ID 原文 译文
17995 使用小卷积核获取局部细节特征；以端到端的方式训练网络。 The local details are obtained by using small convolution kernels, and the network is trained in an end-to-end manner.
17996 实验中，通过设置不同卷积核尺寸和非局部模块层数，优化网络结构。 Inthe experiment, the network structure is optimized by setting different convolution kernel sizes and non-localmodule layers.
17997 实验结果表明，该文所提算法与传统的基于纹理特征的车位占用检测算法相比，无论在预测精度还是模型的泛化性能，均具有显著的优势。 The experimental results show that compared with the traditional texture feature-based parkingspace occupancy detection algorithm, the proposed algorithm has significant advantages in both predictionaccuracy and generalization performance of the model.
17998 与当前广泛应用的基于局部特征提取的卷积神经网络相比，该算法具有较大的优势。 At the same time, compared with the currently widelyused convolutional neural network based on local feature extraction, the algorithm also has great advantages.
17999 在真实场景中，该算法同样具有较高精度，具备实际应用价值。 In real scenes, the algorithm also has high precision and has practical application value.
18000 免授权非正交多址接入技术(NOMA)结合多用户检测技术(MUD)，能够满足大规模机器通信(mMTC)场景中的大连接量、低信令开销和低时延传输等需求。 Grant-free Non-Orthogonal Multiple Access (NOMA) combined with Multi-User Detection (MUD)technology can meet the requirements of large connection volume, low signaling overhead and low latencytransmission in massive Machine Type Communications (mMTC) scenarios.
18001 在基于压缩感知(CS)的MUD算法中，活跃用户数往往作为已知信息，而实际通信系统中很难准确估计。 In the MUD algorithm based on Compressed Sensing (CS), the number of active users is often used as known information, but it is difficult to accurately estimate in the actual communication system.
18002 基于此，该文提出一种改进稀疏度自适应匹配的多用户算法(MSAMP-MUD)。 Based on this, this paper proposes a multi-useralgorithm (Modified Sparsity Adaptive Matching Pursuit MUD, MSAMP-MUP) to improve the adaptivematching of sparsity.
18003 该算法首先利用广义Dice系数匹配准则选择与残差最匹配的原子，更新用户支撑集； Firstly, the algorithm uses the generalized Dice coefficient matching criterion to select theatom that best matches the residual, and updates the user support set.
18004 当残差能量接近噪声能量时，终止迭代，从而获得最终支持集； When the residual energy is close to thenoise energy, the iteration is terminated to obtain the final support set;