ID 原文 译文
57018 利用链路预测技术可以预测出异构信息网络中存在但未被观察到,或者未来可能会出现的链路,更好地帮助用户理解网络的结构生成和演化规律. Link prediction is a necessary technique for predicting the existence of unobserved or future links in heterogeneousinformation networks. It is useful to make users better understand the generation and evolution of networks.
57019 然而,目前链路预测技术缺乏对多种特征的有效融合而影响预测准确性,且难以适应异构信息网络的异构性和动态性. However, current techniques lack the effective fusion of multiple features, often leading to nonsensical results.
57020 本文提出了一种层次化混合特征图模型(hierarchical hybrid feature graph, HHFG),充分考虑了异构信息网络的拓扑特征、语义特征和时序特征. Also, it is difficult for them to adapt to the heterogeneity and dynamics of heterogeneous-information networks. In this paper, we present a hierarchical-hybrid-feature-graph (HHFG) model by fully considering structural,semantic, and time features.
57021 提出了一种基于HHFG的链路预测算法,基于混合特征在HHFG上做随机游走,并采用梯度下降法学习特征权重,转移系数等参数,有效地保证了链路预测的准确性. Also, an HHFG based link-prediction algorithm is proposed to effectively guaranteeaccuracy. On one hand, it performs a random walk on HHFG based upon hybrid features. On the other hand,parameters such as feature weights and transition coefficients are learned by the gradient-descent method.
57022 通过实验验证了本文所提出的关键技术的可行性和有效性. The experiments demonstrate the feasibility and effectiveness of our key techniques.
57023 医学图像融合的目的是将多幅多模态医学图像的信息整合到一幅图像上,此图像有助于临床诊断,帮助医生精确观察细微病变,缩短病人的治疗周期. The purpose of medical-image fusion is to integrate the comprehensive information of multimodalmedical images into a single image, which is helpful for clinical diagnosis, increasing the accuracy of diseaseobservation by physicians, and shortening the treatment period.
57024 本文提出了一种新的解剖图像和功能图像的融合算法,选取了局部拉普拉斯滤波(local Laplacianfiltering, LLF)作为融合过程的分解工具,该工具在增强细节的同时保护边缘,保证解剖图像的细节信息不被功能图像的颜色信息遮盖. A new fusion algorithm for anatomical andfunctional images is proposed in this paper. Local Laplacian filtering (LLF) is chosen as the decompositiontool in the fusion process, which can enhance the details, protect the edges, and ensure that the details of theanatomical features in the fused images cannot be covered by the color information of the functional images.
57025 首先,利用LLF将原图像分解为近似图和一系列细节图. The steps of this algorithm are as follows: firstly, LLF decomposes the original image into an approximate image and aseries of detailed images.
57026 其次,对于近似图,结合区域能量和边缘能量提出一个改进的局部能量取大的融合规则; Secondly, for the approximate image, this paper proposes a fusion rule for an improvedlocal-energy maximum by combining the regional and edge energies.
57027 对于细节图,采用参数自适应的简化脉冲耦合神经网络(parameteradaptive simplified pulse coupled-neural network, PA-SPCNN)模型进行细节图融合,选取改进的拉普拉斯和(novel sum-modified-Laplacian, NSML)与彩色显著特征信息(color saliency feature, CSF)分别作为解剖图像和功能图像所对应的PA-SPCNN模型的外部刺激输入.最后,使用逆LLF变换获得融合图像. For detailed images, the parameter-adaptivesimplified-pulse-coupled neural-network (PA-SPCNN) model is used to fuse the detailed images. The novel sum?modified-Laplacian and color-saliency feature are selected as external-stimulus inputs of the PA-SPCNN modelin the anatomical and functional images, respectively. Finally, the fusion image is obtained by an inverse-LLFtransform.