ID	原文	译文
1573	实验结果表明:所提出算法具有较高的计算精度和较强的寻优能力，有较高的鲁棒性，	The experimental results indicate that the algorithm pro-posed has superior computational accuracy, effective optimization ability and high robustness.
1574	通过与自适应扫描和速度推测粒子群优化算法、K 均值聚类和灰狼优化混合算法、大邻域搜索和蚁群优化混合算法、基于精英选择的多种群人工蜂群算法、基于集覆盖的扩展节省算法、混合变邻域生物共栖搜索算法等 6 个算法对比证明了算法的有效性。	The effectiveness of the algo-rithm proposed is proved by comparing AGGWOA with 6 other algorithms including adaptive sweep plus velocity tentativePSO(Adaptive Sweep + VTPSO), K-means clustering GWO(K-GWO), hybrid large neighbourhood search algorithm withant colony optimization(LNS-ACO), elitism-based multiple colonies artificial bee colony(EBMC-ABC), set-covering-basedextended savings algorithm(SC-ESA), hybrid variable neighborhood symbiotic organisms search(HVNSOS).
1575	在非合作通信中，很多情况下由于信道恶化，使得接收信号的信噪比偏低，导致无法对符号速率这一重要参数进行准确估计。	In non-cooperative communications, due to the deterioration of the channel, the Signal-Noise Ratio (SNR)of the receiving signal is very low in many cases, resulting in the inability to accurately estimate the symbol rate.
1576	随机共振能够在一定程度上利用噪声能量，使其转移并增强微弱信号，小波变换则可以有效检测相位和幅度的瞬变，	Stochastic resonance can use noise energy to transfer and amplify the weak signals to some extent, and wavelet transform can effective-ly detect the instantaneous variation of phase and amplitude of the signals.
1577	利用二者各自优势，提出了一种将随机共振与小波变换联合进行 MPSK(Multiple Phase Shift Ke-ying，多进制数字相位调制)和 MQAM(Multiple Quadrature Amplitude Modulation，多进制正交幅度调制)信号符号速率的估计方法。	By using the advantages of both methods, a com-bination algorithm for estimating the symbol rate of MPSK and MQAM is proposed.
1578	先利用自适应参数调节随机共振为带噪信号匹配最佳系统参数，之后利用 Haar 小波变换进一步提取突变信息，不仅弥补了单独使用随机共振效果不佳及其作为非线性系统易发散的缺点，还降低了小波最佳尺度难以确定的影响。	First, the adaptive parameter-tuning sto-chastic resonance is used to match the optimal system parameters for noisy signals, and then the transient information is fur-ther extracted by Haar wavelet transform, which not only compensates for the shortcomings of the poor effect of using sto-chastic resonance alone and its easy divergence as a non-linear system, but also reduce the influence of the optimal scale of the wavelet.
1579	仿真实验表明，该方法能够在一定程度上提高输出峰值，降低信噪比门限，适合于低信噪比下的符号速率估计。	The simulation result shows that this method can improve the output peak and reduce the SNR threshold, whichis suitable for the symbol rate estimation under low SNR.
1580	为提高现有开关型随机脉冲噪声(Random-Valued Impulse Noise，RVIN)降噪算法的降噪性能，提出了一种基于卷积神经网络的非开关型 RVIN 快速降噪算法(Fast Non-switching RVIN Denoising Algorithm，FNRDA)。	To improve denoising effect and execution efficiency of the existing switching random-valued impulsenoise (RVIN)removal algorithms, we propose a convolutional neural network (CNN)-based fast non-switching RVIN de-noising algorithm (FNRDA), which consists of two serial CNN-based modules, i. e. , noise detector and denoiser.
1581	首先，利用噪声检测器随机地检测给定噪声图像中少量不同位置处的像素点;	Specifical-ly, we first use the noise detector to detect some randomly selected pixels of a given noisy image.
1582	然后，将检测为 RVIN 噪声点的个数除以被检像素点总数转化为噪声比例值;	Then we divide the numberof the detected noisy pixels by the total number of detected pixels to convert it into noise ratio, which can be treated as ameasure of the distortion level for the given noisy image.