Subjects: Civil Engineering and Building Construction >> Civil Construction Engineering submitted time 2018-07-18 Cooperative journals: 《土木建筑工程信息技术》
Abstract： Deep foundation pit engineering is a very complicated geotechnical engineering problems, involved in the soil properties, supporting structure, groundwater and the surrounding environment, such as the rationality of the deep foundation pit supporting scheme selection directly affects the safety, economy, the construction period, etc. In the support design of deep foundation pit, it is necessary to combine the situation of the site and the surrounding environment, and the innovative choice of support type can solve both the practical engineering problems and the comparative advantages of all aspects. Now taking a deep foundation pit supporting design scheme is discussed, through the design calculation, construction, the deformation monitoring and economic aspects such as comparative analysis, the multi-index analysis of piles and pile under the supporting structure of comprehensive benefits, on subsequent similar project will have a positive guidance and reference significance.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-05-02 Cooperative journals: 《计算机应用研究》
Abstract： The mobile apps mostly communicate with servers via HTTP, which makes port-based method ineffective. Furthermore, depth packet inspection and flow-based classifiers have difficulties in designing features and labeling samples manually. Motivated by the excellence of computer vision, this paper proposed a method of mobile app traffic identification based on visual perception features. First, it converted the app traffic flows into vision-meaningful images. Collecting real traffic from the network gateway, it created the IMTD17 dataset. Then, it designed a two-dimensional convolutional perception network (2D-CPN) with the ability of visual feature extraction. The network realized the learning of massive unlabeled samples by the convolutional autoencoder, and used multi-class regression to create the mapping from the latent feature to the app categories. The experimental results show that the identification accuracy of the approach satisfies the practical requirement.
Hits
Hits
Downloads
Comment