交通流量VNNTF神经网络模型多步预测研究

研究了VNNTF 神经网络（Volterra neural network trafficflow model,VNNTF） 交通流量混沌时间序列多步预测问题. 通过分析比较交通流量混沌时间序列相空间重构的嵌入维数和Volterra 离散模型之间的关系,给出了确定交通流量Volterra 级数模型截断阶数和截断项数的方法,并在此基础上建立了VNNTF 神经网络交通流量时间序列模型;设计了交通流量Volterra 神经网络的快速学习算法;最后,利用交通流量混沌时间序列对VNNTF 网络模型,Volterra 预测滤波器和BP 网络进行了多步预测实验,比较了多步预测结果的仿真图、绝对误差的柱状图以及归一化后的方均根;实验结果表明VNNTF 神经网络的多步预测性能明显优于Volterra 预测滤波器和BP 神经网络.     

Cold-Start Link Prediction via Weighted Symmetric Nonnegative Matrix Factorization with Graph Regularization

Link prediction has attracted wide attention among interdisciplinary researchers as an important issue in complex network. It aims to predict the missing links in current networks and new links that will appear in future networks. Despite the presence of missing links in the target network of link prediction studies, the network it processes remains macroscopically as a large connected graph. However, the complexity of the real world makes the complex networks abstracted from real systems often contain many isolated nodes. This phenomenon leads to existing link prediction methods not to efficiently implement the prediction of missing edges on isolated nodes. Therefore, the cold-start link prediction is favored as one of the most valuable subproblems of traditional link prediction. However, due to the loss of many links in the observation network, the topological information available for completing the link prediction task is extremely scarce. This presents a severe challenge for the study of cold-start link prediction. Therefore, how to mine and fuse more available non-topological information from observed network becomes the key point to solve the problem of cold-start link prediction. In this paper, we propose a framework for solving the cold-start link prediction problem, a joint-weighted symmetric nonnegative matrix factorization model fusing graph regularization information, based on low-rank approximation algorithms in the field of machine learning. First, the nonlinear features in high-dimensional space of node attributes are captured by the designed graph regularization term. Second, using a weighted matrix, we associate the attribute similarity and first order structure information of nodes and constrain each other. Finally, a unified framework for implementing cold-start link prediction is constructed by using a symmetric nonnegative matrix factorization model to integrate the multiple information extracted together. Extensive experimental validation on five real networks with attributes shows that the proposed model has very good predictive performance when predicting missing edges of isolated nodes.     

一种融合节点属性信息的社会网络链接预测方法

随着大规模社会网络的发展,链接预测成为了一个重要的研究课题。研究了在社会网络中融合节点属性信息进行链接预测,在传统的社会-属性网络图模型的基础上,将节点属性的类别这一重要参量加入到网络构建中。基于此,提出了一系列为网络中不同类型的连边分配边权重的方法,最后通过随机游走的方法进行网络链接的预测。实验表明,所提链接预测方法相比同类方法有明显的效果提升。     

Temporal link prediction in multi-relational network

Link prediction problem in complex networks has received substantial amount of attention in the field of social network analysis. Though initial studies consider only static snapshot of a network, importance of temporal dimension has been observed and cultivated subsequently. In recent times, multi-domain relationships between node-pairs embedded in real networks have been exploited to boost link prediction performance. In this paper, we combine multi-domain topological features as well as temporal dimension, and propose a robust and efficient feature set called TMLP (Time-aware Multi-relational Link Prediction) for link prediction in dynamic heterogeneous networks. It combines dynamics of graph topology and history of interactions at dyadic level, and exploits time-series model in the feature extraction process. Several experiments on two networks prepared from DBLP bibliographic dataset show that the proposed framework outperforms the existing methods significantly, in predicting future links. It also demonstrates the necessity of combining heterogeneous information with temporal dynamics of graph topology and dyadic history in order to predict future links. Empirical results find that the proposed feature set is robust against longitudinal bias.     

基于PCA优化的神经网络飞机燃油消耗预测方法

针对传统方法存在的不足,提出了基于主成分分析法优化的Elman神经网络飞机燃油消耗预测方法。利用主成分分析法降低神经网络输入维数。构建主成分分析与Elman神经网络模型,进行基于飞参数据的实例分析,并将几种神经网络的预测效果进行了对比;提出了基于K-S检验法预测结果冗余修正法并进行了修正。误差指标和预测图像表明与主成分分析结合后Elman神经网络对飞机燃油消耗的预测性能优于其他传统神经网络,且K S检验法能够有效实现对预测结果的修正。     

Deep learning networks for stock market analysis and prediction: Methodology,data representations,and case studies

We offer a systematic analysis of the use of deep learning networks for stock market analysis and prediction. Its ability to extract features from a large set of raw data without relying on prior knowledge of predictors makes deep learning potentially attractive for stock market prediction at high frequencies. Deep learning algorithms vary considerably in the choice of network structure, activation function, and other model parameters, and their performance is known to depend heavily on the method of data representation. Our study attempts to provides a comprehensive and objective assessment of both the advantages and drawbacks of deep learning algorithms for stock market analysis and prediction. Using high-frequency intraday stock returns as input data, we examine the effects of three unsupervised feature extraction methods—principal component analysis, autoencoder, and the restricted Boltzmann machine—on the network’s overall ability to predict future market behavior. Empirical results suggest that deep neural networks can extract additional information from the residuals of the autoregressive model and improve prediction performance; the same cannot be said when the autoregressive model is applied to the residuals of the network. Covariance estimation is also noticeably improved when the predictive network is applied to covariance-based market structure analysis. Our study offers practical insights and potentially useful directions for further investigation into how deep learning networks can be effectively used for stock market analysis and prediction.     

Social network analytics for churn prediction in telco: Model building,evaluation and network architecture

Social network analytics methods are being used in the telecommunication industry to predict customer churn with great success. In particular it has been shown that relational learners adapted to this specific problem enhance the performance of predictive models. In the current study we benchmark different strategies for constructing a relational learner by applying them to a total of eight distinct call-detail record datasets, originating from telecommunication organizations across the world. We statistically evaluate the effect of relational classifiers and collective inference methods on the predictive power of relational learners, as well as the performance of models where relational learners are combined with traditional methods of predicting customer churn in the telecommunication industry. Finally we investigate the effect of network construction on model performance; our findings imply that the definition of edges and weights in the network does have an impact on the results of the predictive models. As a result of the study, the best configuration is a non-relational learner enriched with network variables, without collective inference, using binary weights and undirected networks. In addition, we provide guidelines on how to apply social networks analytics for churn prediction in the telecommunication industry in an optimal way, ranging from network architecture to model building and evaluation.     

Exploring network reliability by predicting link status based on simplex neural network

Complex networks are graph-based structures with non-trivial topological features that frequently occur in real systems. Link prediction plays an important role in various real-world networks application, such as recommendation systems, protein structure prediction, packet forwarding strategy optimization, etc. The existing link prediction approaches mainly focus on superficial heuristic features, while ignoring high-order structure information. In this paper, we propose a deep-learning based model, named Weisfeiler–Lehman Simplex Neural Network (WL-SNN), which can learn the high-order simplex information of the network. In particular, we design a third-order Laplace operator to extract the simplicial features and utilize the graph convolutional network to compensate for the possible deficiencies of the model resulting from the single-channel features. Furthermore, we use the Weisfeiler–Lehman algorithm to extract closed subgraphs of the target, which significantly enhances the adaptability of the model to large-scale networks. Experimental results on six real-world networks show that our approach achieves comparable performance in the link prediction task as well as in the stability analysis of the network.     

改进人工蜂群算法优化RBF神经网络的短时交通流预测

为了提高径向基函数RBF神经网络预测模型对短时交通流的预测准确性,提出了一种基于改进人工蜂群算法优化RBF神经网络的短时交通流预测模型。利用改进人工蜂群算法确定RBF网络隐含层的中心值以及隐含层单元数,然后训练改进的人工蜂群算法RBF神经网络预测模型,并将其应用到某城市4天的短时交通流量数据的验证。将实验结果与传统RBF神经网络预测模型、BP神经网络预测模型和小波神经网络预测模型进行了比较。对比结果表明,该方法对短时交通流具有更高的预测准确性。     

Welcoming two new Co-Editors-in-Chief for KAIS

This paper addresses link prediction problem in directed networks by exploiting reciprocative nature of human relationships. It first proposes a null model to present evidence that reciprocal links influence the process of “triad formation”. Motivated by this, reciprocal links are exploited to enhance link prediction performance in three ways: (a) a reciprocity-aware link weighting technique is proposed, and existing weighted link prediction methods are applied over the resultant weighted network; (b) new link prediction methods are proposed, which exploit reciprocity; and (c) existing and proposed methods are combined toward supervised prediction to enhance the prediction performance further. All experiments are carried out on two real directed network datasets.     

面向异质变分超图自动编码器的超边链接预测模型

如何采用超边建模网络数据中的多元关联关系,实现潜在超边链接关系的预测具有重要的现实意义。现有方法主要集中于研究具有成对关系的网络数据,然而,直接将现有的链接预测方法用于超图网络中的超边链接预测具有一定的局限性。因此,提出基于异质变分超图自动编码器的超边链接预测模型(heterogeneous variational hypergraph autoencoder,HVGAE)。首先,利用超图卷积实现变分超图自动编码器,将超图网络数据转换成一种低维空间表示;其次,加入节点近邻度函数,最大程度地保留其结构信息,从而构建异质超图网络超边链接预测模型。针对三种不同类型的超图网络进行实验,结果表明相比其他的基准方法,HVGAE模型获得了较好的预测结果,说明其能够较好地解决超图网络中的超边链接预测问题。     

Fusing functional connectivity with network nodal information for sparse network pattern learning of functional brain networks

Sparse learning methods have been powerful tools for learning compact representations of functional brain networks consisting of a set of brain network nodes and a connectivity matrix measuring functional coherence between the nodes. However, these tools typically focus on the functional connectivity measures alone, ignoring the brain network nodal information that is complementary to the functional connectivity measures for comprehensively characterizing the functional brain networks. In order to provide a comprehensive delineation of the functional brain networks, we develop a new data fusion method for heterogeneous data, aiming at learning sparse network patterns to characterize both the functional connectivity measures and their complementary network nodal information within a unified framework. Experimental results have demonstrated that our method outperforms the best alternative method under comparison in terms of accuracy on simulated data as well as both reproducibility and prediction performance of brain age on real resting state functional magnetic resonance imaging data.     

面向软件缺陷预测的网络嵌入特征研究

已有研究根据软件的代码依赖、修改历史、协同开发关系等,建立网络模型来预测软件的缺陷;近年来,网络嵌入技术广泛用于软件网络分析,显著提升了缺陷预测效果.本研究发现不同软件关联网络和网络嵌入算法的组合将影响缺陷预测性能.具体地,本文针对3种软件关联网络(类依赖网络、文件耦合网络和开发者贡献网络),并应用6类网络嵌入方法,分...     

基于共同邻居惩罚的复杂网络链路预测方法

链接预测是确定用户间关系的基本工具。通过相似性度量进行链路预测是一种常见的方法,提出一种基于相似度的链路预测算法,根据网络结构及拓扑特性来确定相似度,引入优化链路预测度量方法,将聚类系数作为网络结构性质。此外,并考虑共享邻域,得到较其他同类链路预测方法更好的性能。实验结果表明,提出的算法性能优于经典算法。结合在Facebook、Twitter与新浪微博等社交网络环境中的实验结果可知,SLP-CNP法较其他算法具有更优精度与效率。在未来的工作中,还可尝试在所提方法的基础上,提升在加权网络、有向网络和二部网络中的适用性。     

基于自适应门控图神经网络的交通流预测

交通流预测是智能交通系统中的重要组成部分,由于交通数据的复杂性,长期而又准确的交通流预测一直是时间序列预测中最具挑战性的任务之一。近年来,研究人员将基于图神经网络的时空图建模方法应用于交通流预测任务,并取得了良好的预测性能。然而,现有的图建模方法仅通过预定义的邻接结构反映道路网络中的空间依赖关系,忽略了各节点之间的序列关联关系对预测的重要性。针对这一局限性,提出了一种自适应门控图神经网络（Ada-GGNN）,其核心为通过空间传递模块同时捕获道路网络的空间结构及自适应的时序相关性,并通过门控机制学习节点上的时间序列特征。在两个真实交通网络数据集PeMSD7和Los-loop上的实验结果证明了该模型具有更优越的性能。     

基于混合算法的通信用户规模预测方法研究

准确地对通信用户规模进行预测对于通信运营商的决策具有十分重要的意义,而现有的常规预测方法存在预测误差较大、预测速率低等问题。研究一种基于RBF神经网络的通信用户规模预测模型。为了使得RBF神经网络算法预测性能更优,使用梯度下降算法与遗传算法混合对RBF神经网络进行参数优化,提高预测模型收敛效率。实例分析表明,使用本文研究的混合RBF神经网络预测模型的预测结果明显优于其他传统的预测模型。同时,在预测速度上也具有较大的优势。     

Adaptative time constants improve the prediction capability of recurrent neural networks

Classical statistical techniques for prediction reach their limitations in applications with nonlinearities in the data set; nevertheless, neural models can counteract these limitations. In this paper, we present a recurrent neural model where we associate an adaptative time constant to each neuron-like unit and a learning algorithm to train these dynamic recurrent networks. We test the network by training it to predict the Mackey-Glass chaotic signal. To evaluate the quality of the prediction, we computed the power spectra of the two signals and computed the associated fractional error. Results show that the introduction of adaptative time constants associated to each neuron of a recurrent network improves the quality of the prediction and the dynamical features of a neural model. The performance of such dynamic recurrent neural networks outperform time-delay neural networks.     

基于深度神经网络的社会媒体网络分析

社会媒体网络中不仅包含了用户、文本、图片和视频等多种模态的数据,还包含了反映不同模态数据之间交互的群体特征。为了更好地描述社会媒体网络,从而为上层应用提供更好的服务,提出了一种基于深度神经网络的社会媒体网络模型。该模型采用深度神经网络对单个模态的数据进行学习,从而得到任意一个模态数据的潜在特征表示方法。对于两种不同模态的数据,利用具有高斯分布的先验矩阵与两个模态数据的后验分布建立反映这两个模态数据间群体特征的生成模型。实验结果表明,提出的模型在网络结构的链接分析中具有更好的预测效果,能有效地描述社会媒体网络的整体特征。     

基于集成学习的动态链接预测方法

链接预测是社会网络分析领域的关键问题。传统的链接预测方法大多针对社会网络的静态结构预测隐含的链接或者将来可能产生的链接,而忽视了网络在动态演变过程中的潜在信息。为了能更好地利用网络演变的动态信息,从而取得更好的链接预测效果,提出了一种基于网络结构演变规律的链接预测方法。该方法使用机器学习技术对网络结构特征的动态变化信息进行训练,学习每种结构特征的变化并得到一个分类器,为每个分类器加权得到最终集成的结果。在三个现实的合著者网络数据集上的实验结果表明,该方法的性能要高于静态链接预测方法和一个相关的动态链接预测方法。这说明,网络结构演变信息有助于提高链接预测效果。此外,实验还表明,不同的结构特征对网络动态变化的刻画能力也有所差别。     

基于门控循环图卷积网络的交通流预测

交通流预测在智能交通系统的建设中起着关键性的作用,然而现有预测方法无法准确地挖掘其潜在的时空相关性,而且大都采用全连接网络进行单步预测。为了进一步挖掘数据的时空特性以及提升长短期预测的精度,提出了一种门控循环图卷积网络（GR-GCN）模型。首先,利用频域上的图卷积结合门控循环单元（GRU）构建一个时空组件（STC）以同时捕获节点的时空相关性,充分地提取数据的时空特征;然后,利用该时空组件构成编码器单元,并将时间序列数据和路网结构数据输入其中;最后,使用门控循环单元作为解码器单元,并按照时间顺序将两者组成一个编码器—解码器（encoder-decoder）结构,依次解码出每个时刻的预测结果。在加利福尼亚交通局（Caltrans）性能评估系统中高速公路数据集PeMSD4和PeMSD8进行了实验。结果表明,所提模型GR-GCN在预测未来15 min、30 min、45 min和60 min的交通流量方面优于大多数现有基准模型,尤其是在长期预测方面。