Time series anomaly detection is widely used to monitor the equipment sates through the data collected in the form of time series. At present, the deep learning method based on generative adversarial networks (GAN) has emerged for time series anomaly detection. However, this method needs to find the best mapping from real-time space to the latent space at the anomaly detection stage, which brings new errors and takes a long time. In this paper, we propose a long short-term memory-based variational autoencoder generation adversarial networks (LSTM-based VAE-GAN) method for time series anomaly detection, which effectively solves the above problems. Our method jointly trains the encoder, the generator and the discriminator to take advantage of the mapping ability of the encoder and the discrimination ability of the discriminator simultaneously. The long short-term memory (LSTM) networks are used as the encoder, the generator and the discriminator. At the anomaly detection stage, anomalies are detected based on reconstruction difference and discrimination results. Experimental results show that the proposed method can quickly and accurately detect anomalies.

With the rapid development of Mobile Internet, social media platforms explosively grow and greatly facilitate people to obtain and exchange information. Since any users can post arbitrary information on social media, some people with ulterior motives try to create and spread various misinformation for their own benefits, which might damage citizen rights and disturb social order. In this paper, we propose a novel rumor detection model based on Graph Convolution Networks (GCNs). Based on the real dataset from social media, we consider not only the static features such as users’ basic information and text contents, but also the dynamic features such as rumor propagation relations. The GCN-based model is used to represent the spreading structure of rumors, with graph convolution operator for node vector updating. We also optimize the feature fusion module and pooling module to make our model have better performance. Experiments on Sina Weibo dataset validate the performance of the propsed GCN-based model for rumor detection.

Fueled by the explosive growth of ultra-low-latency and real-time applications with specific computing and network performance requirements, the computing

The rapid developments in mobile Internet are reshaping our lives and activities. Understanding the user behaviors and dynamics in such a large-scale network is essential for better system design, service provisioning, and network management. In this paper, we focus on the interaction pattern between mobile users and servers based on the traffic flow data. Real traffic flow data is collected from the public network of ISPs by high-performance network traffic monitors. Traffic Flow-based Heterogeneous Information Network (TF-HIN) is introduced to represent the traffic interaction pattern, and node correlation characteristics are mined from TF-HIN. Based on the empirical analysis of traffic interaction pattern, we propose the coupled flow tensor to represent the relations among user, server and time, by incorporating correlations of user and server as auxiliary information. Two iterative algorithms, i.e. FTD and FTD-NFS, are proposed for coupled flow tensor decomposition, and the latent factors are used for user clustering. We evaluate the proposed user clustering algorithms by using benchmark datasets, and also analyze the user clustering results from real traffic flow dataset. Numerical experiments show that the use of coupled flow tensor with auxiliary information provides a novel and scalable user clustering method and improves the clustering accuracy.