检索结果-内蒙古大学图书馆

4th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2021

作者： Zhang, Yikai Zhu, Qi Peng, Yong Kong, Wanzeng School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China Provincial Key Lab. for Computer Information Processing Technology Soochow University Suzhou215123 China

ISBN: (纸本)9781665413220

Random Vector Functional Link (RVFL) is a single hidden layer feed forward network which can be trained with non-iterative learning methods. Concretely, the input weights and hidden biases in RVFL can be randomly generated and then the calculation of the output weights can be reduced to solve a regularized least squares regression formula. Though RVFL network obtained promising performance in diverse applications, most of its current variants work mainly for supervised tasks such as classification and regression while less effort was made to utilize the unlab.led data. In this paper, we propose an unsupervised RVFL model by simultaneously considering the local manifold structure and the global discriminative information of data. The newly formulated unsupervised discriminative RVFL (UDRVFL) model can be efficiently solved by handling an eigen-value decomposition operation. We conduct experiments by comparing UDRVFL with several state-of-the-arts on representative benchmark data sets and the results demonstrate that it has very competitive performance in data clustering. © 2021 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Assessment of rotamer library for protein structure prediction

Assessment of rotamer library for protein structure predicti...

引用

2nd International Conference on information Science and Engineering, ICISE2010

作者： Huang, Xu Lü, Qiang Miao, Dajun Qian, Peide School of Computer Science and Technology Soochow University Suzhou 215006 China Jiangsu Provincial Key Lab for Information Processing Technologies Suzhou 215006 China

ISBN: (纸本)9781424480968

Side chain packing is a crucial step for protein structure prediction. And the quality of rotamer library has important implications in side chain packing. This paper assess dunbrack rotamer libraries and simple sampling rotamer libraries for certain structures by comparing the native structure and solutions come from rotamer libraries. Results of eleven hard targets in CASP9 show that the best solution is near to the native structure. Otherwise, there is no native structure in protein structure *** compare the best solutions which choosing by lower RMSD and energy, it shows that the best solution which choosing by lower energy is near to the best solution which choosing by low RMSD. So, in the case of unknown native structure, the energy guided choosing is necessary, but it must adopt some other method such as clustering to select the best solution. © 2010 IEEE.

关键词： Chains

来源：评论

学校读者我要写书评

暂无评论

Learning Dual-Domain Calibration and Distance-Driven Correlation Filter:A Probabilistic Perspective for UAV Tracking

引用

computers, Materials & Continua 2023年第12期77卷 3741-3764页

作者： Taiyu Yan Yuxin Cao Guoxia Xu Xiaoran Zhao Hu Zhu Lizhen Deng Jiangsu Province Key Lab on Image Processing and Image Communication Nanjing University of Posts and TelecommunicationsNanjingChina School of Computer Science Qufu Normal UniversityQufuChina National Engineering Research Center of Communication and Network Technology Nanjing University of Posts and TelecommunicationsNanjingChina

Unmanned Aerial Vehicle(UAV)tracking has been possible because of the growth of intelligent information technology in smart cities,making it simple to gather data at any time by dynamically monitoring events,people,the environment,and other aspects in the *** traditional filter creates a model to address the boundary effect and time filter degradation issues in UAV tracking *** these methods ignore the loss of data integrity terms since they are overly dependent on numerous explicit previous regularization *** light of the aforementioned issues,this work suggests a dual-domain Jensen-Shannon divergence correlation filter(DJSCF)model address the probability-based distance measuring issue in the event of filter *** two-domain weighting matrix and JS divergence constraint are combined to lessen the impact of sample imbalance and *** new tracking models that are based on the perspectives of the actual probability filter distribution and observation probability filter distribution are proposed to translate the statistical distance in the online tracking model into response *** model is roughly transformed into a linear equality constraint issue in the iterative solution,which is then solved by the alternate direction multiplier method(ADMM).The usefulness and superiority of the suggested strategy have been shown by a vast number of experimental findings.

关键词： Dual-domain weighting distance measure correlation filter ADMM

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Image Features and Similarity Measurement Methods in Cross-modal Retrieval of Commodity Images

A Comparative Study of Image Features and Similarity Measure...

引用

2020 IEEE International Conference on Advances in Electrical Engineering and computer Applications, AEECA 2020

作者： Qiao, Baoxing Fan, Zhipeng Wang, Ran Zhao, Zhijie Zhang, Hongjie Harbin Univ. of Comm. Key Lab. of Electron. Comm. and Info. Processing of Heilongjiang Province School of Computer and Information Engineering Harbin China Graduate School of Harbin University of Commerce Key Laboratory of Electronic Commerce and Information Processing of Heilongjiang Province Harbin China

ISBN: (纸本)9781728165202

With the rapid development of information technology and the widespread popularity of mobile devices and e-commerce trading platforms, the number and scale of commodity images and corresponding description text and other multimedia data are growing rapidly, and the demand for cross-modal retrieval of commodity images is also increasing. Cross-mode hash method has been widely studied and applied. Based on the matrix three-factor decomposition hash cross mode retrieval method, the problem of mapping hash code with different modes is solved. In the cross-modal retrieval process, in order to study and analyze different similarity measurement methods, when searching for product image cross-modalities, in order to analyze the retrieval results of different similarity measurement methods, the potential characteristics of different images are The effect of the image is analyzed and the performance of cross-mode retrieval under the matrix three-factor decomposition hash framework is compared. The research results show the results of cross-modal retrieval of commodity images with different similarity measurement methods and different image underlying features. © 2020 IEEE.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

3D Representation of Chinese Event Factuality

3D Representation of Chinese Event Factuality

引用

第十五届汉语词汇语义学国际研讨会

作者： CAO Yuan ZHU Qiaoming LI Peifeng School of Computer Science and Technology of Soochow University Key Lab of Computer Information Processing Technology of Jiangsu Province

In general,Chinese event factuality is determined by the specific vocabularies and syntactic structures of *** Chinese event factuality corpus is to annotate these specific vocabularies and syntactic *** these information is raw and complex,it will result in high computation complexity and low correct rate if we use these information to compute factuality *** paper proposes a 3D representation of Chinese event factuality based on the annotated factual information in a Chinese event factuality *** also presents the transformation rules between the factual information and 3D representation and those between the 3D representation and event *** experimental results demonstrate the effectiveness of our 3D representation.

关键词： Representation of Chinese Event Factuality

来源：评论

学校读者我要写书评

暂无评论

Tumor gene expressive data classification based on locally linear representation Fisher criterion

Tumor gene expressive data classification based on locally l...

引用

9th International Conference on Intelligent Computing, ICIC 2013

作者： Li, Bo Tian, Bei-Bei Liu, Jin School of Computer Science and Technology Wuhan University of Science and Technology 430081 Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China State Key Lab. of Software Engineering Wuhan China

ISBN: (纸本)9783642394812

In this paper, a discriminant manifold learning method based on Locally Linear Embedding (LLE), which is named Locally Linear Representation Fisher Criterion (LLRFC), is proposed for the classification of tumor gene expressive data. In the proposed LLRFC, an inter-class graph and intra-class graph is constructed based on the class information of tumor gene expressive data, where the weights between nodes in both graph are optimized using locally linear representation trick. Moreover, a Fisher criterion is modeled to maximize the inter-class scatter and minimize the intra-class scatter simultaneously. Experiments on some benchmark tumor gene expressive data validate its efficiency. © 2013 Springer-Verlag.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Remote Authentication Scheme for Multi-Server Environment Based on Biometrics with Access Control 9

Remote Authentication Scheme for Multi-Server Environment Ba...

引用

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

作者： Min Zhang Wen-rong Tan School of Foreign Languages Southwest Minzu University Sichuan Province Key Lab of Signal and Information Processing Southwest Jiao Tong University School of Computer Science and Technology Southwest Minzu University

ISBN: (纸本)9781509038237;9781509038220

Compared with single-server authentication scheme, the authentication scheme for multi-server environment has a lot of advantages. Such as users needn’t to remember various passwords or register for every application server. In 2016, Irshad et al. proposed a three-factor scheme based on chaotic map for multi-server environment. Irshad’s scheme has high efficiency and strong robustness. However, after careful analysis, this paper shows that Irshad’s scheme still has many disadvantages. In order to solve these problems, a new three-factor authentication scheme based on secure sketch and Chebyshev chaotic map has been proposed in this paper. From the analysis, we can see that the proposed scheme has higher security level and deals with biometric more appropriately in spite of slight higher computation cost than Irshad’s scheme. What’s more, an access control method has been introduced for the purpose of making different users enjoy different access privileges with regard to the data. At the same time, the proposed scheme can achieve key agreement.

关键词： multi-server authentication secure sketch access control biometrics

来源：评论

学校读者我要写书评

暂无评论

MMLUP: Multi-Source & Multi-Task Learning for User Profiles in Social Network

引用

computers, Materials & Continua 2019年第9期61卷 1105-1115页

作者： Dongjie Zhu Yuhua Wang Chuiju You Jinming Qiu Ning Cao Chenjing Gong Guohua Yang Helen Min Zhou School of Computer Science and Technology Harbin Institute of TechnologyWeihai264209China College of Information Engineering Sanming University365004SanmingChina Fujian Province University Key Lab for Industry Big Data Analysis and Application FujianChina College of Information Engineering Qingdao Binhai UniversityQingdaoChina Jiangsu Province Wireless Sensing System Application Engneering Technology Research and Development Centre China School of Engineering Manukau Institute of TechnologyAuckland2241New Zealand

With the rapid development of the mobile Internet,users generate massive data in different forms in social network every day,and different characteristics of users are reflected by these social media *** to integrate multiple heterogeneous information and establish user profiles from multiple perspectives plays an important role in providing personalized services,marketing,and recommendation *** this paper,we propose Multi-source&Multi-task Learning for User Profiles in Social Network which integrates multiple social data sources and contains a multi-task learning framework to simultaneously predict various attributes of a ***,we design their own feature extraction models for multiple heterogeneous data ***,we design a shared layer to fuse multiple heterogeneous data sources as general shared representation for multi-task ***,we design each task’s own unique presentation layer for discriminant output of ***,we design a weighted loss function to improve the learning efficiency and prediction accuracy of each *** experimental results on more than 5000 Sina Weibo users demonstrate that our approach outperforms state-of-the-art baselines for inferring gender,age and region of social media users.

关键词： User profiles multi-source multi-task learning social network

来源：评论

学校读者我要写书评

暂无评论

An efficient coverage control algorithm for three-dimensional underwater sensor networks

引用

Advances in information Sciences and Service Sciences 2012年第10期4卷 393-399页

作者： Xiao, Fu Yang, Yang Sun, Li Wang, Ruchuan Nanjing University of Posts and Telecommunications Nanjing 210003 China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou 215006 China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing 210003 China Key Lab of Broadband Wireless Communication and Sensor Network Technology Ministry of Education Nanjing 210003 China

Strategy of sensor nodes deployment is directly related to the cost and performance for underwater wireless sensor networks, which is largely determined the various service-quality improvement of wireless sensor networks. In order to improve the coverage of the target area, this paper presents a distributed algorithm of coverage control. Assume that nodes initially deployed on the surface of the water and can only move in vertical direction in 3-D space, the algorithm is first to control the nodes in-depth and relocate the nodes at different depths, then the nodes continue to adjust their depths until there is no augment for improving their coverage, and to achieve efficient coverage of the three-dimensional sensor networks ultimately. Experimental results show that compared with traditional random deployment method, the proposed coverage control algorithm can improve coverage of network effectively.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Neural conjuncted polynomial's structure adaptive equalizer

Neural conjuncted polynomial's structure adaptive equalizer

引用

ICCCAS 2007 - International Conference on Communications, Circuits and Systems 2007

作者： Haiquan, Zhao Jiashu, Zhang Si-Chuan Province Key Lab. of Signal and Information Processing Southwest Jiaotong University Chengdu 610031 China Dept. of Electronic Eng. Chengdu University of Information Technology Chengdu 610225 China

ISBN: (纸本)9781424414741

Based on the analysis of linear conjuncted polynomial filter and the characteristic of single layer neural network with mild nonlinear and severe nonlinear distortions, novel conjunction's structure equalizer is proposed in this paper, and adaptive algorithm is deduced by the normalized least mean squares (NLMS). computer simulations show that not only the novel type structure equalizer is simpler in structure and but also can availab.y remove nonlinear distortions and intersymbol interference (ISI), improve performance of bit error rates (BER) no matter what linear channel or nonlinear channel in digital communication systems.

关键词： Polynomials

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：