Capacity Analysis for Dynamic Space Networks

To evaluate transmission rate of highly dynamic space networks,a new method for studying space network capacity is proposed in this paper. Using graph theory,network capacity is defined as the maximum amount of flows ground stations can receive per unit time. Combined with a hybrid constellation model,network capacity is calculated and further analyzed for practical cases. Simulation results show that network capacity will increase to different extents as link capacity,minimum ground elevation constraint and satellite onboard processing capability change. Considering the efficiency and reliability of communication networks,how to scientifically design satellite networks is also discussed.

Non-negative matrix factorization based modeling and training algorithm for multi-label learning

Multi-label learning is more complicated than single-label learning since the semantics of the instances are usually overlapped and not identical.The effectiveness of many algorithms often fails when the correlations in the feature and label space are not fully exploited.To this end,we propose a novel non-negative matrix factorization(NMF)based modeling and training algorithm that learns from both the adjacencies of the instances and the labels of the training set.In the modeling process,a set of generators are constructed,and the associations among generators,instances,and labels are set up,with which the label prediction is conducted.In the training process,the parameters involved in the process of modeling are determined.Specifically,an NMF based algorithm is proposed to determine the associations between generators and instances,and a non-negative least square optimization algorithm is applied to determine the associations between generators and labels.The proposed algorithm fully takes the advantage of smoothness assumption,so that the labels are properly propagated.The experiments were carried out on six set of benchmarks.The results demonstrate the effectiveness of the proposed algorithms.

Unpaired image to image transformation via informative coupled generative adversarial networks

We consider image transformation problems,and the objective is to translate images from a source domain to a target one.The problem is challenging since it is difficult to preserve the key properties of the source images,and to make the details of target being as distinguishable as possible.To solve this problem,we propose an informative coupled generative adversarial networks(ICoGAN).For each domain,an adversarial generator-and-discriminator network is constructed.Basically,we make an approximately-shared latent space assumption by a mutual information mechanism,which enables the algorithm to learn representations of both domains in unsupervised setting,and to transform the key properties of images from source to target.Moreover,to further enhance the performance,a weightsharing constraint between two subnetworks,and different level perceptual losses extracted from the intermediate layers of the networks are combined.With quantitative and visual results presented on the tasks of edge to photo transformation,face attribute transfer,and image inpainting,we demonstrate the ICo-GAN’s effectiveness,as compared with other state-of-the-art algorithms.