In this paper we propose a new scaling method to study the Schur complements of SDD1 matrices. Its core is related to the non-negative property of the inverse M-matrix, while numerically improving the Quotient formula...
详细信息
Graph neural network(GNN) is a promising method to analyze graphs. Most existing GNNs adopt the class-balanced assumption, which cannot deal with class-imbalanced graphs well. The oversampling technique is effective i...
详细信息
Graph neural network(GNN) is a promising method to analyze graphs. Most existing GNNs adopt the class-balanced assumption, which cannot deal with class-imbalanced graphs well. The oversampling technique is effective in alleviating class-imbalanced problems. However, most graph oversampling methods generate synthetic minority nodes and their edges after applying GNNs. They ignore the problem that the representations of the original and synthetic minority nodes are dominated by majority nodes caused by aggregating neighbor information through GNN before oversampling. In this paper, we propose a novel graph oversampling framework, termed distribution alignment-based oversampling for node classification in classimbalanced graphs(named Graph-DAO). Our framework generates synthetic minority nodes before GNN to avoid the dominance of majority nodes caused by message passing in GNNs. Additionally, we introduce a distribution alignment method based on the sum-product network to learn more information about minority nodes. To our best knowledge, it is the first to use the sum-product network to solve the class-imbalanced problem in node classification. A large number of experiments on four real datasets show that our method achieves the optimal results on the node classification task for class-imbalanced graphs.
Human pose estimation has given rise to a broad spectrum of novel and compelling applications, including action recognition, sports analysis, as well as surveillance. However, accurate video pose estimation remains an...
Dimeric fused-ring electron acceptors(DFREAs)have attracted much attention due to the combined advantages of their monomeric and polymeric acceptors,including a well-defined molecular structure,excellent repeatability...
详细信息
Dimeric fused-ring electron acceptors(DFREAs)have attracted much attention due to the combined advantages of their monomeric and polymeric acceptors,including a well-defined molecular structure,excellent repeatability,and stable ***,the additionally introduced single-bonds during dimerization may result in a twisted backbone of DFREAs,which is detrimental to intermolecular packing and charge ***,three DFREAs are designed and synthesized,in which DFREA conformations were systematically tuned via adjusting the intensities of intramolecular noncovalent interactions(INIs)to achieve high-performance organic solar cells(OSCs).Theoretical and experimental results show that the gradual introduction of S…F INIs can continuously improve molecular planarity and rigidity,resulting in reduced reorganization energies,ordered packing mode,and enhanced crystallization of *** from the incorporation of fourfold S…F INIs,DYF-TF-based binary OSCs show a record high efficiency of 18.26%with an extremely low energy loss(0.493 eV)for DFREAbased *** addition,DYF-TF-based OSCs exhibited good long-term stability with a T_(80%)lifetime of 2681 h,and the power conversion efficiency of the DYF-TF-based ternary device is further enhanced to 18.73%.This contribution demonstrates the great potential of the INIs strategy in achieving excellent DFREAs materials.
A main result of this paper establishes the global stability of the 3D MHD equations with mixed partial dissipation near a background magnetic field in the domain Ω = T2 × R with T2 = [0, 1]2. More precisely, eac...
详细信息
This paper focuses on the optimization and improvement of the line-of-sight tracking algorithm based on monocular vision, and aims to achieve a series of complex functions through image analysis based on line-of-sight...
详细信息
Visual perception plays an important role in autonomous driving technology. The two key factors in visual perception tasks are monocular object detection and structured data analysis. In this paper, a structured data ...
详细信息
Cold atoms provide a flexible platform for synthesizing and characterizing topological matter,where geometric phases play a central ***,cold atoms are intrinsically prone to thermal noise,which can overwhelm the topol...
详细信息
Cold atoms provide a flexible platform for synthesizing and characterizing topological matter,where geometric phases play a central ***,cold atoms are intrinsically prone to thermal noise,which can overwhelm the topological response and hamper promised *** the other hand,geometric phases also determine the energy spectra of particles subjected to a static force,based on the polarization relation between Wannier-Stark ladders and geometric Zak *** exploiting this relation,we develop a method to extract geometric phases from energy spectra of room-temperature superradiance lattices,which are momentum-space lattices of timed Dicke *** such momentum-space lattices the thermal motion of atoms,instead of being a source of noise,provides effective forces which lead to spectroscopic signatures of the Zak *** measure Zak phases directly from the anti-crossings between Wannier-Stark ladders in the Doppler-broadened absorption spectra of superradiance *** approach paves the way of measuring topological invariants and developing their applications in room-temperature atoms.
Underwater optical imaging produces images with high resolution and abundant information and hence has outstanding advantages in short-distance underwater target ***,low-light and high-noise scenarios pose great chall...
详细信息
Underwater optical imaging produces images with high resolution and abundant information and hence has outstanding advantages in short-distance underwater target ***,low-light and high-noise scenarios pose great challenges in un-derwater image and video *** improve the accuracy and anti-noise performance of underwater target image edge detection,an underwater target edge detection method based on ant colony optimization and reinforcement learning is proposed in this ***,the reinforcement learning concept is integrated into artificial ants’movements,and a variable radius sensing strategy is pro-posed to calculate the transition probability of each *** methods aim to avoid undetection and misdetection of some pixels in image ***,a double-population ant colony strategy is proposed,where the search process takes into account global search and local search *** results show that the algorithm can effectively extract the contour information of underwater targets and keep the image texture well and also has ideal anti-interference performance.
In order to analyse the global exponential stability (GES) of inertial neural networks (INNs) with multiple time-varying transmission delays, a direct parameterized method in this article is proposed. First, the solut...
详细信息
暂无评论