检索结果-南通市图书馆

Aspect-level sentiment analysis based on semantic heterogeneous graph convolutional network

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2023年第6期17卷 87-99页

作者： Yufei ZENG Zhixin LI Zhenbin CHEN Huifang MA guangxi key lab of multi-source information mining and security Guangxi Normal UniversityGuilin 541004China College of Computer Science and Engineering Northwest Normal UniversityLanzhou 730070China

The deep learning methods based on syntactic dependency tree have achieved great success on Aspect-based Sentiment Analysis(ABSA).However,the accuracy of the dependency parser cannot be determined,which may keep aspect words away from its related opinion words in a dependency ***,few models incorporate external affective knowledge for *** on this,we propose a novel architecture to tackle the above two limitations,while fills up the gap in applying heterogeneous graphs convolution network to ***,we employ affective knowledge as an sentiment node to augment the representation of ***,linking sentiment node which have different attributes with word node through a specific edge to form a heterogeneous graph based on dependency ***,we design a multi-level semantic heterogeneous graph convolution network(Semantic-HGCN)to encode the heterogeneous graph for sentiment *** experiments are conducted on the datasets SemEval 2014 Task 4,SemEval 2015 task 12,SemEval 2016 task 5 and ACL 14 *** experimental results show that our method achieves the state-of-the-art performance.

关键词： heterogeneous graph convolution network multi-head attention network aspect-based sentiment analysis deep learning affective knowledge

Efficient multi-scale community search method based on spectral graph wavelet

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2023年第5期17卷 89-101页

作者： Cairui YAN Huifang MA Qingqing LI Fanyi YANG Zhixin LI College of Computer Science and Engineering Northwest Normal UniversityLanzhou 730070China guangxi key lab of multi-source information mining and security Guangxi Normal UniversityGuilin 541004China

Community search is an important problem in network analysis,which has attracted much attention in recent *** a query-oriented variant of community detection problem,community search starts with some given nodes,pays more attention to local network structures,and gets personalized resultant communities *** existing community search method typically returns a single target community containing query nodes by *** is a strict requirement and does not allow much *** many realworld applications,however,query nodes are expected to be located in multiple communities with different *** address this limitation of existing methods,an efficient spectral-based multi-Scale Community Search method(MSCS)is proposed,which can simultaneously identify the multi-scale target local communities to which query node *** MSCS,each node is equipped with a graph Fourier multiplier *** access of the graph Fourier multiplier operator helps nodes to obtain feature representations at various community *** addition,an efficient algorithm is proposed for avoiding the large number of matrix operations due to spectral *** experimental evaluations on a variety of real-world datasets demonstrate the effectiveness and efficiency of the proposed method.

关键词： community search multi-scale spectral wavelets

Synchronously scrambled diffuse image encryption method based on a new cosine chaotic map

在线全文

学校读者我要写书评

暂无评论

Chinese Physics B 2022年第8期31卷 296-309页

作者： Xiaopeng Yan Xingyuan Wang Yongjin Xian School of information Science and Technology Dalian Maritime UniversityDalian 116026China guangxi key laboratory of multi-source information mining&security Guangxi Normal UniversityGuilin 541004China

We present a new cosine chaotic mapping proved by chaos theory test and analysis such that the system has good cryptography properties, wide chaos range, simple structure, and good sensitivity to initial value, and the mapping can meet the needs of chaotic image encryption. Based on the cosine chaotic system, we propose a new encryption method. First,according to the cyclic characteristics of the mapping, the cyclic information wave is simulated. Second, the quasi-Doppler effect is used to synchronously scramble and diffuse the image to obfuscate the original pixel. Finally, the XOR diffusion of image pixels is carried out by information wave to further enhance the encryption effect. Simulation experiment and security analysis show that the algorithm has good security, can resist the common attack mode, and has good efficiency.

关键词： chaos mapping cosine mapping cyclic information wave doppler effect image encryption

The Effects of Wettability on Primary Vortex and Secondary Flow in Three-Dimensional Rotating Fluid

在线全文

学校读者我要写书评

暂无评论

Communications in Theoretical Physics 2019年第12期71卷 1480-1484页

作者： Si-Hao Zhou Wen Qiu Yong Ye Bing He Bing-Hai Wen guangxi key lab of multi-source information mining&security Guangxi Normal UniversityGuilin 541004China Department of Computer Science and information Engineering Guangxi Normal UniversityGuilin 541004China

The secondary flow driven by the primary vortex in a cylinder,generating the so called"tea leaf paradox",is fundamental for understanding many natural phenomena,industrial applications and scientific *** this work,the effect of wettability on the primary vortex and secondary flow is investigated by the three-dimensional multiphase lattice Boltzmann method based on a chemical *** find that the surface wettability strongly affects the shape of the primary *** the increase of the contact angle of the cylinder,the sectional plane of the primary vortex gradually changes from a steep valley into a saddle with two raised *** the surface friction is reduced correspondingly,the core of the secondary vortex moves to the centerline of the cylinder and the vortex intensity also *** stirring force has stronger effects to enhance the secondary flow and push the vortex up than the surface ***,a small secondary vortex is discovered near the three-phase contact line when the surface has a moderate wettability,owing to the interaction between the secondary flow and the curved gas/liquid interface.

关键词： secondary flow lattice Boltzmann method multiphase flow rotating fluid

A novel method for extracting skeleton of fruit treefrom 3D point clouds

在线全文

学校读者我要写书评

暂无评论

International Journal of Modeling, Simulation, and Scientific Computing 2020年第6期11卷 78-89页

作者： Shenglian Lu Guo Li Jian Wang College of Computer Science and information Technology guangxi Normal University Guilin 541004P.R.China guangxi key lab of multi-source information mining and security no.15 yucai road Guilin 541004P.R.China Center of information Technology Beijing Municipal Bureau of Agriculture and Rural Affairs No.6 Yumin Middle Rood Beijing 100029P.R.China

Tree skeleton could be useful to agronomy researchers because the skeleton describes the shape and topological structure of a *** phenomenon of organs’mutual occlusion in fruit tree canopy is usually very serious,this should result in a large amount of data missing in directed laser scanning 3D point clouds from a fruit ***,traditional approaches can be ineffective and problematic in extracting the tree skeleton correctly when the tree point clouds contain occlusions and missing *** overcome this limitation,we present a method for accurate and fast extracting the skeleton of fruit tree from laser scanner measured 3D point *** proposed method selects the start point and endpoint of a branch from the point clouds by user’s manual interaction,then a backward searching is used to find a path from the 3D point cloud with a radius parameter as a *** experimental results in several kinds of fruit trees demonstrate that our method can extract the skeleton of a leafy fruit tree with highly accuracy.

关键词： Skeleton extraction fruit tree 3D point cloud modeling plant structure

Community search over heterogeneous information networks via weighting strategy and query replacement

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2022年第4期16卷 231-233页

作者： Fanyi Yang Huifang Ma Weiwei Gao Zhixin Li College of Computer Science and Engineering Northwest Normal UniversityLanzhou730070China guangxi key lab of multi-source information mining and security Guangxi Normal UniversityGuilin541004China

1Introduction and main contributions Recently,community search over Heterogeneous information Networks(HINs)has attracted much attention in graph analysis,which aims to search for local communities containing query *** existing community search studies in HINs have proved effective in converting heterogeneous graphs to homogeneous graphs via pre-defined meta-paths with consistent head and tail node types,two major limitations ***,they fail to properly utilize the intermediate nodes to assign weights on the edges of the induced homogeneous graph.

关键词： utilize weights properly

DRNet:Towards fast,accurate and practical dish recognition

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2021年第12期64卷 2651-2661页

作者： CHENG SiYuan CHU BinFei ZHONG BiNeng ZHANG ZiKai LIU Xin TANG ZhenJun LI XianXian guangxi key lab of multi-source information mining&security Guangxi Normal UniversityGuilin 541004China Department of Computer Science and Technology Huaqiao UniversityXiamen 361021China Seetatech Technology Nanjing 211800China

Existing algorithms of dish recognition mainly focus on accuracy with predefined classes,thus limiting their application *** this paper,we propose a practical two-stage dish recognition framework(DRNet)that yields a tradeoff between speed and accuracy while adapting to the variation in class *** the first stage,we build an arbitrary-oriented dish detector(AODD)to localize dish position,which can effectively alleviate the impact of background noise and pose *** the second stage,we propose a dish reidentifier(DReID)to recognize the registered dishes to handle uncertain *** further improve the accuracy of DRNet,we design an attribute recognition(AR)module to predict the attributes of *** attributes are used as auxiliary information to enhance the discriminative ability of ***,pruning and quantization are processed on our model to be deployed in embedded ***,to facilitate the study of dish recognition,a well-annotated dataset is *** AODD,DReID,AR,and DRNet run at about 14,25,16,and 5 fps on the hardware RKNN 3399 pro,respectively.

关键词： neural network acceleration neural network quantization object detection reidentification dish recognition

Community detection with attributed random walk via seed replacement

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2022年第5期16卷 45-56页

作者： Yang CHANG Huifang MA Liang CHANG Zhixin LI College of Computer Science and Engineering Northwest Normal UniversityLanzhou 730070China guangxi key lab of multi-source information mining and security Guangxi Normal UniversityGuilin 541004China guangxi key laboratory of Trusted Software Guilin University of Electronic TechnologyGuilin 541004China

Community detection methods based on random walks are widely adopted in various network analysis *** could capture structures and attributed information while alleviating the issues of *** random walks on plain networks have been studied before,in real-world networks,nodes are often not pure vertices,but own different characteristics,described by the rich set of data associated with *** node attributes contain plentiful information that often complements the network,and bring opportunities to the random-walk-based ***,node attributes make the node interactions more complicated and are heterogeneous with respect to topological ***,attributed community detection based on random walk is challenging as it requires joint modelling of graph structures and node *** bridge this gap,we propose a Community detection with Attributed random walk via Seed replacement(CAS).Our model is able to conquer the limitation of directly utilize the original network topology and ignore the attribute *** particular,the algorithm consists of four stages to better identify communities.(1)Select initial seed nodes in the network;(2)Capture the better-quality seed replacement path set;(3)Generate the structure-attribute interaction transition matrix and perform the colored random walk;(4)Utilize the parallel conductance to expand the *** on synthetic and real-world networks demonstrate the effectiveness of CAS.

关键词： community detection seeds colored random walk parallel conductance

Incorporating metapath interaction on heterogeneous information network for social recommendation

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2024年第1期18卷 33-48页

作者： Yanbin JIANG Huifang MA Xiaohui ZHANG Zhixin LI Liang CHANG College of Computer Science and Engineering Northwest Normal UniversityLanzhou 730070China guangxi key lab of multi-source information mining and security Guangxi Normal UniversityGuilin 541001China guangxi key laboratory of Trusted Software Guilin University of Electronic TechnologyGuilin 541004China

Heterogeneous information network(HIN)has recently been widely adopted to describe complex graph structure in recommendation systems,proving its effectiveness in modeling complex graph *** existing HIN-based recommendation studies have achieved great success by performing message propagation between connected nodes on the defined metapaths,they have the following major *** works mainly convert heterogeneous graphs into homogeneous graphs via defining metapaths,which are not expressive enough to capture more complicated dependency relationships involved on the ***,the heterogeneous information is more likely to be provided by item attributes while social relations between users are not adequately *** tackle these limitations,we propose a novel social recommendation model MPISR,which models MetaPath Interaction for Social Recommendation on heterogeneous information ***,our model first learns the initial node representation through a pretraining module,and then identifies potential social friends and item relations based on their similarity to construct a unified *** then develop the two-way encoder module with similarity encoder and instance encoder to capture the similarity collaborative signals and relational dependency on different *** experiments on five real datasets demonstrate the effectiveness of our method.

关键词： heterogeneous information network social reco-mmender system metapath interaction attention mechanism