Secure Logistic Regression for Vertical Federated Learning

Data island effectively blocks the practical application of machine learning. To meet this challenge, a new framework known as federated learning was created. It allows model training on a large amount of scattered data owned by different data providers. This article presents a parallel solution for computing logistic regression based on...

Free multi-floor indoor space extraction from complex 3D building models

Intelligent navigation and facility management in complex indoor environments are issues at the forefront of geospatial information science. Indoor spaces with fine geometric and semantic descriptions provide a solid foundation for various indoor applications, but it is difficult to comprehensively extract free multi-floor indoor spaces from...

Multi-level Indoor Path Planning Method

Indoor navigation is increasingly widespread in complex indoor environments, and indoor path planning is the most important part of indoor navigation. Path planning generally refers to finding the most suitable path connecting two locations, while avoiding collision with obstacles. However, it is a fundamental problem, especially for 3D complex...

Dynamic plasmonic beam shaping by vector beams with arbitrary locally linear polarization states

Vector beams, which have space-variant state of polarization (SOP) comparing with scalar beams with spatially homogeneous SOP, are used to manipulate surface plasmon polarizations (SPPs). We find that the excitation, orientation, and distribution of the focused SPPs excited in a high numerical aperture microscopic configuration highly depend on...