检索结果-内蒙古大学图书馆

soft-GNN:towards robust graph neural networks via self-adaptive data utilization

Frontiers of computer science 2025年第4期19卷 1-12页

作者： Yao WU Hong HUANG Yu sONG Hai JIN National Engineering Research Center for Big Data Technology and System Service Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China College of Information and Communication National University of Defense TechnologyWuhan 430019China Department of Computer Science and Operations Research Universitéde MontréalMontreal H3C 3J7Canada

Graph neural networks(GNNs)have gained traction and have been applied to various graph-based data analysis tasks due to their high ***,a major concern is their robustness,particularly when faced with graph data that has been deliberately or accidentally polluted with *** presents a challenge in learning robust GNNs under noisy *** address this issue,we propose a novel framework called soft-GNN,which mitigates the influence of label noise by adapting the data utilized in *** approach employs a dynamic data utilization strategy that estimates adaptive weights based on prediction deviation,local deviation,and global *** better utilizing significant training samples and reducing the impact of label noise through dynamic data selection,GNNs are trained to be more *** evaluate the performance,robustness,generality,and complexity of our model on five real-world datasets,and our experimental results demonstrate the superiority of our approach over existing methods.

关键词： graph neural networks node classification label noise robustness

来源：评论

学校读者我要写书评

暂无评论

Deep learning and computer vision in plant disease detection: a comprehensive review of techniques, models, and trends in precision agriculture

引用

ARTIFICIAL INTELLIGENCE REVIEW 2025年第3期58卷 1-64页

作者： Upadhyay, Abhishek Chandel, Narendra singh singh, Krishna Pratap Chakraborty, subir Kumar Nandede, Balaji M. Kumar, Mohit subeesh, A. Upendar, Konga salem, Ali Elbeltagi, Ahmed ICAR Cent Inst Agr Engn Dept Farm Machinery & Power Engn Bhopal 462038 Madhya Pradesh India ICAR Cent Inst Agr Engn Agr Mechanizat Div Bhopal 462038 Madhya Pradesh India Indian Council Agr Res New Delhi 110001 India ICAR Cent Inst Agr Engn Technol Transfer Div Bhopal 462038 Madhya Pradesh India Southern Reg Farm Machinery Training & Testing Ins Anantapur Andhra Pradesh India Sri Karan Narendra Agr Univ Jaipur 303329 Rajasthan India Infyz Solut Hyderabad Telangana India Minia Univ Fac Engn Civil Engn Dept Al Minya Egypt Univ Pecs Fac Engn & Informat Technol Struct Diagnost & Anal Res Grp Pecs Hungary Mansoura Univ Fac Agr Agr Engn Dept Mansoura 35516 Egypt

Plant diseases cause significant damage to agriculture, leading to substantial yield losses and posing a major threat to food security. Detection, identification, quantification, and diagnosis of plant diseases are crucial parts of precision agriculture and crop protection. Modernizing agriculture and improving production efficiency are significantly affected by using computer vision technology for crop disease diagnosis. This technology is notable for its non-destructive nature, speed, real-time responsiveness, and precision. Deep learning (DL), a recent breakthrough in computer vision, has become a focal point in agricultural plant protection that can minimize the biases of manually selecting disease spot features. This study reviews the techniques and tools used for automatic disease identification, state-of-the-art DL models, and recent trends in DL-based image analysis. The techniques, performance, benefits, drawbacks, underlying frameworks, and reference datasets of more than 278 research articles were analyzed and subsequently highlighted in accordance with the architecture of computer vision and deep learning models. Key findings include the effectiveness of imaging techniques and sensors like RGB, multispectral, and hyperspectral cameras for early disease detection. researchers also evaluated various DL architectures, such as convolutional neural networks, vision transformers, generative adversarial networks, vision language models, and foundation models. Moreover, the study connects academic research with practical agricultural applications, providing guidance on the suitability of these models for production environments. This comprehensive review offers valuable insights into the current state and future directions of deep learning in plant disease detection, making it a significant resource for researchers, academicians, and practitioners in precision agriculture.

关键词： computer vision Deep learning Plant diseases detection Vision transformers Generative adversarial networks Vision language models

来源：评论

学校读者我要写书评

暂无评论

learning-based tracking control of AUV:Mixed policy improvement and game-based disturbance rejection

引用

CAAI Transactions on Intelligence Technology 2025年第2期10卷 510-528页

作者： Jun Ye Hongbo Gao Manjiang Hu Yougang Bian Qingjia Cui Xiaohui Qin Rongjun Ding State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle College of Mechanical and Vehicle EngineeringHunan UniversityChangshaChina School of Information Science and Technology and Institute of Advanced TechnologyUniversity of Science and Technology of ChinaHefeiChina Nanyang Technological University SingaporeSingapore Wuxi Intelligent Control Research Institute of Hunan University Hunan UniversityWuxiChina

A mixed adaptive dynamic programming(ADP)scheme based on zero-sum game theory is developed to address optimal control problems of autonomous underwater vehicle(AUV)systems subject to disturbances and safe *** combining prior dynamic knowledge and actual sampled data,the proposed approach effectively mitigates the defect caused by the inaccurate dynamic model and significantly improves the training speed of the ADP ***,the dataset is enriched with sufficient reference data collected based on a nominal model without considering modelling ***,the control object interacts with the real environment and continuously gathers adequate sampled data in the *** comprehensively leverage the advantages of model-based and model-free methods during training,an adaptive tuning factor is introduced based on the dataset that possesses model-referenced information and conforms to the distribution of the real-world environment,which balances the influence of model-based control law and data-driven policy gradient on the direction of policy *** a result,the proposed approach accelerates the learning speed compared to data-driven methods,concurrently also enhancing the tracking performance in comparison to model-based control ***,the optimal control problem under disturbances is formulated as a zero-sum game,and the actor-critic-disturbance framework is introduced to approximate the optimal control input,cost function,and disturbance policy,***,the convergence property of the proposed algorithm based on the value iteration method is ***,an example of AUV path following based on the improved line-of-sight guidance is presented to demonstrate the effectiveness of the proposed method.

关键词： adaptive dynamic programming autonomous underwater vehicle game theory optimal control reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Link-Quality Anomaly Detection Framework for software-Defined Wireless Mesh Networks

IEEE Transactions on Machine Learning in Communications and ...

引用

IEEE Transactions on Machine learning in Communications and Networking 2024年 2卷 495-510页

作者： skaperas, sotiris Mamatas, Lefteris Tsaoussidis, Vassilis University of Macedonia Department of Applied Informatics Thessaloniki546 36 Greece Athena Research and Innovation Center Marousi15125 Greece Democritus University of Thrace Department of Electrical and Computer Engineering Xanthi67100 Greece

software-defined wireless mesh networks are being increasingly deployed in diverse settings, such as smart cities and public Wi-Fi access infrastructures. The signal propagation and interference issues that typically characterize these environments can be handled by employing sDN controller mechanisms, effectively monitoring link quality and triggering appropriate mitigation strategies, such as adjusting link and/or routing protocols. In this paper, we propose an unsupervised machine learning (ML) online framework for link quality detection consisting of: 1) improved preprocessing clustering algorithm, based on elastic similarity measures, to efficiently characterize wireless links in terms of reliability, and 2) a novel change point (CP) detector for the real-time identification of anomalies in the quality of selected links, which minimizes the overestimation error through the incorporation of a rank-based test and a recursive max-type procedure. In this sense, considering the communication constraints of such environments, our approach minimizes the detection overhead and the inaccurate decisions caused by overestimation. The proposed detector is validated, both on its individual components and as an overall mechanism, against synthetic but also real data traces;the latter being extracted from real wireless mesh network deployments. © 2023 CCBY.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

sailfish Optimization with Deep learning based Oral Cancer Classification Model

引用

computer systems science & Engineering 2023年第4期45卷 753-767页

作者： Mesfer Al Duhayyim Areej A.Malibari sami Dhahbi Mohamed K.Nour Isra Al-Turaiki Marwa Obayya Abdullah Mohamed Department of Computer Science College of Sciences and Humanities-AflajPrince Sattam bin Abdulaziz UniversityAl-Kharj16278Saudi Arabia Department of Industrial and Systems Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Computer Science College of Science&Art at MahayilKing Khalid UniversityAbha62529Saudi Arabia Department of Computer Science College of Computing and Information SystemUmm Al-Qura UniversityMecca24382Saudi Arabia Department of Information Technology College of Computer and Information SciencesKing Saud UniversityRiyadh4545Saudi Arabia Department of Biomedical Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Research Centre Future University in EgyptNew Cairo11845Egypt

Recently,computer aided diagnosis(CAD)model becomes an effective tool for decision making in healthcare *** advances in computer vision and artificial intelligence(AI)techniques have resulted in the effective design of CAD models,which enables to detection of the existence of diseases using various imaging *** cancer(OC)has commonly occurred in head and neck *** identification of OC enables to improve survival rate and reduce mortality ***,the design of CAD model for OC detection and classification becomes ***,this study introduces a novel computer Aided Diagnosis for OC using sailfish Optimization with Fusion based Classification(CADOC-sFOFC)*** proposed CADOC-sFOFC model determines the existence of OC on the medical *** accomplish this,a fusion based feature extraction process is carried out by the use of VGGNet-16 and Residual Network(ResNet)***,feature vectors are fused and passed into the extreme learning machine(ELM)model for classification ***,sFO algorithm is utilized for effective parameter selection of the ELM model,consequently resulting in enhanced *** experimental analysis of the CADOC-sFOFC model was tested on Kaggle dataset and the results reported the betterment of the CADOC-sFOFC model over the compared methods with maximum accuracy of 98.11%.Therefore,the CADOC-sFOFC model has maximum potential as an inexpensive and non-invasive tool which supports screening process and enhances the detection efficiency.

关键词： Oral cancer computer aided diagnosis deep learning fusion model seagull optimization classification

来源：评论

学校读者我要写书评

暂无评论

computer simulation of Nanocomposite Materials with Distant Technologies and Electronic Resources for Engineering students 7

Computer Simulation of Nanocomposite Materials with Distant ...

引用

7th International Conference on Information Technologies in Engineering Education, Inforino 2024

作者： Romanova, Ksenia A. Galyametdinov, Yuriy G. Kazan National Research Technological University Physical and Colloid Chemistry Department Kazan Russia

ISBN: (纸本)9798350371369

Due to the evolution of computer technologies and theoretical approaches, simulation methods have become one of the most reliable and cost-effective instruments for the educational process and materials science, allowing one to predict the properties of materials in advance and avoid the waste of resources. This article represents the special aspects of introduction of distant technologies and electronic resources into the design and teaching of the discipline "computer simulation of nanocomposite materials"for Master's degree chemical engineering students. This discipline is a part of Master's degree program "smart materials"and available online on the learning platform Moodle. It includes educational and methodological materials, various teaching and learning tools, checkpoints, interactive tasks, crosswords, tests, interactive whiteboards, etc. specific teaching tools, simulation instruments and resources were selected for lectures, laboratory works and seminar classes, including in the case of distance learning format. Remote project tasks for distant learning require the use of electronic and Internet resources, databases and remote computing tools. Using modern software products, students learn how to select components for creating promising nanocomposite materials depending on their practical application. The study of the developed unique discipline will allow engineering students to master modern theoretical methods and techniques, which will help them in research activities and increase their competitive skills in the modern market of innovative materials and computing technologies. © 2024 IEEE.

关键词： students

来源：评论

学校读者我要写书评

暂无评论

self-supervise Reinforcement learning Method for Vacant Parking space Detection based on Task Consistency and Corrupted Rewards

引用

IEEE Transactions on Intelligent Transportation systems 2024年第2期25卷 1346-1363页

作者： Nguyen, Manh-Hung Chao, Tzu-Yin Hsiao, Ching-Chun Li, Yung-Hui Huang, Ching-Chun Hcm University of Technology and Education Faculty of Electrical Electronic Engineering Ho Chi Minh City700000 Viet Nam National Yang Ming Chiao Tung University Department of Computer Science Hsinchu300093 Taiwan Hon Hai Research Institute Ai Research Center New Taipei City114699 Taiwan

This paper proposes a novel task-consistency learning method that enables us to train a vacant space detection network (target task) based on the logic consistency with the semantic outcomes from a flow-based motion behavior classifier (source task) in a parking lot. Note that the source task can introduce false detection during task-consistency learning, which implies noisy rewards or supervision. The target network can be trained in a reinforcement learning setting by appropriately designing the reward mechanism upon semantic consistency. We also introduce a novel symmetric constraint to detect corrupted samples and reduce the effect of noisy rewards. Unlike conventional corrupted learning methods that use only training losses to identify corrupted samples, our symmetric constraint also explores the relationship among training samples to improve performance. Compared with conventional supervised detection methods, the main contribution of our work is the ability to learn a vacant space detector via semantic consistency rather than supervised labels. The dynamic learning property allows the proposed detector to be easily deployed and updated in various lots without heavy human loads. Experiments demonstrate that our noisy task consistency mechanism can be successfully applied to train a vacant space detector from scratch. © 2000-2011 IEEE.

关键词： semantics

来源：评论

学校读者我要写书评

暂无评论

Motion Control Using Brain computer Interface Utilizing GCNs-Net with BILstms 4

Motion Control Using Brain Computer Interface Utilizing GCNs...

引用

4th IEEE International Conference on Data Engineering and Communication systems, ICDECs 2024

作者： Gokulnath, s. Ponraj, Anitha Krishna, Bhargav shivaganesh sandeep Kalasalingam Academy of Research & Education Department of Computer Science and Engineering Tamilnadu Krishnan Kovil India Kalasalingam Academy of Research & Education Department of Computer Science and Engineering Tamilnadu Krishnan Kovil India

ISBN: (纸本)9798350393354

This study focuses on harnessing EEG (electroencephalogram) brain signals for motion control through a Brain-computer Interface (BCI). The research integrates advanced deep learning techniques, such as transfer learning with ResNet, for predicting and interpreting these brain signals. Additionally, the study utilizes LsTM (Long short-Term Memory) and RNN (Recurrent Neural Network) for processing time-series EEG data, enhancing the system's ability to decode the user's intended movements.A key element of the research is the application of an attention-based BiLsTM-GCN (Bidirectional Long short-Term Memory-Graph Convolutional Network) model. This model enables deep feature extraction and mining in the context of human motor imagery recognition. It empowers the system to effectively understand and respond to the user's intentions based on their EEG *** ultimate goal of this research is to create a more efficient and accurate BCI system that can recognize and interpret the user's brain signals, allowing for precise and intuitive motion control. This has the potential to revolutionize various fields, including assistive technology, neurorehabilitation, and human-computer interaction. The combination of EEG-based control and deep learning methods holds promise for enhancing the quality of life for individuals with disabilities and expanding the horizons of human-machine communication. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Cross-subcarrier precoder design for massive MIMO-OFDM downlink with symplectic optimization

引用

science China(Information sciences) 2025年第2期68卷 216-229页

作者： Yuxuan ZHANG An-An LU Xiang-Gen XIA Xiqi GAO National Mobile Communications Research Laboratory Southeast University Purple Mountain Laboratories Department of Electrical and Computer Engineering University of Delaware

We propose a cross-subcarrier precoder design(CsPD) for massive multiple-input multiple-output(MIMO) orthogonal frequency division multiplexing(OFDM) downlink. This work aims to significantly improve the channel estimation and signal detection performance by enhancing the smoothness of the frequency domain effective channel. This is accomplished by designing a few vectors known as the transform domain precoding vectors(TDPVs), which are then transformed into the frequency domain to generate the precoders for a set of subcarriers. To combat the effect of channel aging, the TDPVs are optimized under imperfect channel state information(CsI). The optimal precoder structure is derived by maximizing an upper bound of the ergodic weighted sum-rate(WsR) and utilizing the a posteriori beam-based statistical channel model(BsCM). To avoid the large-dimensional matrix inversion, we propose an algorithm with symplectic optimization. simulation results indicate that the proposed cross-subcarrier precoder design significantly outperforms conventional methods.

关键词： massive MIMO-OFDM cross subcarrier precoder design transform domain precoding vectors effective channel symplectic optimization

来源：评论

学校读者我要写书评

暂无评论

systematic Review of Brain-computer Interface-based User Authentication system: Trends, Challenges, and Directions

引用

IEEE ACCEss 2024年 12卷 96848-96861页

作者： Aldayel, Mashael Alsedairy, Nouf Al-Nafjan, Abeer Alsenan, shrooq King Saud Univ Coll Comp & Informat Sci Informat Technol Dept Riyadh 11421 Saudi Arabia King Saud Univ Coll Comp & Informat Sci Council Joint Masters Program Cyber Secur Riyadh 11421 Saudi Arabia King Abdulaziz City Sci & Technol KACST Natl Ctr Commun Syst & Command & Control Technol Riyadh 12354 Saudi Arabia Imam Mohammad Ibn Saud Islamic Univ IMSIU Coll Comp & Informat Sci Comp Sci Dept Riyadh 11564 Saudi Arabia Princess Nourah Bint Abdulrahman Univ Coll Comp & Informat Sci Informat Syst Dept POB 84428 Riyadh 11671 Saudi Arabia

The authentication process plays a crucial role in ensuring accurate and high-level security in various applications, particularly in the face of emerging technologies and the growing threat of unauthorized access. Through a comprehensive review of previous studies on brain-computer interface (BCI)-based authentication, we have identified it as a secure and promising solution, harnessing the unique characteristics of brainwaves. The main objective of this research is to systematically categorized the literature based on modality, authentication type, BCI paradigm, stimuli and signals types, computational and machine learning methods, databases, and BCI devices. We used the preferred reporting items for systematic reviews and meta-analyses (PRIsMA2020) model in conducting this review. We extracted detailed information from previous studies to gain a deeper understanding of the advancements, challenges, potential applications BCI-based authentication systems. We classified the challenges encountered by BCI systems into three categories: technological, user related, and implementation and suggested the future research directions for each of them. In this study, we presented a systematic literature review the field of BCI-based authentication to provide researchers and practitioners with a comprehensive overview of the advancements, trends, challenges, and future directions in this area.

关键词： Authentication Electroencephalography Reviews Biometrics (access control) systematics Databases Brain modeling Brain-computer interfaces authentication identification machine learning signal processing

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：