检索结果-内蒙古大学图书馆

Unsupervised Nonlinear Adaptive Manifold Learning for Global and Local information

Tsinghua Science and technology 2021年第2期26卷 163-171页

作者： Jiajun Gao Fanzhang Li Bangjun Wang Helan Liang School of Computer Science and Technology Soochow UniversitySuzhou 215006China Joint International Research Laboratory of Machine Learning and Neuromorphic Computing Provincial Key Laboratory for Computer Information Processing TechnologySoochow UniversitySuzhou 215006China

In this paper,we propose an Unsupervised Nonlinear Adaptive Manifold Learning method(UNAML)that considers both global and local *** this approach,we apply unlabeled training samples to study nonlinear manifold features,while considering global pairwise distances and maintaining local topology *** method aims at minimizing global pairwise data distance errors as well as local structural *** order to enable our UNAML to be more efficient and to extract manifold features from the external source of new data,we add a feature approximate error that can be used to learn a linear ***,we add a feature approximate error that can be used to learn a linear *** addition,we use a method of adaptive neighbor selection to calculate local structural *** paper uses the kernel matrix method to optimize the original *** algorithm proves to be more effective when compared with the experimental results of other feature extraction methods on real face-data sets and object data sets.

关键词： unsupervised manifold learning global and local information,adaptive neighbor selection method kernel matrix

来源：评论

学校读者我要写书评

暂无评论

Gray cerebrovascular image skeleton extraction algorithm using level set model

引用

Journal of Multimedia 2010年第3期5卷 208-215页

作者： Wu, Jian Zhang, Guang-ming Xia, Jie Cui, Zhi-ming Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou 215006 China The Institute of Intelligent Information Processing and Application Soochow University Suzhou 215006 China

The ambiguity and complexity of medical cerebrovascular image makes the skeleton gained by conventional skeleton algorithm discontinuous, which is sensitive at the weak edges, with poor robustness and too many burrs. This paper proposes a cerebrovascular image skeleton extraction algorithm based on Level Set model, using Euclidean distance field and improved gradient vector flow to obtain two different energy functions. The first energy function controls the obtain of topological nodes for the beginning of skeleton curve. The second energy function controls the extraction of skeleton surface. This algorithm avoids the locating and classifying of the skeleton connection points which guide the skeleton extraction. Because all its parameters are gotten by the analysis and reasoning, no artificial interference is needed. © 2010 ACADEMY PUBLISHER.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

A new quadtree-based terrain LOD algorithm

Journal of Software

引用

Journal of Software 2010年第7期5卷 769-776页

作者： Wu, Jian Yang, Yuan-feng Gong, Sheng-rong Cui, Zhi-ming Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou 215006 China The Institute of Intelligent Information Processing and Application Soochow University Suzhou 215006 China

Terrain LOD algorithm is a dynamic and local dough sheet subduction algorithm. On the basis of the research on traditional quadtree algorithm, this paper proposed a new terrain LOD algorithm using quadtree. On deviation computing standard, besides static deviation and view distance, motion vector and observation vector are introduced, which made the result of deviation computing close to the accurate deviation value. On crack elimination, a new crack elimination algorithm is proposed, which increases the list of crack polygon specially and eliminates all the cracks by one time rendering. So, the judge of crack vertex is not required in the course of terrain block segmentation and rendering. The experimental result shows that our algorithm is practical and effective, which can meet the need of real-time rendering for massive terrain data. © 2010 ACADEMY PUBLISHER.

关键词： Cracks

来源：评论

学校读者我要写书评

暂无评论

Rethinking Masked Autoencoder for Salient Object Detection in Optical Remote Sensing Images from a Pseudo Image Pretraining Perspective

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年

作者： Fu, Yuxiang Fang, Wei Sheng, Victor S. Nanjing University of Information Science and Technology School of Computer Science Nanjing210044 China Soochow University Provincial Key Laboratory for Computer Information Processing Technology Suzhou215031 China Texas Tech University Department of Computer Science LubbockTX79409 United States

Recently masked autoencoder (MAE) has achieved great success in visual representation learning and delivered promising potential in many downstream vision tasks. However, due to the lack of saliency supervision signal in original MAE, almost no saliency information can be learned from masked image reconstruction process. Therefore, salient object detection (SOD) can hardly benefit from MAE pretraining. To address this issue, we integrate SOD model and saliency supervision in MAE and propose a simple and effective framework DHMMAE utilizing MAE with dynamic hybrid masking ratios to pretrain SOD model. Specifically, we treat MAE as an online data augmenter to generate endless pseudo images for SOD model to predict saliency maps, where saliency supervision is employed to ensure the model can learn robust saliency prior knowledge from the reconstructed images. Besides, we propose a simple and novel network EANet driven by DHMMAE pretraining for SOD in optical remote sensing images (ORSIs). Two key modules are designed for EANet to further enhance the performance: enhanced diverse feature aggregation module (EDFAM) and adjacent-context shuffle spatial attention module (ASSAM). EDFAM aggregates diverse features via three different types of convolution layer and enhances them by convolution block attention module. ASSAM captures spatial location information of salient objects by employing channel shuffle operation and weighted spatial attention mechanism on the fused adjacent context. Experiments on three ORSI-SOD datasets demonstrate that our proposed method outperforms the cutting-edge methods. © 1980-2012 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Moving object classification method based on SOM and K-means

引用

Journal of computers 2011年第8期6卷 1654-1661页

作者： Wu, Jian Xia, Jie Chen, Jian-ming Cui, Zhi-ming The Institute of Intelligent Information Processing and Application Soochow University Suzhou 215006 China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou 215006 China

We do research on moving object classification in traffic video. Our aim is to classify the moving objects into pedestrians, bicycles and vehicles. Due to the advantage of self-organizing feature map (SOM), an unsupervised learning algorithm, which is simple and self organization, and the common usage of K-means clustering method, this paper combines SOM with K-means to do classification of moving objects in traffic video, constructs a system including four parts, and proposes a method based on bidirectional comparison of centroid to do tracking, and an improved method to obtain initial background when using background subtraction method to detect motion of moving objects. Experimental results show the effectiveness and robustness of the proposed approach. © 2011 ACADEMY PUBLISHER.

关键词： Self organizing maps

来源：评论

学校读者我要写书评

暂无评论

Wireless Service Prediction Algorithm in Mobile Social Environment 2

Wireless Service Prediction Algorithm in Mobile Social Envir...

引用

2017 IEEE 2nd International Conference on Big Data Analysis（ICBDA 2017）

作者： Hui Zhang Min Wang Jiangsu Key Lab of Wireless Communications Nanjing University of Posts and Telecommunications Provincial Key Laboratory for Computer Information Processing Technology Soochow University

ISBN: (纸本)9781509036202

First,according to characteristics of mobile social environment,by using optimization models based on similarity degree and interaction degree respectively,the optimal correlated users can be selected for analyzing two main factors of a target user's behaviors(***-term habits and shortterm influences);furthermore,an adaptive update strategy based on fuzzy theory is proposed to describe the importance of two factors in real time and quantitative ***,an improved Apriori theory is introduced to predict user service behaviors accurately;particularly,a new update mechanism for Apriori sample database is built to effectively integrate the samples of optimal correlated ***,simulation results verify the effectiveness of proposed algorithm.

关键词： mobile social environment user behavior prediction fuzzy theory adaptive update strategy improved Apriori theory

来源：评论

学校读者我要写书评

暂无评论

Relative influence maximization in competitive social networks

引用

Science China(information Sciences) 2017年第10期60卷 252-254页

作者： Dingda YANG Xiangwen LIAO Huawei SHEN Xueqi CHENG Guolong CHEN College of Physics and Information Engineering Fuzhou University Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing College of Mathematics and Computer Science Fuzhou University Institute of Computing Technology Chinese Academy of Sciences

In many realistic scenarios,such as political election and viral marketing,two opposite opinions,i.e.,positive opinion and negative opinion,spread simultaneously in the same social networks[1,2].Consequently,to achiev... 详细信息

关键词： net RIM Relative influence maximization in competitive social networks Figure

来源：评论

学校读者我要写书评

暂无评论

Neural Network-Assisted Hybrid Model Based Message Passing for Parametric Holographic MIMO Near Field Channel Estimation

引用

IEEE Transactions on Wireless Communications 2025年

作者： Yuan, Zhengdao Guo, Yabo Gao, Dawei Guo, Qinghua Wang, Zhongyong Huang, Chongwen Jin, Ming Wong, Kai-Kit Henan Open University Artificial Intelligence Technology Engineering Research Center Zhengzhou450002 China University of Wollongong School of Electrical Computer and Telecommunications Engineering WollongongNSW2522 Australia Zhengzhou University School of Information Engineering Zhengzhou450002 China Xidian University Hangzhou Institute of Technology Hangzhou311200 China University of Wollongong School of Electrical Computer and Telecommunications Engineering NSW2522 Australia Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China Zhejiang Provincial Key Laboratory of Multi-Modal Communication Networks and Intelligent Information Processing Hangzhou310027 China Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo315211 China University College London Department of Electronic and Electrical Engineering Torrington Place WC1E 7JE United Kingdom Yonsei University Yonsei Frontier Lab Seoul Korea Republic of

Holographic multiple-input and multiple-output (HMIMO) is a promising technology with the potential to achieve high energy and spectral efficiencies, enhance system capacity and diversity, etc. In this work, we address the challenge of HMIMO near field (NF) channel estimation, which is complicated by the intricate model introduced by the dyadic Green's function. Despite its complexity, the channel model is governed by a limited set of parameters. This makes parametric channel estimation highly attractive, offering substantial performance enhancements and enabling the extraction of valuable sensing parameters, such as user locations, which are particularly beneficial in mobile networks. However, the relationship between these parameters and channel gains is nonlinear and compounded by integration, making the estimation a formidable task. To tackle this problem, we propose a novel neural network (NN) assisted hybrid method. With the assistance of NNs, we first develop a novel hybrid channel model with a significantly simplified expression compared to the original one, thereby enabling parametric channel estimation. Using the readily available training data derived from the original channel model, the NNs in the hybrid channel model can be effectively trained offline. Then, building upon this hybrid channel model, we formulate the parametric channel estimation problem with a probabilistic framework and design a factor graph representation for Bayesian estimation. Leveraging the factor graph representation and unitary approximate message passing (UAMP), we develop an effective message passing-based Bayesian channel estimation algorithm. Extensive simulations demonstrate the superior performance of the proposed method. © 2025 IEEE.

关键词： Green's function

来源：评论

学校读者我要写书评

暂无评论

IDSGA: A high-performance search model for differential-neural cryptanalysis

引用

Digital Signal processing 2025年 164卷

作者： Zhiwen Hu Lang Li Siqi Zhu Yemao Hu College of Computer Science and Technology Hengyang Normal University Hengyang 421002 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang Normal University Hengyang 421002 China

Differential-neural cryptanalysis poses critical security threats to internet of things-embedded lightweight block ciphers, outperforming traditional methods but requiring efficient input difference identification. Current solutions are constrained by the opacity of neural networks and the prohibitive computational demands during search processes. Therefore, an input difference search model IDSGA is proposed in this paper. IDSGA model innovatively combines cryptographic theory with deep learning through two key processes. First, feature purification enhances differential characteristics by eliminating redundant patterns while preserving attack-relevant statistical properties through traditional differential probability integration. Second, multi-dimensional distribution mapping enables quantitative dataset evaluation by transforming purified data into interpretable statistical metrics. It enables our model to break through the reliance on neural network evaluation. Moreover, IDSGA model constructs a more optimal search path by integrating a genetic algorithm to deal with the problem of differential search of full inputs with high computational complexity. A quantum variant theoretically extends these capabilities. The experimental results show that the execution time of the IDSGA model is 93% less than that of Gohr. For the CARX cipher, the input differences found by IDSGA are more optimal. This work establishes a new paradigm for differential-neural cryptanalysis by decoupling dataset evaluation from neural network training dependencies.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Toward the Completely Independent Spanning Trees Problem on BCube 9

Toward the Completely Independent Spanning Trees Problem on ...

引用

2017 9th IEEE International Conference on Communication Software and Networks (ICCSN 2017)

作者： Ting Pan Baolei Cheng Jianxi Fan Cheng-Kuan Lin Dongfang Zhou School of Computer Science and Technology Soochow University Provincial Key Laboratory for Computer Information Processing Technology Soochow University

ISBN: (纸本)9781509038237;9781509038220

Completely independent spanning trees（CISTs） are important construct which can be used in data center networks for multi-node broadcasting, one-to-all broadcasting, reliable broadcasting, and secure message distribution, etc. As a recently proposed server-centric data center network, BCube has many good properties. By focusing on the connections between servers, we define the logic graph of BCube as LBCube. We study the construction of CISTs with small diameter on BCubek and show that there are n/2 [（n-1）/2 if n is odd] CISTs with the diameter 2 k + 3 on L-BCubek by presenting a recursive algorithm.

关键词： BCube completely independent spanning trees diameter data center network vertex-disjoint

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：