ID 原文 译文
17865 邻道干扰(ACI)抑制中需要获取干扰信号非线性特征进行信号重建与抵消，因此接收机需使用高速率宽带模数转换器(ADC)采集干扰信号，这将大幅增加接收机成本。 In Adjacent Channel Interference (ACI) suppression, in order to obtain the nonlinear characteristicsof interference signal for reconstruction and cancellation, the receiver needs to use high-sampling-rate widebandAnalog-to-Digital Converter (ADC) to sample interference signal, which will greatly increase the cost of thereceiver.
17866 针对上述问题，该文提出一种采用干扰信号带外分量卷积反演的邻道干扰抑制方法， To solve the problem, a ACI suppression method based on deconvolution of interference signal’s out-of-band component is proposed in this paper.
17867 利用接收的干扰信号带外非线性分量，计算并消除相邻帧之间的影响，由窄带部分卷积信号帧构造出线性卷积信号帧，然后用正则化最小二乘方法恢复原始非线性宽带干扰信号，从而降低ADC采样率。 By using the known out-of-band nonlinear component, theinfluence between adjacent frames is calculated and eliminated, and then the narrow band linear convolutionframe is constructed from the partial convolution frame. Finally, the original wide band signal is recovered byregularized least square method, thus reducing the ADC sampling rate.
17868 仿真验证结果表明当采样率仅为传统方案1/3，所提方法带来的残余干扰不高于底噪6 dB。 The simulation results show that whenthe sampling rate is only 1/3 of the traditional scheme, the residual interference brought by the proposedmethod is not higher than the noise floor of 6 dB.
17869 针对难以准确有效地提取混合失真图像质量特征的问题，该文提出一种基于空间分布分析的图像质量评价方法。 Considering the problem that it is difficult to accurately and effectively extract the quality features ofmixed distortion image, an image quality assessment method based on spatial distribution analysis is proposed.
17870 首先将图像进行亮度系数归一化处理，然后将图像进行分块，利用卷积神经网络(CNN)进行端对端的深度学习，采用多层次卷积核堆叠的方法获取图像的质量感知特征，并通过全连接层将特征映射到图像块的质量分数。 Firstly, the brightness coefficients of the image are normalized, and the image is divided into blocks. While the Convolutional Neural Network (CNN) is used for end-to-end depth learning, the multi-level stacking of convolution cores is applied to acquire image quality perception features. The feature is mapped to the massfraction of the image block through the full connection layer, then the quality pool is obtained by aggregatingthe quality of the block.
17871 再将块质量分数汇总获取质量池，通过对质量池中局部质量的空间分布情况进行分析，提取能够表征其空间分布情况的特征，然后采用神经网络建立局部质量到整体质量的映射模型，将图像的局部质量进行汇总。 Through the analysis of the spatial distribution of local quality in the quality pool, thefeatures that can represent its spatial distribution are extracted, and then the mapping model from local qualityto overall quality is established by the neural network to aggregate the local quality of the image.
17872 最后在MLIVE, MDID2013, MDID2016混合失真图像库中进行性能测试以及与相关的对比算法进行比较，验证了该算法的有效性。 Finally, the effectiveness of the algorithm is verified by the performance tests in MLIVE, MDID2013 and MDID2016 mixed distortion image databases.
17873 一直以来，情绪是心理学、教育学、信息科学等多个学科的研究热点，脑电信号(EEG)因其客观、不易伪装的特点，在情绪识别领域受到广泛关注。 Emotion has always been a research hot spot in many disciplines such as psychology, education, andinformation science.  Electro EncephaloGram(EEG) signal has received extensive attention in the field ofemotion recognition because of its objective and not easy to disguise.
17874 由于人类情绪是大脑多个脑区相互作用产生的，该文提出一种基于同步性脑网络的支持张量机情绪分类算法(SBN-STM)， Since human emotions are generated bythe interaction of multiple brain regions in the brain, an algorithm of Support Tensor Machine based onSynchronous Brain Network (SBN-STM) for emotion classification is proposed.