检索结果-内蒙古大学图书馆

An end-to-end repair-based joint training framework for weakly supervised pavement crack segmentation

Multimedia Tools and applications 2025年第16期84卷 16281-16299页

作者： Zhou, Hui Tao, Huanjie Duan, Qianyue Hu, Zhenwu Deng, Yishi School of Computer Science Northwestern Polytechnical University Xi’an710129 China School of Cyberspace Security Northwestern Polytechnical University Xi’an710129 China Engineering Research Center of Embedded System Integration Ministry of Education Xi’an710129 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an710129 China

Weakly supervised pavement crack segmentation aims to assign each pixel of pavement surface images a category label (crack or non-crack) using limited annotation information. Most existing methods adopt the multi-stage approach based on the class activation map (CAM), which outputs from a pre-trained crack classification model, to generate the pixel-level pseudo labels, and then train a segmentation model using these pseudo labels. However, these methods have two notable drawbacks: (i) CAM focuses primarily on the most discriminative regions of the image, potentially resulting in an incomplete estimation of crack regions, and (ii) the process of obtaining pixel-level pseudo labels from CAM is complex and may introduce noise. To avoid these issues, we propose an end-to-end repair-based joint training framework for weakly supervised pavement crack segmentation. Specifically, to better guide the model to pay more attention to the repair process of crack regions, we introduce the segmentation loss, which assigns different weights for crack regions and background regions, through the Residual Project Network. Additionally, to alleviate the impact of the domain gap between synthetic and real datasets, we introduce the consistency loss through the joint training paradigm of unpaired data that incorporates both crack and non-crack images into the training process simultaneously. Furthermore, to enable the model to effectively extract local features and reduce the model's computational complexity, we introduce the Lightweight Multi-head Self-attention module. The experiment results on the CRACK500 Dataset, the CFD Dataset, and the AEL Dataset demonstrate that our model achieves better performance than some existing weakly supervised pavement segmentation methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Repair

来源：评论

学校读者我要写书评

暂无评论

Earlier peak photosynthesis timing potentially escalates global wildfires

引用

National Science Review 2024年第09期11卷 171-180页

作者： Gengke Lai Jialing Li Jun Wang Chaoyang Wu Yongguang Zhang Constantin M.Zohner Josep Pe?uelas Quansheng Ge International Institute for Earth System Sciences Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing University Jiangsu Provincial Key Laboratory of Geographic Information Science and Technology Key Laboratory for Land Satellite Remote Sensing Applications of Ministry of Natural ResourcesSchool of Geography and Ocean Science Nanjing University The Key Laboratory of Land Surface Pattern and Simulation Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Huangshan National Park Ecosystem Field Scientific Observation and Research Station of the Ministry of Education Jiangsu International Joint Carbon Neutrality Laboratory Nanjing University Department of Environmental Systems Science Institute of Integrative BiologyETH Zurich CSIC Global Ecology Unit CREAF-CSIC-UAB CREAF Cerdanyola del Vallès

More intense fire weather due to climate change is implicated as a key driver of recent extreme wildfire events. As fuel stock, the role of vegetation and its phenology changes in wildfire dynamics, however is not fully appreciated. Using long-term satellite-based burned areas and photosynthesis observations, we reveal that an earlier peak photosynthesis timing(PPT) potentially acts to escalate subsequent wildfires, with an increase in the global average burned fraction of 0.021%(～2.20 Mha) for every additional day of PPT advancement. Satellite observations and Earth system modeling consistently show that this fire escalation is likely due to intensified drought conditions and increased fuel availability associated with the climate feedback arising from earlier PPT. Current fire-enabled dynamic global vegetation models can reproduce the observed negative correlation between PPT and burned area but underestimate the strength of the relationship notably. Given the continued PPT advancement owing to climate change, the bioclimatic effects of vegetation phenology change suggest a potentially pervasive upward pressure on future wildfires.

关键词： vegetation photosynthesis phenology wildfire climate feedback Earth system model

来源：评论

学校读者我要写书评

暂无评论

Substation Safety Operation Monitoring system Based on Internet of Things Technology

Substation Safety Operation Monitoring System Based on Inter...

引用

2023 Asia-Europe Conference on Electronics, Data Processing and Informatics, ACEDPI 2023

作者： Yu, Chaoyu Han, Junfei Zhang, Yifan Hu, Hongbin Wang, Yuqiang Zhang, Baoquan Yuan, Ningping Inner Mongolia Enterprise Key Laboratory of Smart Grid Simulation of Electrical Power System Inner Mongolia Power Research Institute Hohhot China Inner Mongolia Medical University School of Computer Information Hohhot China

ISBN: (纸本)9798350301151

The existing wireless technologies for substation operation safety monitoring include WiFi, RFID, ZigBee, CSS and other wireless positioning technologies, but due to poor positioning accuracy, it is difficult to meet the needs of applications. IoT technology has a variety of information sensors, powerful information collection and communication functions, and can provide advantages such as precise positioning. For a high-risk industry such as substations, it is also essential to monitor the safe operation of substations. Therefore, IoT technology is safe in substations. The application of operation monitoring has also become a research hotspot. In this paper, three positioning algorithms such as TOA, TDOA and AOA are proposed, and the positioning accuracy of TDOA is determined by the positioning accuracy measurement experiment. Therefore, TDOA can be selected for the positioning of the operator's position by the monitoring system. The information transmission function transmits the location information of the operator to the monitoring background. When the operator exceeds the safe area, the system will alarm and remind to ensure the safety of the personnel. © 2023 IEEE.

关键词： Time difference of arrival

来源：评论

学校读者我要写书评

暂无评论

HiCoCS: High Concurrency Cross-Sharding on Permissioned Blockchains

引用

IEEE Transactions on computers 2025年第07期74卷 2168-2182页

作者： Yang, Lingxiao Dong, Xuewen Wan, Zhiguo Lu, Di Zhang, Yushu Shen, Yulong Xidian University School of Computer Science and Technology China Ministry of Education Engineering Research Center of Blockchain Technology Application and Evaluation China Shaanxi Key Laboratory of Blockchain and Secure Computing Xi’an710071 China Zhejiang Lab Zhejiang Hangzhou311121 China Shaanxi Key Laboratory of Network and System Security Xi’an710071 China Jiangxi University of Finance and Economics School of Computing Nanchang330013 China Jiangxi University of Finance and Economics Nanchang330013 China

As the foundation of the Web3 trust system, blockchain technology faces increasing demands for scalability. Sharding emerges as a promising solution, but it struggles to handle highly concurrent cross-shard transactions (CSTxs), primarily due to simultaneous ledger operations on the same account. Hyperledger Fabric, a permissioned blockchain, employs multi-version concurrency control for parallel processing. Existing solutions use channels and intermediaries to achieve cross-sharding in Hyperledger Fabric. However, the conflict problem caused by highly concurrent CSTxs has not been adequately resolved. To fill this gap, we propose HiCoCS, a high concurrency cross-shard scheme for permissioned blockchains. HiCoCS creates a unique virtual sub-broker for each CSTx by introducing a composite key structure, enabling conflict-free concurrent transaction processing while reducing resource overhead. The challenge lies in managing large numbers of composite keys and mitigating intermediary privacy risks. HiCoCS utilizes virtual sub-brokers to receive and process CSTxs concurrently while maintaining a transaction pool. Batch processing is employed to merge multiple CSTxs in the pool, improving efficiency. We explore composite key reuse to reduce the number of virtual sub-brokers and lower system overhead. Privacy preservation is enhanced using homomorphic encryption. Evaluations show that HiCoCS improves cross-shard transaction throughput by 3.5-20.2 times compared to the baselines. © 1968-2012 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

A Client Selection Method Based on Loss Function Optimization for Federated Learning

引用

computer Modeling in Engineering & Sciences 2023年第10期137卷 1047-1064页

作者： Yan Zeng Siyuan Teng Tian Xiang Jilin Zhang Yuankai Mu Yongjian Ren Jian Wan School of Computer Science and Technology Hangzhou Dianzi UniversityHangzhou310018China Key Laboratory of Complex System Modeling and Simulation Ministry of EducationHangzhou310018China Zhejiang Engineering Research Center of Data Security Governance Hangzhou310018China Intelligent Robotics Research Center Zhejiang LabHangzhou311100China HDU-ITMO Joint Institute Hangzhou Dianzi UniversityHangzhou310018China

Federated learning is a distributedmachine learningmethod that can solve the increasingly serious problemof data islands and user data privacy,as it allows training data to be kept locally and not shared with other *** trains a globalmodel by aggregating locally-computedmodels of clients rather than their ***,the divergence of local models caused by data heterogeneity of different clients may lead to slow convergence of the global *** this problem,we focus on the client selection with federated learning,which can affect the convergence performance of the global model with the selected local *** propose FedChoice,a client selection method based on loss function optimization,to select appropriate local models to improve the convergence of the global *** firstly sets selected probability for clients with the value of loss function,and the client with high loss will be set higher selected probability,which can make them more likely to participate in ***,it introduces a local control vector and a global control vector to predict the local gradient direction and global gradient direction,respectively,and calculates the gradient correction vector to correct the gradient direction to reduce the cumulative deviationof the local gradient causedby *** experiments to verify the validity of FedChoice on CIFAR-10,CINIC-10,MNIST,EMNITS,and FEMNIST datasets,and the results show that the convergence of FedChoice is significantly improved,compared with FedAvg,FedProx,and FedNova.

关键词： Federated learning model aggregation Non-IID

来源：评论

学校读者我要写书评

暂无评论

Machine learning for membrane bioreactor research:principles,methods,applications,and a tutorial

引用

Frontiers of Environmental Science & Engineering 2025年第3期19卷 119-144页

作者： Yizhe Lai Kang Xiao Yifan He Xian Liu Jihua Tan Wenchao Xue Aiqian Zhang Xia Huang Beijing Yanshan Earth Critical Zone National Research Station College of Resources and EnvironmentUniversity of Chinese Academy of SciencesBeijing 101408China Key Laboratory of Earth System Numerical Modeling and Application University of Chinese Academy of SciencesBeijing 101408China Environmental Chemistry Faculty College of Resources and EnvironmentUniversity of Chinese Academy of SciencesBeijing 101408China State Key Laboratory of Environmental Chemistry and Ecotoxicology Research Center for Eco-Environmental SciencesChinese Academy of SciencesBeijing 100085China Department of Energy Environmentand Climate ChangeSchool of EnvironmentResourcesand DevelopmentAsian Institute of TechnologyP.O.Box 4Klong LuangPathumthani 12120Thailand State Key Joint Laboratory of Environment Simulation and Pollution Control School of EnvironmentTsinghua UniversityBeijing 100084China

Membrane fouling poses a significant challenge to the sustainable development of membrane bioreactor(MBR)technologies for wastewater *** accurate prediction of the membrane filtration process is of great importance for identifying and controlling *** learning methods address the limitations of traditional statistical approaches,such as low accuracy,poor generalization ability,and slow convergence,particularly in predicting complex filtration and fouling processes within the realm of big *** article provides an in-depth exposition of machine learning *** study then reviews advances in MBRs that utilize machine learning methods,including artificial neural networks(ANN),support vector machines(SVM),decision trees,and ensemble *** on current literature,this study summarizes and compares the model input and output characteristics(including foulant characteristics,solution environments,filtration conditions,operating conditions,and time factors),as well as the selection of models and optimization *** modeling procedures of SVM,random forest(RF),back propagation neural network(BPNN),long short-term memory(LSTM),and genetic algorithm-back propagation(GA-BP)methods are elucidated through a tutorial *** simulation results demonstrated that all five methods yielded accurate predictions with R2>***,the existing challenges in the implementation of machine learning models in MBRs were *** is notable that integration of deep learning,automated machine learning(AutoML)and explainable artificial intelligence(XAI)may facilitate the deployment of models in practical engineering *** insights presented here are expected to facilitate the establishment of an intelligent control framework for MBR processes in future endeavors.

关键词： Membrane bioreactor Machine learning Pollutant removal Membrane fouling Model prediction

来源：评论

学校读者我要写书评

暂无评论

An adaptive representation model for geoscience knowledge graphs considering complex spatiotemporal features and relationships

引用

Science China Earth Sciences 2023年第11期66卷 2563-2578页

作者： Yunqiang ZHU Kai SUN Shu WANG Chenghu ZHOU Feng LU Hairong LV Qinjun QIU Xinbing WANG Yanmin QI State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources ResearchChinese Academy of SciencesBeijing 100101China Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing 210023China Department of Automation Tsinghua UniversityBeijing 100084China School of Computer Science China University of GeosciencesWuhan 430074China Department of Electronic Engineering Shanghai Jiao Tong UniversityShanghai 200240China School of Computer Science University of Nottingham Ningbo ChinaNingbo 315100China

Geoscience knowledge graph(GKG)can organize various geoscience knowledge into a machine understandable and computable semantic network and is an effective way to organize geoscience knowledge and provide knowledge-related *** a result,it has gained significant attention and become a frontier in *** knowledge is derived from many disciplines and has complex spatiotemporal features and relationships of multiple scales,granularities,and ***,establishing a GKG representation model conforming to the characteristics of geoscience knowledge is the basis and premise for the construction and application of ***,existing knowledge graph representation models leverage fixed tuples that are limited in fully representing complex spatiotemporal features and *** address this issue,this paper first systematically analyzes the categorization and spatiotemporal features and relationships of geoscience *** this basis,an adaptive representation model for GKG is proposed by considering the complex spatiotemporal features and *** the constraint of a unified spatiotemporal ontology,this model adopts different tuples to adaptively represent different types of geoscience knowledge according to their spatiotemporal *** model can efficiently represent geoscience knowledge,thereby avoiding the isolation of the spatiotemporal feature representation and improving the accuracy and efficiency of geoscience knowledge *** can further enable the alignment,transformation,computation,and reasoning of spatiotemporal information through a spatiotemporal ontology.

关键词： Geoscience Knowledge graph Representation model Spatiotemporal features Spatiotemporal relationships

来源：评论

学校读者我要写书评

暂无评论

SC-GNN: A Communication-Efficient Semantic Compression for Distributed Training of GNNs 24

SC-GNN: A Communication-Efficient Semantic Compression for D...

引用

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Wang, Jihe Wu, Ying Wang, Danghui School of Computer Science Northwestern Polytechnical University Xi'an China Engineering Research Center of Embedded System Integration Ministry of Education Northwestern Polytechnical University Xi'an China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9798400706011

Training big graph neural networks (GNNs) in distributed systems is quite time-consuming mainly because of the ubiquitous aggregate operations that involve a large amount of cross-partition communication for collecting embeddings/gradients during the forward and backward propagation. To reduce the volume of the communication, some recent approaches focused on decaying each of connections via sampling, quantifying, or delaying until satisfactory trade-off are obtained between volume and accuracy. However, when applied to popular GNNs, those approaches are found to be bounded by a common volume/accuracy Pareto frontier which shows that the decaying for individual connection cannot further accelerate the aggregate of training. In this work, SC-GNN, a semantic compression of the cross-partition communication, is proposed to concentrate a group of connections as a high-level semantics and transmit to a target partition. Since carrying the overall intent of a group, the semantics can keep transferring the interactions, i.e., embeddings/gradients, between a pair of remote partitions until GNN models converge. In addition, a connection-pattern based differential optimization is proposed to further prune those weak connections, while guaranteeing the training accuracy. The results show that, for multi-field datasets, the compression rate of SC-GNN is 40.8 × higher than SOTA methods and the epoch time is reduced to 31.8% on average. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

research and Implementation of Model Engineering Environment Integration Based on OpenMBEE 21st

Research and Implementation of Model Engineering Environment...

引用

21st Asia simulation Conference, AsiaSim 2022

作者： Xue, Junjie Zhou, Junhua Shi, Guoqiang Feng, Chaoqun Xu, Lin Liu, Penghua Quan, Hongyan Engineering Research Center Beijing Simulation Center Beijing100854 China State Key Laboratory of Intelligent Manufacturing System Technology Beijing Institute of Electronic System Engineering Beijing100854 China Science and Technology on Space System Simulation Laboratory Beijing Simulation Center Beijing100854 China Yunnan Chensheng Tendering Consulting Co. Ltd. Kuming650102 China School of Computer Science and Technology East China Normal University Shanghai200062 China

ISBN: (纸本)9789811991974

Aiming at the problem of integrating open tools in a user development environment in complex product design, an integration strategy of model engineering environment based on OpenMBEE is studied. It is based on the technologies of user identity unified authentication and user interaction data collaboration. Specifically, in the solution of unified identity authentication on cross-platform, the extended controller method is provided based on the message queue information flow mechanism. Then, the separation of business logic, data information, and interactive view of user unified authentication are realized, on the basis, that the function of unified identity authentication is realized by using the Software Development Kit (SDK) of OpenMBEE. Besides, in the study of user interaction data collaboration technology, three-layer collaboration mechanisms are proposed, they are the presentation layer collaboration, the business layer collaboration, and the persistence layer collaboration. When the jQuery programming framework is integrated into the bootstrap front-end framework, combing with the OpenMBEE back-end server interface, the collaboration of user interaction data is realized. Through experiments and project practice analysis, the user unified authentication strategy and user interactive collaboration strategy are tested respectively for proving the effectiveness and feasibility of the proposed method. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

A new perspective for enhancing social and ecological systems coordination in ecological restoration

引用

生态过程（英文） 2025年第1期14卷 269-281页

作者： Guangjin Zhou Jixi Gao Riqi Zhang Zixiao Yang Siqi Zhang Lingqing Wang Yiming Su Yizhong Huan Tao Liang Satellite Application Center for Ecology and Environment Ministry of Ecology and EnvironmentBeijingChina Key Laboratory of Satellite Remote Sensing Ministry of Ecology and EnvironmentBeijingChina Institute of Land Surface System and Sustainable Development Faculty of Geographical ScienceBeijing Normal UniversityBeijingChina Satellite Application Center for Ecology and Environment Ministry of Ecology and EnvironmentBeijingChina Key Laboratory of Satellite Remote Sensing Ministry of Ecology and EnvironmentBeijingChina Centre for Environmental Policy Imperial College LondonLondonUK School of Public Policy and Manage-ment Tsinghua UniversityBeijingChina Department of Diplomacy China Foreign Affairs UniversityBeijingChina Key Laboratory of Land Surface Pat-tern and Simulation Institute of Geographic Sciences and Natural Resources ResearchChinese Academy of SciencesBeijingChina University of Chinese Academy of Sciences BeijingChina College of Humanities and Develop-ment Studies China Agricultural UniversityBeijingChina College of Inter-national Development and Global Agriculture China Agricultural UniversityBeijingChina

Background Ecosystem services(ESs)are fundamental to ensuring human well-being and sustainable ***,the complex nonlinear relationships between ESs and social systems are still not fully recognized at ***,we used a comprehensive indicator framework,a coupling coordination degree(CCD)model,and a GeoDetec-tor model to measure the CCD and development level of ESs and social systems in Sanmenxia City,Henan Prov-ince,China from 2000 to 2020,analyze the spatial patterns and temporal variations of their development,and quantify the influence of 15 factors on the spatial heterogeneity of their CCD. Results We observed that the increase of social system development level in Sanmenxia City was higher than that of ESs'provisioning *** 2000 to 2020,the ecosystem service index value of Sanmenxia City increased by about 25％,while the level of social system development increased by 118.9％.The coordination between ESs and social systems improved by 25％,indicating that their relationships were shifting from trade-offs to *** County(one of the six administrative regions of Sanmenxia City)had the highest level of CCD,but the overall coordination remained relatively weak in Sanmenxia City,and none of the six administrative regions achieved a high level of *** was influenced by multiple interacting factors,with topography and land use patterns being the primary drivers. Conclusions Optimizing the spatial layout of ecological space,agricultural space,and urban space based on natural geographic patterns can be an effective way to improve ***,we identified the impacts of potential bar-riers on sustainable development and provided multiple possible effective *** findings deepen the knowl-edge and understanding of the"human-nature relationships",which are of great significance in promoting the syner-gistic development of social and ecological systems.

关键词： Ecosystem services Coupling coordination degree Ecological restoration Sustainable development goals Sanmenxia

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

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

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：