Search

The problem of community detection in multiplex networks (the networks with multiple layers and the same set of nodes in each layer) is fundamental in the field of network analysis and can be solved by a variety of methods. Usually the methods are unsupervised and detect communities by optimization of a chosen objective function (e.g. multiplex modularity). There are also semi-supervised approaches that use known metadata about communities (in the form of ground truth) on a part of the network considered to detect communities on the other part of network. Nevertheless, as far as we know, the field however has the lack of supervised methods that, for example, train a model on one multiplex network using all known ground truth metadata about communities therein and then apply it to another network to detect communities there (under the assumption that both networks are similar, in a sense). In this paper, we propose a supervised method that is based on the so-called layers convex flattening of multiplex networks (when multiple layers are aggregated to a single layer network for further processing) and modularity optimization of the flattened network. Our experiments with synthetic and real-world networks show the efficiency of the supervised method, particularly, by means of promising Normalized Mutual Information values (from 0.37 up to 0.79 on average) observed on several real-world networks for the community detection models trained on another network. [ABSTRACT FROM AUTHOR]

The current status of mine network was summarized. According to development goal of mine Internet of things and changing trend of information processing modes in future mine, developing requirements and trend of mine network were analyzed form aspects of network capacity, manageability, dense access, real-time performance, intelligentization, emergency communication after disaster, etc. Design principles of network of mine Internet of things were proposed including flattening, intelligentization, resource abstraction, etc. The application and developing requirements of key technologies in mine Internet of things were introduced such as wireless transmission coding, software-defined network, flow offloading, edge computation, network function virtualization, cognitive radio, energy capture, semantic network and so on.

With the development of wired broadband services,new requirements on the carrying ability of network was put forward by video-dominated services.The demand on bandwidth and network quality of wired broadband traffic grooming was analyzed,and a feasible network evolution solution were presented from the perspective of multicast technology application,BRAS and CDN deployment,backbone network architecture evolution and other point of view.

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)