检索结果-内蒙古大学图书馆

IEEE International Symposium on Biomedical Imaging

作者： Mingyue Zhao Xiaolan Qiu S.Kevin Zhou Division of Life Sciences and Medicine School of Biomedical Engineering University of Science and Technology of China (USTC) China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) Suzhou Institute for Advance Research USTC China Suzhou Key Laboratory of Microwave Imaging Processing and Application Technology Suzhou Aerospace Information Research Institute China Key Laboratory of Precision and Intelligent Chemistry University of Science and Technology of China (USTC) China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology China

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Airway extraction is paramount in the early diagnosis and treatment of respiratory diseases. As a tree-like structure, both topological-aware learning and voxel-wise classification are equally crucial for the airway. However, existing methods demonstrate insufficient topological learning, emphasizing only the supervision of individual key topological points. Consequently, this paper proposes a Explicit Topological Modeling (ExpTopo) approach to aid airway segmentation. It explicitly introduces topological metric space learning based on semantic segmentation, enhancing the model's structural perception by implementing global skeleton-level sparse topological learning (STL) and local voxel-level dense topological perception (DTP). Extensive experimental results demonstrate that the algorithm achieves competitive performance at both the topological and voxel levels. Code will be available in https://***/MorineZ/ExpTopo.

关键词： Codes Atmospheric modeling Semantic segmentation Pulmonary diseases Biological system modeling Extraterrestrial measurements Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Dong, Xuewen Li, Jiachen Li, Shujun You, Zhichao Qu, Qiang Kholodov, Yaroslav Shen, Yulong The School of Computer Science and Technology Xidian University The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education China The Shaanxi Key Laboratory of Blockchain and Secure Computing Xi’an710071 China The School of Computing Kent Interdisciplinary Research Centre in Cyber Security University of Kent CanterburyCT2 7NF United Kingdom Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China The Intelligent Transportation Systems Lab Innopolis University Innopolis Russia The School of Computer Science and Technology Xidian University China

Recent studies show that graph neural networks (GNNs) are vulnerable to backdoor attacks. Existing backdoor attacks against GNNs use fixed-pattern triggers and lack reasonable trigger constraints, overlooking individual graph characteristics and rendering insufficient evasiveness. To tackle the above issues, we propose ABARC, the first Adaptive Backdoor Attack with Reasonable Constraints, applying to both graph-level and node-level tasks in GNNs. For graph-level tasks, we propose a subgraph backdoor attack independent of the graph’s topology. It dynamically selects trigger nodes for each target graph and modifies node features with constraints based on graph similarity, feature range, and feature type. For node-level tasks, our attack begins with an analysis of node features, followed by selecting and modifying trigger features, which are then constrained by node similarity, feature range, and feature type. Furthermore, an adaptive edge-pruning mechanism is designed to reduce the impact of neighbors on target nodes, ensuring a high attack success rate (ASR). Experimental results show that even with reasonable constraints for attack evasiveness, our attack achieves a high ASR while incurring a marginal clean accuracy drop (CAD). When combined with the state-of-the-art defense randomized smoothing (RS) method, our attack maintains an ASR over 94%, surpassing existing attacks by more than 7%. © 2004-2012 IEEE. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

applications of Acoustic Emission Monitoring in Grinding: A Review

引用

International Journal of Precision engineering and Manufacturing - Green technology 2025年 1-26页

作者： Jia, Jianfei Guo, Bing Krajnik, Peter Gu, Yan Wu, Guicheng Yao, Honghui Zhao, Huan Li, Kenan Yang, Wei Zhao, Qingliang Center for Precision Engineering School of Mechatronics Engineering Harbin Institute of Technology P.O. Box 413 Harbin 150001 China Department of Industrial and Materials Science Chalmers University of Technology Gothenburg Sweden Chongqing Research Institute Harbin Institute of Technology Chongqing 401120 China Sichuan Aerospace Fenghuo Servo Control Technology Co. Ltd Chengdu 611130 China Zhongshan Sprecision Technology Co. Ltd Zhongshan 528437 China State Key Laboratory of Intelligent Manufacturing Equipment and Technology School of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan 430074 China State Key Laboratory for High Performance Tools Zhengzhou Abrasive Grinding Research Institute Co. Ltd Henan 450001 China

Grinding is typically the final operation in many manufacturing chains owing to its ability to achieve high surface quality. However, any failure in this process can lead to irreparable damage to the workpiece and increased costs. Reliable, online, and onsite monitoring techniques must be implemented to avoid these problems. Over the past decades, various technologies have been developed to monitor grinding processes, utilizing a range of signals. Among these, acoustic emission (AE) has demonstrated significant advantages, including high sensitivity to fine dynamic interactions between the grinding wheel and workpiece, as well as excellent performance in filtering mechanical noise. Consequently, AE is widely recognized as one of the most effective monitoring and detection methods in grinding. However, comprehensive literature reviews on AE monitoring in grinding remain scarce. This paper provides an overview of the history and sources of AE monitoring in grinding. Subsequently, it outlines the process of AE monitoring in grinding and introduces different methods applied in AE monitoring. Lastly, research gaps and future trends for the applications of AE monitoring in grinding are highlighted. Overall, this paper systematically summarizes the monitoring system, analysis methods, and practical applications of AE in grinding, while also identifying knowledge gaps and scope for future work. © The Author(s), under exclusive licence to Korean Society for Precision engineering 2025.

关键词： Acoustic emission Grinding Monitoring

来源：评论

学校读者我要写书评

暂无评论

The spindle running laws in the continuous braiding of multi-jointed tubular truss preforms

引用

Journal of Reinforced Plastics and Composites 2025年

作者： Wang, Shenghang Ma, Wensuo Ma, Huijie Xu, Yonghao Ma, Zhenyu Huang, Zhaohua Yang, Liguang School of Mechatronics Engineering Henan University of Science and Technology Luoyang China College of Automobile and Traffic Engineering Nanjing Forestry University Jiangsu China Longmen Laboratory Intelligent Manufacturing Fundamental Research Center Luoyang China Sinomach Precision Industry Group Co. Ltd Zhengzhou China

High-performance fiber-braided composite tubular truss structures have been widely used in satellites due to their advantages, such as lightweight and thermal stability. The continuous braiding of yarns in a multi-jointed truss preform is challenging because of the complexity of its joint structure. To realize the preform continuous braiding process with a constant number of yarns at the truss joints, a mathematical model for the spindle motion trajectory was developed by intermittently segmenting the spindle track. Based on the model, the relationship between the number of braiding spindles and the trajectory units in the segmented track, and the running laws of the spindles was analyzed. The results revealed that interference consistently existed between the spindles after segmenting the track based on the tubular braided track. A supplementary structural design method was proposed, based on the original track of the Maypole braiding equipment, which enables the spindles to run without interference in the segmented track. The research provides a theoretical foundation for designing the equipment used in the continuous processing of multi-joint truss tubular preforms. © The Author(s) 2025.

关键词： Preforming

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Augmented Reality Using Human-Computer Interaction Models

引用

Journal of Control and Decision 2024年第1期11卷 1-14页

作者： Ying Sun Qiongqiong Guo Shumei Zhao Karthik Chandran G.Fathima Henan intelligent education and intelligent technology application engineering technology research center Zhengzhou Railway Vocational and technical collegeZhengzhouHenanPeople’s Republic of China Henan Provincial Research Center of Wisdom Education and Intelligent Technology Application Engineering Technology Zhengzhou Railway Vocational and technical collegeZhengzhouHenanPeople’s Republic of China Department of Mechatronics Engineering Jyothi Engineering CollegeKeralaIndia CSE Adhiyamaan College of Engineering HosurTamilnaduIndia

Augmented Reality is a technique that allows users to overlap digital information with their physical *** Augmented Reality(AR)displays have an exceptional characteristic from the Human–Computer Interaction(HCI)*** to its increasing popularity and application in diverse domains,increasing user-friendliness and AR usage are ***-aware is one approach since an AR application can adapt to the user,environment,needs and enhance ergonomic principles and *** paper proposes the intelligent Contextaware Augmented Reality Model(ICAARM)for Human–Computer Interaction *** study explores and reduces interaction uncertainty by semantically modeling user-specific interaction with context,allowing personalised *** information is captured from an AR device to understand user interactions and *** depictions carry semantics to Augmented Reality applications about the user’s intention to interact with a specific device ***,this study describes personalised gesture interaction in VR/AR applications for immersive/intelligent environments.

关键词： Augmented Reality Context-aware Human–Computer Interaction

来源：评论

学校读者我要写书评

暂无评论

Provably Secure Authenticated Key-Management Mechanism for e-Healthcare Environment

引用

IEEE Internet of Things Journal 2025年

作者： Saleem, Muhammad Asad Li, Xiong Mahmood, Khalid Ghaffar, Zahid Xie, Yong Wang, Guijuan University of Electronic Science and Technology of China School of Computer Science and Engineering Sichuan Chengdu611731 China National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Yunlin Douliu64002 Taiwan National Yunlin University of Science and Technology Graduate School of Engineering Science and Technology Douliu64002 Taiwan Qinghai Institute of Technology School of Computer and Information Science China Qinghai Provincial Laboratory for Intelligent Computing and Application China Key Laboratory of Computing Power Network and Information Security Jinan250353 China Shandong Provincial Key Laboratory of Industrial Network and Information System Security China Shandong Fundamental Research Center for Computer Science Jinan250353 China

The Internet of Things (IoT) is rapidly permeating all aspects of human life, involving a network of devices that share sensitive data. A notable application is the e-healthcare systems, which employ connected sensors, medical servers, and wearable devices. However, the public nature of communication in e-healthcare systems poses challenges such as security, privacy, and authentication of participating entities. Recently, many authentication protocols have been introduced to address these challenges. However, most of these protocols remain vulnerable to various security attacks, including device or medical server impersonation, denial of service, physical or cloning, and de-synchronization attacks. Therefore, we introduce an authenticated key-management protocol utilizing hash functions and Cipher-Block Chaining-Advanced Encryption Standard encryption (CBC-AES) encryption. The proposed protocol also employs the Physical Unclonable Function (PUF), which makes it more robust and efficient in resisting physical or cloning attacks. Additionally, the proposed scheme resists various security threats, including impersonation, session key leakage, ephemeral secret leakage, and de-synchronization attacks. We analyze the scheme’s security and reliability through formal and informal analysis. The informal analysis demonstrates that the scheme encompasses crucial security features, while the formal analysis substantiates. Moreover, performance analysis of the proposed protocol with various competing results indicates that our protocol achieves an average reduction in communication and computation overheads by 36.03.% and 41.79%, respectively. © 2014 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Joint extraction method for entity relations from mineral resources reports integrating dependency parsing and improved graph convolutional networks

引用

Ore Geology Reviews 2025年 182卷

作者： Qiu, Qinjun Jin, Xiangguo Tian, Miao Wu, Qirui Tao, Liufeng Chen, Jianguo Xie, Zhong Technology Innovation Center for Geological Data Intelligent Application Department of Natural Resources of Jiangsu Province 210012 China School of Computer and Science China University of Geosciences Hubei Wuhan430074 China National Engineering Research Center for Geographic Information System Hubei Wuhan430074 China Key Laboratory of Geological Survery and Evaluation of Ministry of Education Hubei Wuhan430074 China School of Future Technology China University of Geosciences Hubei Wuhan430074 China Wuhan University Hubei Wuhan430074 China

Geological reports, as crucial technical documents reflecting the outcomes of geological survey work, encapsulate extensive expert and domain knowledge. Geological knowledge graphs integrate vast amounts of data, facilitating efficient and rapid extraction of knowledge embedded within geoscientific data. The extraction of geological entity relations is a key method in creating these knowledge graphs. Existing techniques for extracting geological entities and their relations encounter difficulties such entity overlap, relation overlap, and the challenge of obtaining deep semantic information because of the vastness and complexity of geological data. Our study suggests a collaborative extraction model for entity relations that integrates dependency syntactic relations with a graph convolutional network (GCN) in order to address these problems. This model learns dependency syntactic structures and deep semantic information by building a GCN that includes dependency syntactic relations. A pointer network decoder is then added to increase entity relation extraction efficiency. Dependencies between words in a phrase, such as subject-verb and verb-object relations, are revealed via dependency syntactic analysis. By structuring these dependencies into a graph, the model captures syntactic structural information. Through operations involving adjacency matrices and feature matrices, the model effectively propagates and aggregates node information, thereby capturing the global dependency syntactic structure and deep semantic information of sentences. The integration of dependency syntactic relations with GCN processing enables the model to more accurately comprehend entity relations within sentences. Results from experiments show that this model successfully tackles problems like overlapping entity relations and the challenge of gleaning deep semantic information from geological texts. It achieves a 79.73% accuracy rate and a 77.98% F1 score on geological text datasets. © 2025

关键词： Geochemical surveys

来源：评论

学校读者我要写书评

暂无评论

Hydrogen production prediction from Co-gasification of biomass and plastics using attention-gated MLP model

引用

Renewable Energy 2025年 249卷

作者： Ukwuoma, Chiagoziem C. Cai, Dongsheng Bamisile, Olusola Bizi, Antonio M. Amos, Toluwani Joan Delali, Fiasam Linda Thomas, Dara Huang, Qi College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan P.R. 610059 China Sichuan Engineering Technology Research Center for Industrial Internet Intelligent Monitoring and Application Chengdu University of Technology Sichuan P.R. 610059 China OBU Sino-British Collaborative Education Chengdu University of Technology Sichuan P.R. 610059 China School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Sichuan P.R. 610059 China School of Life Science and Technology University of Electronic Science and Technology of China Sichuan P.R. 610059 China School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan P.R. 610059 China School of Business Administration Sichuan University Sichuan P.R. 610059 China

research explores combining plastics and biowastes to decrease carbon footprints in the cement, iron, and steel industries. Co-gasification of these materials cuts carbon and converts it into hydrogen and syngas. The escalating demand for alternative energy sources has driven significant interest in hydrogen as a clean and efficient fuel. However, accurate prediction techniques are indispensable for ensuring the viability and sustainability of hydrogen production processes. While artificial intelligence models have shown promise in various fields, including computer vision and hydrogen prediction, they often encounter limitations such as low prediction accuracy with few data samples, lack of interpretability in yield result explanations, and susceptibility to adversarial attacks. Addressing these challenges is critical for advancing the reliability and applicability of hydrogen production prediction models. This study presents an attention-gated MLP model (agMLP). This novel end-to-end approach integrates MLP and attention mechanisms to enhance the accuracy and interpretability of hydrogen production prediction from the co-gasification of biomass and plastics. Furthermore, several explainable AI models were implemented to explain the proposed agMLP prediction for human understanding while using the Williams plot to indicate the applicability of the proposed agMLP. Further analysis was carried out using the Fast Gradient Sign Method and Projected Gradient Descent adversarial attack on the proposed agMLP model based on 0.2, 0.4, 0.6, and 0.8 perturbation to establish the associated risk of artificial intelligence model prediction via adversarial attack. Lastly, to compare the result of the agMLP model, nine (9) machine learning regression models and three ensemble models were developed and evaluated. The implemented model's performance was assessed using various evaluation metrics, including Mean Absolute, Mean Squared, Root Mean Squared, Root Mean Squared Logarithmic

关键词： Iron and steel industry

来源：评论

学校读者我要写书评

暂无评论

EPS mortar-filling technique to improve explosive-resistance of pultruded GFRP sandwich panels

引用

Construction and Building Materials 2025年 477卷

作者： Li, Sensen Zhang, Bei He, Huguang Wang, He Fan, Hualin Department of Civil Engineering Nanyang Institute of Technology Nanyang473004 China Henan International Joint Laboratory of Dynamics of Impact and Disaster of Engineering Structures Nanyang473004 China Institute of Defense Engineering AMS PLA Beijing100850 China State Key Laboratory for Disaster Prevention & Mitigation of Explosion & Impact Army Engineering University of PLA Nanjing210007 China College of Civil and Architectural Engineering Guangxi University of Science and Technology Liuzhou545006 China Research center of Lightweight Structures and Intelligent Manufacturing State Key Laboratory of Mechanics and Control of Aerospace Structures Nanjing University of Aeronautics and Astronautics Nanjing210016 China

Glass fiber reinforced plastic (GFRP) pultruded sandwich panels (PSPs) are lightweight and low-cost structures with relatively high bending strength, but their flexural performance is limited by the weak shear strength. The mechanical properties of the PSPs can be effectively improved by filling expanded polystyrene (EPS) mortar. In this paper, EPS foam-filled pultruded GFRP sandwich panels (GFRP-EPS sandwich panels) were designed and prepared. The dynamic responses and failure patterns of the GFRP-EPS sandwich panels were revealed based on the close-in explosion testing. Through the quasi-static three-point bending experiments, the residual load bearing capacity of the GFRP-EPS sandwich panels was evaluated, which can reveal the damage degree of the exploded panels. The explosion resistance of the GFRP-EPS sandwich panels is greatly improved compared with that of the unfilled GFRP PSPs. Based on the equivalent static load method, the critical scaled distance of panels P1 and P2 is 1.275 m/kg1/3 and 1.095 m/kg1/3, respectively, providing a design basis for the application of the GFRP-EPS sandwich panel. © 2025

关键词： Mortar

来源：评论

学校读者我要写书评

暂无评论

Long and Recent Preference Learning with Recent-k Items Distribution for Recommender System

引用

IEEE Transactions on Multimedia 2025年

作者： Gao, Yongbiao Niu, Sijie Lv, Guohua Ling, Miaogen Geng, Xin Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan China Southeast University Ministry of Education Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Application China University of Jinan Shandong Provincial Key Laboratory of Ubiquitous Intelligent Computing School of Information Science and Engineering China Nanjing University of Information Science and Technology School of Computer Science China Southeast University School of Computer Science and Engineering China

Reinforcement learning (RL) aims to formulate the recommendation task as a Markov decision process (MDP) and trains an agent to automatically learn the optimal recommendation policy from interaction trajectories through trial-and-error and reward mechanisms. However, most existing RL-based approaches overlook the correlation between items and the dynamics of user interests implied in temporally close interactions. Therefore, in this paper, we propose a reinforcement learning method that incorporates a "recent-k items"distribution to capture users' local preferences. Specifically, we model the output layer as two distinct branches. The "recent-k items"branch, formulated with a Kullback-Leibler divergence loss, learns the recent interests of users, whereas the other branch utilizes a one-step temporal difference error to capture long-term preferences. The proposed structure is integrated into deep Q-learning and actor-critics, resulting in two enhanced methods named R k Q and R k AC, respectively. Furthermore, a novel soft inter-reward is carefully designed to enhance the proposed method, and we theoretically prove the convergence of the proposed algorithm. We perform extensive experiments on two large real-world datasets and conduct further analysis of the influences of different action sequences, time intervals, and enhancement capabilities for state-of-the-art models. The experimental results demonstrate the efficacy of our proposed methods. © 1999-2012 IEEE.

关键词： Deep reinforcement learning

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：