ID 原文 译文
40736 针对实时变化且不同时段差异大的时间序列，提出一种基于高斯过程混合模型的预测算法。 Aiming at the time series that change in real time and differ greatly in different time periods, a prediction algorithm based on Gaussian process mixture model is proposed.
40737 该算法首先对时间序列进行预处理，并采用密度空间含噪聚类(DBSCAN)去除奇点。 Firstly, the time series is preprocessed and the singularities are removed by density-space noise-containing clustering(DBSCAN).
40738 然后针对扩展迪基-福勒(ADF)检验结果将时间序列分为常数项、平稳和非平稳三类， Then, according to the results of the extended Diki-Fowler test, the time series are divided into three categories: constant term, stationary term and non-stationary term.
40739 最后基于高斯过程混合(GPM)模型对各类时间序列进行预测，并和差分自回归移动平均模型(ARIMA)、支持向量机(SVM)、高斯过程(GP)模型进行性能对比。 Finally, the prediction of various time series is made based on the Gaussian process mixture(GPM) model, and the performance of the different autoregressive moving average model(ARIMA), support vector machine(SVM) and Gaussian process(GP) model is compared.
40740 以采购商品报价时间序列为例进行的预测结果表明:GP模型与GPM模型均能输出预测置信区间，给出预测结果的可信程度; Taking the time series of government procurement commodity quotes as an example, the results show that both the GP model and the GPM model can output prediction confidence intervals and give the credibility of the prediction results.
40741 GPM模型的优势是能够更精准刻画时间序列各时段差异，预测精度更高。 The advantage of the GPM model is that it can more accurately characterize the differences of time series in different periods, and the prediction accuracy is higher.
40742 针对基于深度学习的多尺度边缘检测不可避免出现自适应性低，参数增加，计算量大，检测边缘不连续等问题，本文提出一种基于改进整体嵌套的多尺度边缘检测方法。 Aiming at the problems of deep learning-based multi-scale edge detection inevitably low adaptability, increased parameters, large calculations, and discontinuous detection edges, this paper proposes a multi-scale edge detection method based on improved overall nesting.
40743 该方法将多尺度检测与弱监督模型相结合，解决参数多计算量大的问题。 The method combines multi-scale detection with weak supervision model to solve the problem of large amount of parameter calculation.
40744 为了充分利用卷积强大的特征表达能力，在整体嵌套边缘检测的基础上，提出了一种多尺度下深度学习结构，一个相互独立的多网络多尺度结构，由不同深度和输出的多个网络组合。 In order to make full use of the powerful feature expression ability of convolution, based on the whole nested edge detection, a multi-scale deep learning structure is proposed, which is an independent multi-network multi-scale structure, which is composed of multiple networks with different depths and outputs.
40745 同时引用整体嵌套的权重混合层，权重混合层将所有的弱监督预测结果连接到一起，并在训练的过程中学习混合权重。 At the same time, the whole nested weight mixing layer is referenced.The weight mixing layer connects all the weak supervised prediction results together and learns the mixed weight in the training process.