检索结果-内蒙古大学图书馆

14th International Conference on Measuring Technology and Mechatronics Automation, ICMTMA 2022

作者： Qiang, Chengyu Li, Xiaogo Ma, Xianyan Han, Wei Yao, Yi School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Xi'an71012 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi'an710121 China Xi 'an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China

ISBN: (纸本)9781665499781

Entity disambiguation based on entity-link is a technique which constructs the mappings between entity reference items appearing in the short text and target entity in knowledge base respectively. In this paper we propose an entity disambiguation method based on Graph Attention networks for semi-structured knowledge base data. First, a global Knowledge Graph is constructed from the semi-structured knowledge base, and the entity reference items are embedded by Bert pre-trained model meanwhile. Next, Graph Attention networks which leverages masked self-attention layers is applyed on candidate entity nodes of global Knowledge Graph to fetch a vector of node level. Furtherly, we compute similarity scores rank between the entity reference items and the candidate entity to complete the task of entity disambiguation. The experimental results on CCKS2019 dataset achieve state-of-the-art. © 2022 IEEE

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

User Information Enhanced Knowledge Graph Convolutional networks for Recommender Systems 14

User Information Enhanced Knowledge Graph Convolutional Netw...

引用

14th International Conference on Measuring Technology and Mechatronics Automation, ICMTMA 2022

作者： Hao, Junyu Li, Xiaoge School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Xi'an71012 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi'an710121 China Xi'an Key laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China

ISBN: (纸本)9781665499781

To deeply excavate the information contained in user data and better alleviate cold start problem, we propose KGCN++, a user information enhanced knowledge graph convolutional networks model for recommender system, which simulates nerves' influence diffusion of information of user and items in a unified framework. The model combines user information and user-item interaction information into a user knowledge graph, which advances KGCN by injecting high-order user potential information reflected in user graph and high-order influence of items reflected in item knowledge graph. In addition, we have designed the influence factors of different items on users, which are used to characterize the weight of items on the user's information dissemination, so as to distinguish users with different information. Through extensive experiments on real-world datasets, we demonstrate that KGCN++ achieves substantial gains in a variety of ecenarios, including movie and book recommendation, better performance compared to the other methods. © 2022 IEEE

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

EEG-Based Fatigue Detection Using PLI Brain network and Relief Algorithm

EEG-Based Fatigue Detection Using PLI Brain Network and Reli...

引用

2022 International Conference on networking and network Applications, NaNA 2022

作者： He, Yan Wang, Zhongmin Zhao, Yupeng Xi'an University of Posts and Telecommunications Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Xi'an710121 China

ISBN: (数字)9781665461313

ISBN: (纸本)9781665461313

EEG-based fatigue driving monitoring has important application value in road traffic safety, and the ultimate goal of the research is the development and use of wearable devices, and too many EEG channels in practical application scenarios is detrimental to device portability, and it will lead to problems such as large amount of data, complex calculation and long processing time, so it is especially important to study how to select the EEG channels highly correlated with fatigue. In this paper, a PLI-Relief-based channel selection algorithm by combining the PLI functional connectivity and the weighting idea of Relief algorithm is proposed, and it is applied to the channel selection of fatigue driving EEG. First, the PLI functional connectivity matrix is constructed for the EEG signals after preprocessing, and the binarized PLI matrix is mapped into a brain functional network, and the prime channels are selected by the degree property of the brain network. Then, the power spectral density features are extracted from the EEG signals of the prime channels, and the weights of each prime channel are obtained using the relief algorithm, then the number and the names of optimal channels are determined according to the recognition accuracy of different channel combinations. The proposed method was validated on the publicly available SEED-VIG dataset, and the data of the seven optimal channels is finally selected and obtains a classification accuracy of 81.25%. The framework proposed in this paper takes into account both the correlation between channels and the characteristics of the channel signals themselves in channel selection, which is a reference value for the development and application of wearable devices. © 2022 IEEE.

关键词： Wearable technology

来源：评论

学校读者我要写书评

暂无评论

Incremental QR-based tensor-train decomposition for industrial big data

引用

The Journal of China Universities of Posts and Telecommunications 2021年第1期28卷 10-23页

作者： Chen Yanping Jin Xiaodong Xia Hong Wang Zhongmin School of Computer Technology Xi'an University of Posts and TecomniunicationsXi'an 710121China Shaanxi Key Laboratory of Network Dala Analysis anti Intelligent Processing Xi'an L nivarsity of Posts and TelecommunicationsXi'an 710121China

Industrial big data was usually multi-source, heterogeneous, and deeply intertwined. It had a wide range of data sources, high data dimensions, and strong data correlation. In order to effectively analyze and process streaming industrial big data generated by edge computing, it was very important to provide an effective real-time incremental data method. However, in the process of incremental processing, industrial big data incremental computing faced the challenges of dimensional disaster, repeated calculations, and the explosion of intermediate results. Therefore, in order to solve the above problems effectively, a QR-based tensor-train(TT) decomposition(TTD) method and a QR-based incremental TTD(QRITTD) method were proposed. This algorithm combined the incremental QR-based decomposition algorithm with an approximate singular value decomposition(SVD) algorithm and had good scalability. In addition, the computational complexity, space complexity, and approximation error analysis were analyzed in detail. The effectiveness of the three algorithms of QRITTD, non-incremental TTD(NITTD), and TT rank-1(TTr1) SVD(TTr1 SVD)were verified by comparison. Experimental results show that the SVD QRITTD method has better performance under the premise of ensuring the same tensor size.

关键词： tensor-train decomposition incremental processing edge computing industrial big data

来源：评论

学校读者我要写书评

暂无评论

Multi-scale fusion residual encoder-decoder approach for low illumination image enhancement

引用

The Journal of China Universities of Posts and Telecommunications 2022年第2期29卷 63-72页

作者： Pan Xiaoying Wei Miao Wang Hao Jia Fengzhu School of Computer Science and Technology Xi'an University of Posts and TelecommunicationsXi'an 710121China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and TelecommunicationsXi'an 710121China School of Software Northwestern Polytechnical UniversityXi'an 710072China

The sensing light source of the line scan camera cannot be fully exposed in a low light environment due to the extremely small number of photons and high noise,which leads to a reduction in image quality.A multi-scale fusion residual encoder-decoder(FRED)was proposed to solve the *** directly learning the end-to-end mapping between light and dark images,FRED can enhance the image’s brightness with the details and colors of the original image fully restored.A residual block(RB)was added to the network structure to increase feature diversity and speed up network ***,the addition of a dense context feature aggregation module(DCFAM)made up for the deficiency of spatial information in the deep network by aggregating the context’s global multi-scale *** experimental results show that the FRED is superior to most other algorithms in visual effect and quantitative evaluation of peak signal-to-noise ratio(PSNR)and structural similarity index measure(SSIM).For the factor that FRED can restore the brightness of images while representing the edge and color of the image effectively,a satisfactory visual quality is obtained under the enhancement of low-light.

关键词： image enhancement low illumination feature fusion residual network

来源：评论

学校读者我要写书评

暂无评论

A Model robustness optimization method based on adversarial sample detection 5

A Model robustness optimization method based on adversarial ...

引用

5th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2022

作者： Sun, Jiaze Long, Siyuan Ma, Xianyan Tang, Yanmei Xi'an University of Posts and Telecommunications Shaanxi Provincial Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'an710121 China Xi'an University of Posts and Telecommunications Xi'an710121 China

ISBN: (纸本)9781450396899

Deep neural networks are extremely vulnerable due to the existence of adversarial samples. It is a challenging problem to optimize the robustness of the model to protect deep neural networks from the threat of adversarial samples. To improve the model robustness, an integrated detection model of adversarial samples is designed to detect the existence of adversarial samples, which consists of a multi-classification detector and five single-classification detectors to perform double-layer detection of adversarial samples and intercept the adversarial samples finally sent to the image classification model. The detection experiments were conducted on the CIFAR-10 dataset for the adversarial samples generated by five attack algorithms: FGSM, BIM, DeepFool, JSMA, and C&W, and the detection success rate for all types of adversarial samples reached over 98.96%. After that, secondary attack experiments were conducted on the model, and the detection success rate of the model for the second attack adversarial samples reached over 92.36%. It provides an efficient and robust optimization method for deep neural network models in adversarial environments. © 2022 ACM.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

UAV Visual Tracking Algorithm Based on Feature Fusion of the Attention Mechanism 5

UAV Visual Tracking Algorithm Based on Feature Fusion of the...

引用

5th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2022

作者： Ma, Sugang Zhang, Zixian Zhao, Zhixian Yang, Xiaobao Hou, Zhiqiang School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Xi'an China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and Telecommunications Shaanxi Xi'an China Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'an University of Posts and Telecommunications Shaanxi Xi'an China

ISBN: (纸本)9781450396899

To enhance the expression ability of deep features and improve the tracking performance of the fully convolutional siamese network (SiamFC) in the UAV scene, we propose a UAV visual tracking algorithm based on feature fusion of the attention mechanism. By designing the local perception attention module and the global perception attention module to enhance the features extracted from the backbone network, a set of complementary local enhanced features and global enhanced features are obtained. And then, the tracking response map fused with the two features is then located, which effectively improves the tracking robustness of SiamFC in the UAV scene. The algorithm and nine other related algorithms such as SiamFC are tested on the DTB70 dataset. The experiments show that the algorithm has a good tracking performance and can adapt to the visual object tracking task in the UAV scene. © 2022 ACM.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

On the connectivity of highly dynamic wireless sensor networks in smart factory

On the connectivity of highly dynamic wireless sensor networ...

引用

2019 International Conference on networking and network Applications, NaNA 2019

作者： Gao, Cong Wang, Zhongmin Chen, Yanping School of Computer Science and Technology Xi'an China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an China Xi'An University of Posts and Telecommunications Xi'an China

ISBN: (纸本)9781728126296

With the development of smart manufacturing in Industry 4.0, large amount of heterogeneous data are generated from multiple sources. Various data processing techniques can be applied to these data for the purpose of extracting potential information about the status of the manufacturing network. Thus, data are valuable to the analysis and adjustment of the manufacturing processes. Due to the diversity of products, assembly lines and manufacturing processes are highly dynamic. In view of the flexible deployment of wireless sensor networks, they have been widely deployed to conduct data collection. However, due to the limited radio range of a wireless sensor node, the connectivity of a highly dynamic wireless sensor network is a key issue. In this paper, we analyzed the connectivity in a wireless sensor network and accorded three types of connectivity. Then, we developed two network connectivity models from the perspective of one dimension and two dimensions. The degrees of connectivity for both two nodes and the network are elaborated. Finally, the relation between the number of sink nodes and the average degree of connectivity of the network is analyzed based on experimental results. © 2019 IEEE.

关键词： data handling

来源：评论

学校读者我要写书评

暂无评论

Object Detection Algorithm Based on Second-Order Pooling network and Gaussian Mixture Attention 5

Object Detection Algorithm Based on Second-Order Pooling Net...

引用

5th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2022

作者： Ma, Sugang Li, Ningbo Yang, Xiaobao School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Xi'an China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and Telecommunications Shaanxi Xi'an China Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'an University of Posts and Telecommunications Shaanxi Xi'an China

ISBN: (纸本)9781450396899

To improve the feature representation ability of the YOLOX algorithm and obtain better detection performance, an object detection algorithm based on second-order pooling network and gaussian mixture attention is proposed. Firstly, the second-order pooling network is added after the PAFPN, and the higher-order statistical information is obtained by calculating the covariance matrix between different channels, to enhance the non-linear modeling capability. Secondly, the mixture attention based on the gaussian function is added after the SPP to model global contexts in the spatial and channel dimensions respectively, which improves the network performance with almost no extra parameters. The experimental results show that the detection accuracy of the proposed algorithm on the PASCAL VOC dataset reaches 82.6 %, which is 1.6 % higher than the YOLOX algorithm. © 2022 ACM.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Image Description Generation Method Based on X-Linear Attention Mechanism 5

Image Description Generation Method Based on X-Linear Attent...

引用

5th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2022

作者： Qiao, Pingan Li, Yuan Shen, Ruixue Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an710121 China School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi'an710121 China

ISBN: (纸本)9781450396899

Aiming at the problem that existing image description models cannot model high-order multimodal feature interaction, this paper introduces the X-Linear attention mechanism, which uses bilinear pooling and ELU activation function to model high-order feature interaction between multimodal features. At the same time, the X-Linear attention mechanism uses spatial and channel attention mechanisms to enhance the expression ability of the model and the ability to generate image description sentences. The experimental results on the MSCOCO data set show that this method is effective and has a great improvement in each evaluation metric. © 2022 ACM.

关键词： Image enhancement

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：