indoor positioning domain was summarized, the development trend of integrated network was pointed out,and some important concepts, such as “online is inplace”, were proposed.
3060 针对快时变频分双工(FDD)大规模多输入多输出(MIMO)系统中因无线信道干扰使信道状态信息(CSI)矩阵中存在噪声以及多普勒频移导致的时间相关性使系统无法保证高可靠和低时延通信的问题,提出一种智能CSI 反馈方法。 In the frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) system, the chan-nel state information (CSI) matrix existed noise caused by the wireless channel interference and the time correlationcaused by Doppler shift. Because of these effects, the communication system couldn't guarantee the requirements of re-liability and low delay. An intelligent CSI feedback method was adopted.
3061 该方法利用卷积神经网络(CNN)和批标准化(BN)网络对 CSI 矩阵中的噪声进行提取并且学习信道的空间结构,通过注意力机制提取 CSI 矩阵间的时间相关性以提高 CSI 重构的精度。 The convolutional neural network (CNN) andbatch normalization (BN) network was used to extract the noise in the CSI matrix and learned the spatial structure of thechannel. The time correlation between the CSI matrices through the attention mechanism was extracted to improve theaccuracy of CSI reconstruction.
3062 利用标准的快时变信道模型仿真产生的数据对网络进行离线训练。 The data was generated by the standard fast time-varying channel model simulation totrain the network offline.