检索结果-内蒙古大学图书馆

Inductive Relation Prediction by Disentangled Subgraph Structure

Tsinghua Science and Technology 2024年第5期29卷 1566-1579页

作者： Guiduo Duan Rui Guo Wenlong Luo Guangchun Luo Tianxi Huang Laboratory of Intelligent Collaborative Computing University of Electronic Science and Technology of ChinaChengdu 611731Chinaand also with Trusted Cloud Computing and Big Data Key Laboratory of Sichuan ProvinceChengdu 611731China School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China Hangzhou NetEase Cloud Music Technology Co. Ltd.Hangzhou 310052China Department of Fundamental Courses Chengdu Textile CollegeChengdu 611700China

Currently,most existing inductive relation prediction approaches are based on subgraph structures,with subgraph features extracted using graph neural networks to predict ***,subgraphs may contain disconnected regions,which usually represent different semantic *** not all semantic information about the regions is helpful in relation prediction,we propose a relation prediction model based on a disentangled subgraph structure and implement a feature updating approach based on relevant semantic *** indirectly achieve the disentangled subgraph structure from a semantic perspective,the mapping of entity features into different semantic spaces and the aggregation of related semantics on each semantic space are *** disentangled model can focus on features having higher semantic relevance in the prediction,thus addressing a problem with existing approaches,which ignore the semantic differences in different subgraph ***,using a gated recurrent neural network,this model enhances the features of entities by sorting them by distance and extracting the path information in the ***,it is shown that when there are numerous disconnected regions in the subgraph,our model outperforms existing mainstream models in terms of both Area Under the Curve-Precision-Recall(AUC-PR)and Hits@*** prove that semantic differences in the knowledge graph can be effectively distinguished and verify the effectiveness of this method.

关键词： disentangled subgraph structure knowledge graph completion Gated Recurrent Unit(GRU) feature updating

来源：评论

学校读者我要写书评

暂无评论

Dark channel a priori defogging algorithm based on a combination of bright channel inversion and dark channel weighting 3

Dark channel a priori defogging algorithm based on a combina...

引用

3rd International Conference on Optics and Image Processing, ICOIP 2023

作者： Wei, Qida Zhou, Yunqing School of Information Engineering Zhejiang Ocean University Zhoushan316022 China Department of Physics Key Laboratory of Oceanographic Big Data Mining Application of Zhejiang Province Zhejiang Ocean University Zhoushan316000 China

ISBN: (纸本)9781510667426

The classical traditional dark channel priori algorithm causes colour distortion in bright areas of the sky, snow and other surfaces when processing images, and the overall darkness of the recovered image is complicated, resulting in slow processing speed. In this paper, we propose an adaptive modified dark channel priori defogging algorithm that combines inverse bright channel and dark channel weighting. Firstly, the brightest channel of the RGB channel of the fogged image is inverted, and then the dark channel is weighted and combined with the dark channel to correct the dark channel and adaptively correct the transmittance. Secondly, the mean value of the brightest 0.1% of pixels in the new dark channel is used in estimating atmospheric light values;finally, the transmittance estimation is optimised using multi-window fitting and guided filtering methods. Experimental results show that the algorithm improves the dark channel priori colour distortion in bright regions, with faster processing and more effective defogging. © 2023 SPIE. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

An effective global learning framework for hyperspectral image classification based on encoder-decoder architecture

引用

International Journal of Digital Earth 2022年第1期15卷 1350-1376页

作者： Lanxue Dang Chongyang Liu Weichuan Dong Yane Hou Qiang Ge Yang Liu Henan Key Laboratory of Big Data Analysis and Processing Henan UniversityKaifengChina School of Computer and Information Engineering Henan UniversityKaifengChina Department of Geography Kent State UniversityKentOHUSA

Most deep learning methods in hyperspectral image(HSI)classification use local learning methods,where overlapping areas between pixels can lead to spatial redundancy and higher computational *** paper proposes an efficient global learning(EGL)framework for HSI *** EGL framework was composed of universal global random stratification(UGSS)sampling strategy and a classification model *** UGSS sampling strategy was used to solve the problem of insufficient gradient variance resulted from limited training *** fully extract and explore the most distinguishing feature representation,we used the modified linear bottleneck structure with spectral attention as a part of the BrsNet network to extract spectral spatial *** a type of spectral attention,the shuffle spectral attention module screened important spectral features from the rich spectral information of HSI to improve the classification accuracy of the ***,we also designed a double branch structure in BrsNet that extracted more abundant spatial information from local and global perspectives to increase the performance of our classification *** were conducted on three famous datasets,IP,PU,and *** with other classification methods,our proposed method produced competitive results in training time,while having a greater advantage in test time.

关键词： Deep learning global learning feature representation hyperspectral image classification spectral attention

来源：评论

学校读者我要写书评

暂无评论

Graph Regularized Sparse Non-Negative Matrix Factorization for Clustering

引用

IEEE Transactions on Computational Social Systems 2023年第3期10卷 910-921页

作者： Deng, Ping Li, Tianrui Wang, Hongjun Wang, Dexian Horng, Shi-Jinn Liu, Rui Southwest Jiaotong University National Engineering Laboratory of Integrated Transportation Big Data Application Technology School of Computing and Artificial Intelligence Chengdu611756 China National Taiwan University of Science and Technology Department of Computer Science and Information Engineering Taipei106 Taiwan North Sichuan Medical College School of Preclinical Medicine Department of Computer and Mathematics Nanchong637100 China

The graph regularized nonnegative matrix factorization (GNMF) algorithms have received a lot of attention in the field of machine learning and data mining, as well as the square loss method is commonly used to measure the quality of reconstructed data. However, noise is introduced when data reconstruction is performed;and the square loss method is sensitive to noise, which leads to degradation in the performance of data analysis tasks. To solve this problem, a novel graph regularized sparse NMF (GSNMF) is proposed in this article. To obtain a cleaner data matrix to approximate the high-dimensional matrix, the l1-norm to the low-dimensional matrix is added to achieve the adjustment of data eigenvalues in the matrix and sparsity constraint. In addition, the corresponding inference and alternating iterative update algorithm to solve the optimization problem are given. Then, an extension of GSNMF, namely, graph regularized sparse nonnegative matrix trifactorization (GSNMTF), is proposed, and the detailed inference procedure is also shown. Finally, the experimental results on eight different datasets demonstrate that the proposed model has a good performance. © 2014 IEEE.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Multiobjective Feature Selection Assisted by Unselected Features 13

Evolutionary Multiobjective Feature Selection Assisted by Un...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Duan, Xuan Liu, Songbai Ji, Junkai Li, Lingjie Lin, Qiuzhen Tan, Kay Chen College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen China Shenzhen China The Hong Kong Polytechnic University Department of Computing Hong Kong

ISBN: (纸本)9798350308365

To enhance the generalization of multi-objective feature selection (MOFS) in classification, this paper proposes an evolutionary multitasking algorithm, diverging from previous approaches that exclusively target selected features. The algorithm integrates information from both selected and unselected features, introducing a novel objective to minimize the accuracy of unselected features. This objective, combined with the goal of minimizing classification errors for selected features, forms an auxiliary MOFS task. The paper presents a dual-population evolutionary multitasking framework that synergizes the main MOFS task with the auxiliary task. A knowledge transfer mechanism, based on accuracy preferences, seamlessly shares insights from the auxiliary to the main task, aiming to identify improved Pareto feature subsets. Empirical results demonstrate the superior performance of several state-of-the-art multi-objective algorithms within this framework, highlighting significant improvements across diverse datasets. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Sequence-Based Predicting Bacterial Essential ncRNAs Algorithm by Machine Learning

引用

Intelligent Automation & Soft Computing 2023年第6期36卷 2731-2741页

作者： Yuan-Nong Ye Ding-Fa Liang Abraham Alemayehu Labena Zhu Zeng Bioinformatics and Biomedical Big data Mining Laboratory Department of Medical InformaticsSchool of Big HealthGuizhou Medical UniversityGuiyang550025China Cells and Antibody Engineering Research Center of Guizhou Province Key Laboratory of Biology and Medical EngineeringSchool of Biology and EngineeringGuizhou Medical UniversityGuiyang550025China Key Laboratory of Environmental Pollution Monitoring and Disease Control Ministry of EducationGuizhou Medical UniversityGuiyang550025China College of Computational and Natural Sciences Dilla UniversityDilla419Ethiopia

Essential ncRNA is a type of ncRNAwhich is indispensable for the sur-vival of *** essential ncRNAs cannot encode proteins,they are as important as essential coding genes in *** have got wide variety of applications such as antimicrobial target discovery,minimal genome construction and evolution *** present,the number of species required for the deter-mination of essential ncRNAs in the whole genome scale is still very few due to the traditional methods are time-consuming,laborious and *** addition,tra-ditional experimental methods are limited by the organisms as less than 1%of bacteria can be cultured in the ***,it is important and necessary to develop theories and methods for the recognition of essential non-coding *** this paper,we present a novel method for predicting essential ncRNA by using both compositional and derivative features calculated by information theory of ncRNA *** method was developed with Support Vector Machine(SVM).The accuracy of the method was evaluated through cross-species cross-vali-dation and found to be between 0.69 and *** shows that the features we selected have good performance for the prediction of essential ncRNA using ***,the method can be applied for discovering essential ncRNAs in bacteria.

关键词： Bioinformatics biological information theory biomedical informatics

来源：评论

学校读者我要写书评

暂无评论

Research on Image Captioning Based on Vision-language Pre-trained Models 9

Research on Image Captioning Based on Vision-language Pre-tr...

引用

9th International Conference on Big data and Information Analytics, BigDIA 2023

作者： Zou, Shiwei Xie, Yuxiang Yan, Jie Wei, Yingmei Luan, Xidao National University of Defense Technology Department of System Engineering Hunan China National University of Defense Technology Key Laboratory of Big Data Department of System Engineering Changsha Hunan China Changsha University Department of Computer Science Hunan China

ISBN: (纸本)9798350330076

Image captioning is a vision-language task that targets at describing an image by generating a coherent sentence automatically. This technology allows computers to understand and describe images like humans, enabling further processing of images. It combines computer vision and natural language processing, which has broad applications. This paper investigates the use of vision-language pre-trained models for image captioning. In this article, an encoder-decoder hybrid model based on PVT and BERT is pre-trained on a large number of image-text pairs, possessing both understanding and generation capabilities. It consists of three components: 1) an image encoder and a text encoder to extract image and text features respectively;2) a multi-modal encoder to align the two modalities;and 3) a text decoder to generate text descriptions. This paper focuses on enhancing the image encoder of the model, which is crucial for image captioning models as it extracts high-resolution image features. Reducing training time and computational costs can also improve the applicability of pre-trained models. Improvements are made to the original model by modifying the ViT model architecture of the image encoding module. A feature pyramid structure and a spatial reduction attention mechanism is introduced to extract high-resolution image features while reducing computational complexity and memory usage, thereby enhancing the universality of the model. The model adopts a pure Transformer architecture, discarding the convolutional structure, and achieves excellent performance. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Research and implementation of image enhancement method based on improved retinex algorithm 3

Research and implementation of image enhancement method base...

引用

3rd International Conference on Optics and Image Processing, ICOIP 2023

作者： Zhang, Diya Wang, Yumeng Wang, Yanrui Pu, Yile Bi, Zhenbo Rao, Wei School of Information Engineering Zhejiang Ocean University Zhoushan316022 China Department of Physics Key Laboratory of Oceanographic Big Data Mining Application of Zhejiang Province Zhejiang Ocean University Zhoushan316000 China

ISBN: (纸本)9781510667426

In view of the phenomenon of detail loss and edge blurring in color images collected underwater, noise reduction is mostly ignored in underwater image enhancement research. In this paper, an improved image enhancement method based on Retinex algorithm is proposed. First,the original underwater image is transferred from RGB channels to HSI color space, and the saturation component is adaptively linearly stretched by gamma correction, The improved Retinex decomposition network based on homomorphic filtering is used to decompose and enhance the Lightness component separately. Eventually, the fused image is transferred from HSI to RGB color space, and the processed image is output. According to the experimental results, this algorithm can not only eliminate the halo artifacts, but also improve the brightness and contrast of the image, restore the original details of the image, and effectively remove the image noise. It greatly improves the visual effect and objective evaluation results of images. © 2023 SPIE. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Investigation on Analog and Digital Modulations Recognition Using Machine Learning Algorithms

引用

World Journal of engineering and Technology 2024年第4期12卷 867-884页

作者： Jean Ndoumbe Ivan Basile Kabeina Gaelle Patricia Talotsing Soubiel-Noël Nkomo Biloo Laboratory of Computer Engineering Data Science and Artificial Intelligence National Higher Polytechnic School of Douala Douala Cameroon Mobile Computing and Networking Research Laboratory Department of Computer and Software Engineering Polytechnique Montreal Montreal Canada

In the field of radiocommunication, modulation type identification is one of the most important characteristics in signal processing. This study aims to implement a modulation recognition system on two approaches to machine learning techniques, the K-Nearest Neighbors (KNN) and Artificial Neural Networks (ANN). From a statistical and spectral analysis of signals, nine key differentiation features are extracted and used as input vectors for each trained model. The feature extraction is performed by using the Hilbert transform, the forward and inverse Fourier transforms. The experiments with the AMC Master dataset classify ten (10) types of analog and digital modulations. AM_DSB_FC, AM_DSB_SC, AM_USB, AM_LSB, FM, MPSK, 2PSK, MASK, 2ASK, MQAM are put forward in this article. For the simulation of the chosen model, signals are polluted by the Additive White Gaussian Noise (AWGN). The simulation results show that the best identification rate is the MLP neuronal method with 90.5% of accuracy after 10 dB signal-to-noise ratio value, with a shift of more than 15% from the k-nearest neighbors’ algorithm.

关键词： Automatic Recognition Artificial Neural Networks K-Nearest Neighbors Machine Learning Analog Modulations Digital Modulations

来源：评论

学校读者我要写书评

暂无评论

HOFD: An Outdated Fact Detector for Knowledge Bases

引用

IEEE Transactions on Knowledge and data engineering 2023年第10期35卷 10775-10789页

作者： Hao, Shuang Chai, Chengliang Li, Guoliang Tang, Nan Wang, Ning Yu, Xiang Beijing Jiaotong University School of Computer and Information Technology Beijing100044 China Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing100044 China Beijing Institute of Technology School of Computer Science and Technology Beijing100811 China Beijing100190 China Qatar Computing Research Institute Hbku Doha34110 Qatar Huawei Company Gauss Department Beijing100031 China

Knowledge bases (KBs), which store high-quality information, are crucial for many applications, such as enhancing search results and serving as external sources for data cleaning. Not surprisingly, there exist outdated facts in most KBs due to the rapid change of information. Naturally, it is important to keep KBs up-to-date. Traditional wisdom has investigated the problem of using reference data (such as new facts extracted from the news) to detect outdated facts in KBs. However, existing approaches can only cover a small percentage of facts in KBs. In this paper, we propose HOFD, a novel human-in-the-loop approach for outdated fact detection in KBs. HOFD trains a binary classifier using features such as historical update frequency and update time of a fact to compute the likelihood of a fact in a KB to be outdated. Then, HOFD interacts with humans to verify whether a fact with high likelihood is indeed outdated. In addition, HOFD also uses logical rules to detect more outdated facts based on human feedback. The outdated facts detected by the logical rules will also be fed back to train the ML model further for data augmentation. Extensive experiments on real-world KBs, such as Yago and DBpedia, show the effectiveness of our solution. © 1989-2012 IEEE.

关键词： Knowledge based systems

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：