Deep Neural Network Based Complex-Heterogeneous Cyberspace Cartographic Visualization

It seems complicated to imagine our life without the Internet, but it is only a few decades old, and Internet forms most extensive cyberspace environment. Cyberspace non-physical environment created by joint computers inter-operating on network. The complex heterogeneous virtual computer world that encompasses variety of computers, network devices, systems have been manufactured different entities. As an essential spatial cognitive tool, map has significantly contributed human civilization for thousands years. However, cartographic elements traditional maps are mostly geospatial entities or phenomena, some people apply them draw abstract resources, resulting in development cartography lagging. Additionally, process data visualization involves conversion into visual such as charts graphs, with aim effectively conveying data’s importance. realize expression cyberspace, which basis understanding cyberspace. Therefore, this paper introduces deep neural (DNN) study complex-heterogeneous visualization. At first, locally linear embedding adopted reduce dimensionality. Then, DNN used train coordinates obtained after dimensionality reduction. Finally, several modeling methods studied concerning temporal attributes achieve effectively. simulation powered datasets sourced from accessible via data.world. results demonstrate suggested approach superior efficiency when compared baseline methods.