检索结果-内蒙古大学图书馆

International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)

作者： Refka Hanachi Akrem Sellami Imed Riadh Farah Mauro Dalla Mura RIADI Laboratory University of Manouba Manouba Tunisia CNRS Centrale Lille UMR 9189 CRIStAL University of Lille Lille France GIPSA laboratory CNRS Grenoble INP Grenoble France

ISBN: (数字)9798350351484

ISBN: (纸本)9798350351491

High-dimensional image analysis, such as Hyperspectral Imaging (HSI) data, poses unique challenges due to their high dimensionality and non-Euclidean structures, making their analysis and classification complex. In this study, we explore the use of both graph deep learning (GDL) and multi-view graph representation learning for HSI classification. Furthermore, we present our proposed approach of multi-view graph convolutional networks (GCNs) and how it leverages multiple views of the data by combining spectral and spatial features to improve classification accuracy. We discuss then specific challenges encountered when training our model on large HSIs, including managing large-scale graph data. We also discuss promising opportunities to overcome these challenges. By highlighting the challenges and opportunities associated with GDL and multi-view GCN usage for HSI classification, this study aims to shed light on recent developments and future prospects in this rapidly evolving field.

关键词： Deep learning Training Representation learning Image analysis Accuracy Navigation graph convolutional networks

来源：评论

学校读者我要写书评

暂无评论

Node Influence Evaluation Through K-Shell Convoluted Proximal Aggregation

Node Influence Evaluation Through K-Shell Convoluted Proxima...

引用

International Conference on Computers, Communications, and Systems (ICCCS)

作者： Yongji Liu Boyuan Zhu Fansong Chen Weicheng Lin Haiqiang Fei Hongsong Zhu Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350350210

ISBN: (纸本)9798350350227

Optimizing methodologies for identifying vital nodes within complex networks is an active field of study. Our findings indicate that although the traditional techniques for static undirected complex networks are effective in vital node identification, opportunities persist for enhancing both node ranking accuracy and resolution. In response, we introduce a novel approach, K-Shell Convoluted Proximal Aggregation (KSCPA). This novel method incorporates the convolution characteristic from graph convolutional networks (GCNs), enabling localized node evaluation through the aggregation of adjacent node information. To evaluate the proposed method, we employed Kendall's Tau correlation index to compare with the Susceptible Infected Recovered model (SIR) for ranking accuracy and used a monotonicity function to assess ranking resolution. At the end, empirical analysis across 12 real-world network datasets reveals that KSCPA outperforms established techniques in ranking accuracy and resolution, thereby confirming its efficacy in identifying key nodes in complex networks.

关键词： Accuracy Correlation graph convolutional networks Convolution Computer network reliability Refining Complex networks

来源：评论

学校读者我要写书评

暂无评论

Common-Memory Bridged Cross-Modal Adaptive graph Embedding for Image-Text Retrieval

Common-Memory Bridged Cross-Modal Adaptive Graph Embedding f...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Zheng Cui Yongli Hu Jiapu Wang Junbin Gao Yanfeng Sun Baocai Yin Beijing Institute of Artificial Intelligence Beijing University of Technology Beijing China The University of Sydney Business School The University of Sydney Sydney Australia

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

The task of image-text retrieval has gained significant attention in the realm of multimodal artificial intelligence. Nonetheless, existing works encounter challenges in efficiently utilizing inter-modal information and adequately leveraging crucial intra-modal details. In this paper, we propose a novel common-Memory Bridged cross-modal Adaptive graph Embedding (MBAGE) network for image-text retrieval. Initially, we represent images and text as graphs, wherein nodes symbolize salient regions and words. Subsequently, we incorporate a common-memory bank as an intermediate bridge, facilitating interactions between nodes in the two graphs and enabling efficient utilization of inter-modal information. Additionally, we propose an adaptive graph convolutional network to implement intra-modal interaction, which can adaptively suppress the learning of unimportant nodes. Finally, adaptive pooling is employed to retain essential information, yielding a superior holistic embedding. Experimental results on the Flickr30K and MS-COCO datasets demonstrate that the MBAGE network not only achieves compelling retrieval precision but also exhibits high retrieval efficiency.

关键词： Bridges Visualization Adaptive systems graph convolutional networks Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Skin cancer classification: A comparative analysis of EfficientNet and Hybrid model(Xception+Efficient Net+GCN)

Skin cancer classification: A comparative analysis of Effici...

引用

Innovations in Communications, Electrical and Computer Engineering (ICICEC), International Conference on

作者： Kamireddy Vijay Chandra C.V. Rambabu S. Bhargav K. Sudha Rani Poornaiah Billa Dept of EIE Valluripalli Nageshwar Rao Vignana Jyothi Institute of Engineering and Technology Hyderabad Department of ECE Lakireddy Bali Reddy College of Engineering AP India

ISBN: (数字)9798350376517

ISBN: (纸本)9798350376524

Skin cancer, primarily caused by abnormal skin cell growth due to excessive exposure to UV radiation, includes common forms such as squamous cell carcinoma, basal cell carcinoma, and melanoma. Early and accurate detection is crucial for effective treatment. This study compares the performance of a newly developed hybrid model with several well-established pretrained convolutional neural networks (CNNs) for skin cancer image classification. The analysis focuses on popular CNN architectures, including EfficientNet, alongside a hybrid model that integrates Xception, EfficientNet, and graph convolutional networks (GCN) to enhance feature extraction and classification accuracy. Both models were fine-tuned using the Skin Cancer ISIC 2020 dataset from Kaggle, comprising 11,396 images. Of these, 9,200 images (5,200 benign and 4,000 malignant) were used for training, while 2,196 images (1,100 benign and 1,096 malignant) were reserved for testing. Evaluation metrics such as runtime, accuracy, precision, recall, and F1 score were employed. The EfficientNet model achieved an accuracy of 77% with a runtime of 43 seconds. However, the hybrid model demonstrated significantly better performance, achieving 90% accuracy and greater efficiency. Additionally, a user-friendly interface was developed using the Flask framework to allow users to easily test and validate the model's performance.

关键词： Training Analytical models Accuracy Runtime graph convolutional networks Computational modeling Computer architecture Feature extraction Skin cancer Testing

来源：评论

学校读者我要写书评

暂无评论

Human Object Interactivity Detection usinggraph Neural networks

Human Object Interactivity Detection usingGraph Neural Netwo...

引用

Electronics, Computing, Communication and Control Technology (ICECCC), International Conference on

作者： Arun Harbola Rahul Rana Shubham Singh Rawat Krishna Saini Satvik Vats Vikrant Sharma Computer Science and Engineering Graphic Era Hill University Dehradun India Computer Science and Engineering Graphic Era Hill University Adjunct professor Graphic Era Deemed to be University Dehradun India

ISBN: (数字)9798350371802

ISBN: (纸本)9798350371819

graph-based machine learning is a versatile framework tailored for diverse object interactions, particularly in action recognition. Skeleton-based graph Neural Network (GNN) methods have proven effective, capturing temporal relationships in frame-by-frame human- object interactions. This study addresses the complexity of recognizing multiple actions in untrimmed videos, focusing on a multi-person scenario. YOLOv5's object detection identifies objects in videos, and various neural network architectures (ANN, 1DCNN, LSTM, GNN) are compared for action recognition. The GNN-based technique, leveraging adult skeleton data from established datasets, outperforms others in efficiency and accuracy, showcasing its potential for robust human-object interaction recognition.

关键词： YOLO graph convolutional networks Focusing Machine learning graph neural networks Skeleton Spatiotemporal phenomena

来源：评论

学校读者我要写书评

暂无评论

Drug-disease association prediction based on end-to-end multi-layer heterogeneous graph convolutional encoders

引用

Informatics in Medicine Unlocked 2023年 37卷

作者： Ghasemi, Shahin Lakizadeh, Amir Computer Engineering Department University of Qom Qom Iran

Traditional drug development in wet labs has long been a costly, cumbersome and error-prone process. Thus, taking advantage of computational power to create algorithmic methods for identifying new treatments for approved drugs is of high importance. Most of the previous works have been strongly relying on the drug's features as well as the similarities between the biological entities to predict potential associations between drugs and diseases. However, the relationships between different biological entities provide crucial information and, unlike previously conducted researches, can be used as the knowledge graph for drug-disease pair interaction prediction tasks. In this study, a novel end-to-end multi-layers heterogeneous graph convolutional encoder (LHGCE) has been proposed to predict candidate associations between drugs and diseases. Firstly, it creates multiple networks between different biological entities, then combines them to build a heterogeneous network as a knowledge graph to capture the topological information of the nodes in the network context. After constructing the network and applying a message-passing operation, the embeddings of the drugs and diseases of each drug-disease pair is extracted and fed into the linear layers to predict the potential interactions. The experimental results based on 5-fold cross-validation showed that LHGCE outperforms state-of-the-art methods in terms of the most evaluation metrics. © 2023

关键词： Drug repurposing Drug–disease association prediction graph convolutional networks Node embedding

来源：评论

学校读者我要写书评

暂无评论

Knowledge graph enhanced neural collaborative recommendation

引用

Expert Systems with Applications 2021年 164卷

作者： Sang, Lei Xu, Min Qian, Shengsheng Wu, Xindong Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) Ministry of Education Hefei 230009 China Faculty of Engineering and Information Technology University of Technology Sydney Sydney 2007 Australia School of Computer Science and Information Engineering Hefei University of Technology Hefei 230009 China Institute of Automation Chinese Academy of Sciences Beijing 100190 China Mininglamp Academy of Sciences Mininglamp Technology Beijing 100084 China

Existing neural collaborative filtering (NCF) recommendation methods suffer from severe sparsity problem. Knowledge graph (KG), which commonly consists of fruitful connected facts about items, presents an unprecedented opportunity to alleviate the sparsity problem. However, pure NCF models can hardly model the high-order connectivity in KG, and ignores complex pairwise correlations between user/item embedding dimensions. To address these problems, we propose a novel Knowledge graph enhanced Neural Collaborative Recommendation (K-NCR) framework, which effectively combines user–item interaction information and auxiliary knowledge information for recommendation task into three parts: (1) For items, the proposed propagating model learns the representation of item entity. It recursively aggregates information from its multi-hop neighbours in KG, and employs an attention mechanism to discriminate the importance of the relation type to mine users’ potential preferences. (2) For users, another heterogeneous attention weights are leveraged to strengthen the embedding learning of users. (3) The user and item embeddings are then fed into a newly designed two-dimensional interaction map with convolutional hidden layers to model the complex pairwise correlations between their embedding dimensions explicitly. Extensive experimental results on three benchmark datasets demonstrate the effectiveness of our K-NCR framework. © 2020

关键词： Attention mechanism graph convolutional networks Knowledge graph Neural collaborative filtering Recommendation system

来源：评论

学校读者我要写书评

暂无评论

Recognition of Forward Head Posture Through 3D Human Pose Estimation With a graph convolutional Network: Development and Feasibility Study

引用

JMIR Formative Research 2024年 8卷 e55476页

作者： Lee, Haedeun Oh, Bumjo Kim, Seung-Chan Machine Learning Systems Laboratory School of Sports Science Sungkyunkwan University Gyunggi-do Suwon South Korea Department of Family Medicine SMG-SNU (Seoul Metropolitan Government - Seoul National University) Boramae Medical Center Seoul South Korea Department of Family Medicine Seoul National University College of Medicine Seoul South Korea

Background: Prolonged improper posture can lead to forward head posture (FHP), causing headaches, impaired respiratory function, and fatigue. This is especially relevant in sedentary scenarios, where individuals often maintain static postures for extended periods—a significant part of daily life for many. The development of a system capable of detecting FHP is crucial, as it would not only alert users to correct their posture but also serve the broader goal of contributing to public health by preventing the progression of chronic injuries associated with this condition. However, despite significant advancements in estimating human poses from standard 2D images, most computational pose models do not include measurements of the craniovertebral angle, which involves the C7 vertebra, crucial for diagnosing FHP. Objective: Accurate diagnosis of FHP typically requires dedicated devices, such as clinical postural assessments or specialized imaging equipment, but their use is impractical for continuous, real-time monitoring in everyday settings. Therefore, developing an accessible, efficient method for regular posture assessment that can be easily integrated into daily activities, providing real-time feedback, and promoting corrective action, is necessary. Methods: The system sequentially estimates 2D and 3D human anatomical key points from a provided 2D image, using the Detectron2D and VideoPose3D algorithms, respectively. It then uses a graph convolutional network (GCN), explicitly crafted to analyze the spatial configuration and alignment of the upper body’s anatomical key points in 3D space. This GCN aims to implicitly learn the intricate relationship between the estimated 3D key points and the correct posture, specifically to identify FHP. Results: The test accuracy was 78.27% when inputs included all joints corresponding to the upper body key points. The GCN model demonstrated slightly superior balanced performance across classes with an F₁-score (macro) of

关键词： algorithms deep learning forward head posture graph graph convolutional networks graph neural network human pose estimation injury prediction machine learning neural network neural networks pose postural posture posture correction upper

来源：评论

学校读者我要写书评

暂无评论

Denoising structure against adversarial attacks on graph representation learning

引用

ACM Transactions on Intelligent Systems and Technology 1000年

作者： Na Chen Ping Li Jincheng Huang Kai Zhang School of Computer Science and Software Engineering Southwest Petroleum University China School of Computer Science Southwest Petroleum University China School of Computer Science and Technology East China Normal University China

Despite their excellent performance in graph representation learning, graph convolutional networks have been proved to be vulnerable to adversarial perturbations on the connectivity between nodes in an unnoticed manner. In this work, by looking into the impacts of adversarial attacks on graph data, we empirically find that the dominant edge-addition attacks generally increase the heterophily between connected nodes, which will fool the transductive inference models on node classification task. To defend against such attacks, we develop a two-stage denoising method (TSD) that aims at removing possible malicious edges so as to mitigate the heterophily issue introduced by attacks. In particular, after a rough removal of the links that have quite low feature similarity, our method further spots the potentially heterophilious links by predicting node labels with a multi-view labeling consensus. This design is based on assumption that if the label predictions for the same node from two different views of a graph data are consistent, then we have a high chance to acquire the reliable labeling. The experiments demonstrate that by denoising a graph this way, the robustness of graph convolutional networks on node classification task is remarkably improved, compared to several strong competitive robust graph neural network models.

关键词： Adversarial Attacks Robustness graph convolutional networks Node classification

来源：评论

学校读者我要写书评

暂无评论

Maximal-Semantics-Augmented BertGCN for Text Classification

International Journal of Asian Language Processing

引用

International Journal of Asian Language Processing 2023年第2期33卷

作者： Xiaoqi Yang Wuying Liu https://***/0009-0004-9776-2294 Center for Linguistics and Applied Linguistics Guangdong University of Foreign Studies Guangzhou Guangdong 510420 P. R. China https://***/0009-0004-4641-8012 Shandong Key Laboratory of Language Resources Development and Application Ludong University Yantai Shandong 264025 P. R. China Center for Linguistics and Applied Linguistics Guangdong University of Foreign Studies Guangzhou Guangdong 510420 P. R. China

Text classification is an important research work in the field of natural language processing (NLP), and many methods of machine learning and deep learning are widely used in this work. In this paper, we propose a method namely Maximal-Semantics-Augmented BertGCN (MSABertGCN) based on BertGCN that further improves the results of text categorization tasks. In this work, the extended semantic information of text is utilized more effectively by means of text semantic enhancement and graph nodes enhancement while preserving the original text features. Four datasets commonly used in the fields of text classification, namely R8, R52, Ohsumed and MR, were used to verify the validity of the method we proposed. Experimental results show that compared with BertGCN and other baselines, the proposed method MSABertGCN has varying degrees of improvement in the accuracy with respect to the R8, R52, Ohsumed and MR datasets.

关键词： Semantics Augmented graph convolutional networks Text Classification Pre-training

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：