检索结果-内蒙古大学图书馆

International Conference on Multimedia Information networking and Security

作者： Ye, Lihong Hua, Yuan Communication and Computer Network Key Lab. of Guangdong South China University of Technology Guangzhou China

ISBN: (纸本)9780769542584

Similarity-Search based index structure is an important topic in many application areas, such as content-based multimedia information retrieval, data mining, cluster analysis, etc. In order to improve query performance in highdimensional vector spaces, lots of index structures have been proposed. However, many well-known index structures encounter "dimensional curse" while the dimension of feature vector increase. In order to solve such problem, researchers analyzed the nearest-neighbor search problem in highdimensional vector spaces deeply and proposed some approximation-based index structures. The VA-File which is the first implement approximation-based index structures has done well in solving "dimensional curse" problem. However, approximate vectors in VA-File are just simply placed in flat structure files without other optimization methods. In this paper, we propose the Collecting and Multi-Vector-Approximation Indexed-File (CMVAI-File). The CMVAI-File is still an approximate-based index structure and uses a filterbased approach. Unlike the VA-File, the CMVAI-File uses multi-level approximate, collect the same vectorapproximations and a segmental structure to improve query performance. Experimental results show that CMVAI-File has a promising improvement in performance. © 2010 IEEE.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Normalized cut segmentation algorithm combined with fractional differential

Normalized cut segmentation algorithm combined with fraction...

引用

2011 8th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2011, Jointly with the 2011 7th International Conference on Natural Computation, ICNC'11

作者： Huang, Ying Xie, Mei Li, Weisheng Zhou, Lifang School of Electronic Engineering University of Electronic Science and Technology of China Chengdu 610054 China Chongqing Key Lab of Computer Network and Communication Technology Chongqing 400065 China Institute of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing 400065 China School of Software Chongqing University of Posts and Telecommunications Chongqing 400065 China

ISBN: (纸本)9781612841816

Fractional differential is used to adjust the affinity matrix of the image and to extract more useful edge and texture information. A graph is constructed for the original image with edge and texture information calculated with fractional differential, and the Laplacian matrix is obtained and the eigenvector corresponding to the second eigenvalue is classified to get the final segmentation results. Experimental results show that the proposed method can extract more fine details, preserve more useful information and get more accurate results. © 2011 IEEE.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

A Multi-dimensional Index Structure Based on Improved VA-file and CAN in the Cloud

引用

International Journal of Automation and computing 2014年第1期11卷 109-117页

作者： Chun-Ling Cheng Chun-Ju Sun Xiao-Long Xu Deng-Yin Zhang College of Computer Nanjing University of Posts and Telecommunications Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Key Lab of Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and TelecommunicationsMinistry of Education Jiangsu Province

Currently,the cloud computing systems use simple key-value data processing,which cannot support similarity search efectively due to lack of efcient index structures,and with the increase of dimensionality,the existing tree-like index structures could lead to the problem of"the curse of dimensionality".In this paper,a novel VF-CAN indexing scheme is ***-CAN integrates content addressable network(CAN)based routing protocol and the improved vector approximation fle(VA-fle) *** are two index levels in this scheme:global index and local *** local index VAK-fle is built for the data in each storage ***-fle is thek-means clustering result of VA-fle approximation vectors according to their degree of *** cluster forms a separate local index fle and each fle stores the approximate vectors that are contained in the *** vector of each cluster center is stored in the cluster center information fle of corresponding storage *** the global index,storage nodes are organized into an overlay network CAN,and in order to reduce the cost of calculation,only clustering information of local index is issued to the entire overlay network through the CAN *** experimental results show that VF-CAN reduces the index storage space and improves query performance efectively.

关键词： Cloud computing index similarity search clustering vector approximation fle(VA-fle) content addressable network(CAN)

来源：评论

学校读者我要写书评

暂无评论

Trustworthy web services discovery via supervised services representation and collaborative QoS prediction

引用

Journal of Computational Information Systems 2012年第21期8卷 8835-8846页

作者： Chen, Lei Yang, Geng Zhang, Yingzhou Wang, Tao Mou, Bolin College of Computer Nanjing University of Posts and Telecommunications Nanjing 210003 China Key Lab of Broadband Wireless Communication and Sensor Network Technology Ministry of Education Nanjing 210003 China

With the exponential growth of web services, the researches on how to accurately find the trustworthy services become increasingly important. Currently, some researchers have utilized the idea of services classification to minimize the services discovery duration, but seldom employed category label information to further improve services representation. In addition, the existing researches always assume that the nonfunctional QoS characteristics are known, which is actually impossible in reality. In this paper, in order to address these problems, we present a trustworthy web services discovery framework named *** with the existing approaches, the TWSDisC has the two advantages. First, by using the prior category label information, the TWSDisC imports the supervised Inverse Category Frequency term weighting scheme to facilitate services representation. Second, the TWSDisC adopts the state-of-the-art matrix completion technique to predict the missing QoS values and correct the corrupted ones. Experimental results performed on the real-world web services collection demonstrate the feasibility of the proposed approaches. © 2012 Binary Information Press.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Crowd-Sourced Mobility Mapping for Location Tracking Using Unlabeled Wi-Fi Simultaneous Localization and Mapping

引用

Mobile Information Systems 2015年第1期2015卷

作者： Zhou, Mu Xu, Kunjie Tian, Zengshan Wu, Haibo Shi, Ruikang Chongqing Key Lab of Mobile Communications Technology Chongqing University of Posts and Telecommunications Chongqing400065 China Ericsson San JoseCA95134 United States China Internet Research Lab Computer Network Information Center Chinese Academy of Sciences Beijing100190 China

Due to the increasing requirements of the seamless and round-the-clock Location-based services (LBSs), a growing interest in Wi-Fi network aided location tracking is witnessed in the past decade. One of the significant problems of the conventional Wi-Fi location tracking approaches based on received signal strength (RSS) fingerprinting is the time-consuming and labor intensive work involved in location fingerprint calibration. To solve this problem, a novel unlabeled Wi-Fi simultaneous localization and mapping (SLAM) approach is developed to avoid the location fingerprinting and additional inertial or vision sensors. In this approach, an unlabeled mobility map of the coverage area is first constructed by using the crowd-sourcing from a batch of sporadically recorded Wi-Fi RSS sequences based on the spectral cluster assembling. Then, the sequence alignment algorithm is applied to conduct location tracking and mobility map updating. Finally, the effectiveness of this approach is verified by the extensive experiments carried out in a campus-wide area. Copyright © 2015 Mu Zhou et al.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Collusion detector based on G-N algorithm for trust model

引用

Journal of Systems Engineering and Electronics 2016年第4期27卷 926-935页

作者： Lin Zhang Na Yin Jingwen Liu Ruchuan Wang College of Computer Nanjing University of Posts and TelecommunicationsNanjing 210003China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing 210003China Key Lab of Broadband Wireless Communication and Sensor Network Technology Nangjing University of Posts and TelecommunicationsNangjing 210003China

In the open network environment, malicious attacks to the trust model have become increasingly serious. Compared with single node attacks, collusion attacks do more harm to the trust model. To solve this problem, a collusion detector based on the GN algorithm for the trust evaluation model is proposed in the open Internet environment. By analyzing the behavioral characteristics of collusion groups, the concept of flatting is defined and the G-N community mining algorithm is used to divide suspicious communities. On this basis, a collusion community detector method is proposed based on the breaking strength of suspicious communities. Simulation results show that the model has high recognition accuracy in identifying collusion nodes, so as to effectively defend against malicious attacks of collusion nodes.

关键词： trust model collusion detector G-N algorithm

来源：评论

学校读者我要写书评

暂无评论

BrainPST: Pre-training Stacked Transformers for Dynamic Brain Functional network Analysis

BrainPST: Pre-training Stacked Transformers for Dynamic Brai...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Hu, Jinlong Huang, Yangmin Zhuo, Yi Dong, Shoubin South China University of Technology Guangdong Key Lab of Communication and Computer Network School of Computer Science and Engineering Guangzhou China

ISBN: (纸本)9798350337488

Deep learning methods have been applied for dynamic brain functional network analysis recently. However, they are usually restricted by the complex spatio-temporal dynamics and the limited labeled data. In this paper, we proposed a stacked Transformer neural network, namely BrainPST, to capture spatio-temporal patterns for dynamic brain functional network classification. BrainPST model integrated spatial and temporal information by stacking two Transformers: one for learning snapshot networks and the other for learning sequence of functional connections. Unlike recent models, BrainPST was designed to pre-train the stacked Transformer network by leveraging unlabeled existing brain imaging data. A pre-training framework with designed pre-training strategies was proposed to learn general spatio-temporal representations from the unlabeled brain networks, and to fine-tune the pre-trained model in downstream tasks. BrainPST is a conceptually simple and effective model. The results of experiments showed the BrainPST model without pre-training achieved comparative performance with the recent models, and the pre-trained BrainPST obtained new state-of-the-art performance. The pre-trained BrainPST improved 3.92% of AUC compared with the model without pre-training. © 2023 IEEE.

关键词： Classification Dynamic brain functional networks Pre-training Transformer

来源：评论

学校读者我要写书评

暂无评论

Prediction of Potential Repurposed Drugs against SARS-CoV-2 based on Text Mining and Molecular Docking Analysis 6

Prediction of Potential Repurposed Drugs against SARS-CoV-2 ...

引用

6th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2023

作者： Zhou, Jie Xu, Yi-Qing Guangdong Key Lab of Communication and Computer Network School of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9798400707674

Many research papers focusing the relationships between drugs and coronavirus-related protein interactions are indexed in the PubMed database. These studies provide a reference for predicting potential repurposed drugs against SARS-CoV-2. Drug repurposing, the most efficient strategy to quickly deploy new effective therapeutic drugs against SARS-CoV-2, can shorten the time and reduce the cost compared to de novo drug discovery. The purpose of this study was to predict potential repurposed drugs and drug pairs against SARS-CoV-2 using text mining and molecular docking analysis. We first constructed a coronavirus-related protein names list and a drug names list using the relevant protein and drug databases. We also constructed a qualifier list. A crawler program was implemented to retrieve the desired parts from the relevant papers in the PubMed database using records from the three query lists. Based on these extracted parts, we constructed a document set, a document drug names set, and a document protein names set. Then, we used the method proposed in our previous work to calculate the document vector of each document in the document set and the TF, IDF, and TF-IDF values. We calculated the vectors of each drug and protein in the document drug names set and document protein names set based on the document vectors. The cosine similarity between the protein vector and drug vector was calculated and the score of the pair of protein and drug was defined by the cosine similarity. Next, we selected the protein-drug pairs that scored above a given threshold as the predicted interactions for coronavirus-related protein-drug pairs and then extracted all the drugs from these predicted interactions and combined them to form distinct drug pairs. Finally, the drugs with PubChem 3D structure were simulated by a molecular docking tool with the four recently identified important SARS-CoV-2 proteins, and the drug pairs were simulated by the molecular docking tool with the SARS-CoV-2

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Transformer and Snowball Graph Convolution Learning for Brain Functional network Analysis

Transformer and Snowball Graph Convolution Learning for Brai...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Hu, Jinlong Huang, Yangmin Dong, Shoubin South China University of Technology Guangdong Key Lab of Communication and Computer Network School of Computer Science and Engineering Guangzhou China

ISBN: (纸本)9798350337488

Advanced deep learning methods, especially graph neural networks (GNNs), are increasingly expected to learn from brain functional network data and predict brain disorders. In this paper, we proposed a novel Transformer and snowball encoding networks (TSEN) for brain functional network classification, which introduced Transformer architecture with graph snowball connection into GNNs for learning whole-graph representation. TSEN combined graph snowball connection with graph Transformer by snowball encoding layers, which enhanced the power to capture multi-scale information and global patterns of brain functional networks. TSEN also introduced snowball graph convolution as position embedding in Transformer structure, which was a simple yet effective method for capturing local patterns naturally. We evaluated the proposed model by two large-scale brain functional network datasets from autism spectrum disorder and major depressive disorder respectively, and the results demonstrated that TSEN outperformed the state-of-the-art GNN models and the graph-transformer based GNN models. © 2023 IEEE.

关键词： Brain disorders Graph neural networks Snowball graph convolutional networks Transformer

来源：评论

学校读者我要写书评

暂无评论

(t, n) secret sharing scheme based on cylinder model in wireless sensor networks

引用

Journal of networks 2012年第7期7卷 1009-1016页

作者： Huang, Haiping Chen, Hao Wang, Ruchuan Mao, Qian Cheng, Renyuan Nanjing University of Posts and Telecommunications Department of Computer Nanjing University of Aeronautics and Astronautics Department of Computer Science and Technology Nanjing China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Ministry of Education/Key Lab of Broadband Wireless Communication and Sensor Network Technology Nanjing China

Since the existence of characteristics of heterogeneity, limited energy, complexity and so forth, it turns into a research hot spot on the security mechanism of wireless sensor networks (WSN), especially the problems on the key management. On regard of the deficiency of extant secret sharing schemes, we develop a (t, n) threshold secret sharing scheme which is based on the cylinder model, including the procedures of master-key reconfiguration and sub-key updating. This scheme enables several nodes to be responsible for the security of key together, and by the mean time, we introduce a monitoring mechanism to improve the capability of anti-capturing. With the security theoretical analysis and the comparison with the performance on BPCGR, GKD simulation experiment, it reveals that our scheme satisfies the security requirement of key management in wireless sensor networks, and can effectively reduce the cost on communication and computation. © 2012 ACADEMY PUBLISHER.

关键词： Wireless sensor networks

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：