检索结果-内蒙古大学图书馆

Multi-Scale Feature Fusion and Advanced Representation Learning for Multi Label Image Classification

Computers, Materials & Continua 2025年第3期82卷 5285-5306页

作者： Naikang Zhong Xiao Lin Wen Du Jin Shi Institute of Artificial Intelligence on Education Research College of InformationMechanical and Electrical EngineeringShanghai Normal UniversityShanghai200234China Lab for Educational Big Data and Policymaking Ministry of EducationShanghai Normal UniversityShanghai200234China Shanghai Intelligent Education Big Data Engineering Technology Research Center Shanghai Normal UniversityShanghai200234China Shanghai Online Education Research Base for Primary and Secondary Schools Shanghai200234China DS Information Technology Co. Ltd.Shanghai200032China Faculty of Innovation Engineering Macao university of Science and TechnologyMacao999078China

Multi-label image classification is a challenging task due to the diverse sizes and complex backgrounds of objects in *** class-specific precise representations at different scales is a key aspect of feature ***,existing methods often rely on the single-scale deep feature,neglecting shallow and deeper layer features,which poses challenges when predicting objects of varying scales within the same *** some studies have explored multi-scale features,they rarely address the flow of information between scales or efficiently obtain class-specific precise representations for features at different *** address these issues,we propose a two-stage,three-branch Transformer-based *** first stage incorporates multi-scale image feature extraction and hierarchical scale *** design enables the model to consider objects at various scales while enhancing the flow of information across different feature scales,improving the model’s generalization to diverse object *** second stage includes a global feature enhancement module and a region selection *** global feature enhancement module strengthens interconnections between different image regions,mitigating the issue of incomplete represen-tations,while the region selection module models the cross-modal relationships between image features and ***,these components enable the efficient acquisition of class-specific precise feature *** experiments on public datasets,including COCO2014,VOC2007,and VOC2012,demonstrate the effectiveness of our proposed *** approach achieves consistent performance gains of 0.3%,0.4%,and 0.2%over state-of-the-art methods on the three datasets,*** results validate the reliability and superiority of our approach for multi-label image classification.

关键词： Image classification multi-label multi scale attention mechanisms feature fusion

来源：评论

学校读者我要写书评

暂无评论

MC-2PF: a Multi-edge Cooperative Universal Framework for Load Prediction with Personalized Federated Deep Learning

引用

IEEE Transactions on Mobile Computing 2025年第6期24卷 5138-5154页

作者： Chen, Zheyi Jiang, Qingnan Chen, Lixian Chen, Xing Li, Jie Min, Geyong Fuzhou University College of Computer and Data Science Fuzhou350116 China Ministry of Education Engineering Research Center of Big Data Intelligence Fuzhou350002 China Fuzhou350116 China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200240 China University of Exeter Faculty of Environment Science and Economy Department of Computer Science ExeterEX4 4QF United Kingdom

The emerging load prediction techniques support up-front and rational resource provisioning in edge systems to enhance system efficiency and Quality-of-Service (QoS). Classic prediction methods may handle loads with apparent trends, but they cannot achieve accurate prediction for highly-variable edge loads. With the advantage of sequential data analysis, recurrent neural networks (RNNs) are often used for load prediction but reveal limited generalization ability and low training efficiency. Moreover, it is hard to obtain a well-performed prediction model by discrete single-edge training with insufficient historical data. To address these important challenges, we propose a novel Multi-edge Cooperative universal framework for load Prediction with Personalized Federated deep learning (MC-2PF), enabling multi-edge cooperative training of load prediction models. Specifically, to solve the client-drift issue in federated learning (FL) caused by distinct data distribution, we customize personalized models for each edge by independent control parameters and theoretically analyze the model convergence improvement. Meanwhile, we prove the generalization bound of the MC2PF and its universality to RNN-based prediction models through a practical example. Using the real-world testbed and load datasets, extensive experiments verify the effectiveness and practicality of the MC-2PF for different RNN-based prediction models. Compared to state-of-the-art frameworks, the MC-2PF achieves higher prediction accuracy, faster convergence, and stronger adaptiveness. © 2002-2012 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Improving service accessibility and equity for sustainable development goals without newly facilities by rural settlement reconstruction

引用

Geography and Sustainability 2025年第1期6卷 105-117页

作者： Caihui Cui Zhigang Han Feng Liu Jingru Ma Haiying Wang Xiang Chen College of Geographical Sciences Faculty of Geographical Science and EngineeringHenan UniversityZhengzhou 450046China College of Remote Sensing and Geoinformatics Engineering Faculty of Geographical Science and EngineeringHenan UniversityZhengzhou 450046China Henan Industrial Technology Academy of Spatiotemporal Big Data Henan UniversityZhengzhou 450046China Henan Technology Innovation Center of Spatio-Temporal Big Data Henan UniversityZhengzhou 450046China Key Research Institute of Yellow River Civilization and Sustainable Development Henan UniversityKaifeng 475004China Department of Geography University of ConnecticutStorrsCT 06269USA

Ensuring the provision of accessible,affordable,and high-quality public services to all individuals aligns with one of the paramount aims of the United Nations’Sustainable Development Goals(SDGs).In the face of esca lating urbanization and a dwindling rural populace in China,reconstructing rural settlements to enhance public service accessibility has become a fundamental strategy for achieving the SDGs in rural ***,few stud ies have examined the optimal methods for rural settlement reconstruction that ensure accessible and equitable public services while considering multiple existing facilities and service *** paper focuses on rural settlement reconstruction in the context of the SDGs,employing an inverted MCLP-CC(maximal coverage loca tion problem for complementary coverage)model to identify optimal rural settlements and a rank-based method for their *** in Changyuan,a county-level city in Henan Province,China,this study observed significant enhancements in both accessibility and equity following rural settlement reconstruction by utilizing the MH3SFCA(modified Huff 3-step floating catchment area)and the spatial Lorenz curve ***,these improvements were achieved without the addition of new facilities,with the accessibility increasing by 44.21%,4.97%,and 3.11%;Gini coefficients decreasing by 19.53%,1.64%,and 3.18%;Ricci-Schutz coef-ficients decreasing by 21.09%,2.09%,and 4.33%for educational,medical,and cultural and sports facilities,*** indicated that rural settlement reconstruction can bolster the accessibility and equity of public ser-vices by leveraging existing *** paper provides a new framework for stakeholders to better reconstruct rural settlements and promote sustainable development in rural areas in China.

关键词： SDGs Equity Accessibility Rural settlement reconstruction Spatial optimization

来源：评论

学校读者我要写书评

暂无评论

Electrochemical dissolution, reduction, and nucleation mechanisms of molybdenum in NaCl-KCl molten salt systems

引用

Journal of Materials Science and Technology 2025年 238卷 45-54页

作者： Lv, Hongzhan Zhang, Liwen Xi, Xiaoli Nie, Zuoren Collaborative Innovation Center of Capital Resource-Recycling Material Technology Beijing University of Technology Beijing100124 China Key Laboratory of Advanced Functional Materials Ministry of Education Faculty of Materials and Manufacturing Beijing University of Technology Beijing100124 China National Engineering Laboratory for Industrial Big-data Application Technology Beijing University of Technology Beijing100124 China

This study investigates the anodic dissolution and electrochemical behavior of molybdenum in a NaCl-KCl molten salt system at 1023 K. The anodic dissolution process was systematically analyzed, revealing a sequential oxidation pathway of molybdenum into high-valence ions (Mo6+, Mo5+, Mo4+) under varying electrolysis potentials. Electrochemical Impedance Spectroscopy (EIS) demonstrated that the dissolution is governed by both charge transfer and diffusion mechanisms, with reduced impedance at higher potentials facilitating molybdenum dissolution. The reduction behavior of dissolved molybdenum ions was further explored using cyclic voltammetry (CV) and square wave voltammetry (SWV), confirming a multi-step reduction process controlled by diffusion and high reversibility. Nucleation studies using chronoamperometry established that molybdenum deposition follows an instantaneous nucleation mechanism. Morphological analysis of cathodic deposits revealed that current density significantly influences particle size, transitioning from nano-sized spherical particles to larger equiaxed crystals with increasing current density. These findings provide a comprehensive understanding of molybdenum's electrochemical properties in molten salts, offering valuable insights for optimizing electrolysis processes and advancing molybdenum-based material production. © 2025

关键词： Cyclic voltammetry

来源：评论

学校读者我要写书评

暂无评论

Automated Generation of Challenge Questions for Student Code Evaluation Using Abstract Syntax Tree Embeddings and RAG: An Exploratory Study 24

Automated Generation of Challenge Questions for Student Code...

引用

7th International Conference on Educational Technology Management, ICETM 2024

作者： Boubaker, Anis Fang, Ying General Education Department Ecole de Technologie Superieure MontrealQC Canada Faculty of Artificial Intelligence in Education Central China Normal University Hubei Wuhan China National Engineering Research Center of Educational Big Data Central China Normal University Hubei Wuhan China

ISBN: (纸本)9798400717468

This paper presents an exploratory study on detecting learning gaps in student-submitted code by generating automated challenge questions. The proposed method compares the abstract syntax trees (ASTs) of student code with those of class-taught examples using embeddings and retrieval-augmented generation (RAG). The approach identifies the most structurally deviant sections of student code and generates challenge questions targeting advanced, untaught coding techniques, such as function pointers and variadic functions. The evaluation, conducted on real-world C programming assignments, demonstrates the effectiveness of the selection process and the quality of generated questions. This work highlights the potential for using structural analysis and automated challenge questions generation to improve student assessment in coding education. © 2024 Copyright held by the owner/author(s).

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

A capability maturity model for smart city process-aware digital transformation

引用

Journal of Urban Management 2025年

作者： Ajoudanian, Shohreh Aboutalebi, Hamid Reza Faculty of Computer Engineering Najafabad Branch Islamic Azad University Najafabad Iran Big Data Research Center Najafabad Branch Islamic Azad University Najafabad Iran

Smart cities are constructed and developed by governmental bodies and urban leaders capable of digital transformation. This modification aims to mitigate urban challenges while fostering robust urban growth using advanced technologies. However, many existing maturity models fail to adequately address the specific requirements and gaps in digital transformation capabilities necessary for effective urban management. The implementation of information and innovative communication strategies in urban areas has led to the development of new organizational procedures and business models. City managers recognize that digital transformation can drive urban growth. Therefore, they can enhance their processes by following a clear strategy outlined in a digital transformation capability maturity model. Despite the growing emphasis on digital transformation in urban management, existing maturity models do not adequately capture the specific processes and requirements necessary for effective implementation, resulting in challenges for city managers in assessing their capabilities. For this purpose, this study evaluates smart city maturity models and identifies gaps in the requirements for digital transformation capability. As a result, an innovative model for assessing the maturity of digital transformation capability in smart cities is proposed. The presented maturity model is particularly helpful for businesses and private companies seeking to embrace digital transformation for urban growth. It facilitates their systematic advancement toward higher maturity levels by enabling them to assess current capabilities. The majority of assessors are either very satisfied or satisfied with the criteria, according to the SC-DT-CMM evaluation results. © 2025 The Authors

关键词： Capability maturity model Digital transformation Smart city Smart city maturity model Urban management

来源：评论

学校读者我要写书评

暂无评论

Dynamic scheduling of independent tasks in cloud computing environment applying improved chicken swarm optimization and differential evolution

引用

The Journal of Supercomputing 2025年第8期81卷 1-63页

作者： Safi-Esfahani, Faramarz Larian, Habib Saeedi Mobarakeh, Saeed Mirjalili, Seyedali School of Information Systems and Modelling Faculty of Engineering and IT University of Technology Sydney Sydney Australia Faculty of Computer Engineering Najafabad Branch Islamic Azad University Najafabad Iran Big Data Research Center Najafabad Branch Islamic Azad University Najafabad Iran Centre for Artificial Intelligence Research and Optimisation Torrens University Australia Brisbane Australia University Research and Innovation Center Obuda University Budapest Hungary

Cloud computing dynamically allocates computational resources to meet user demands, but task scheduling remains an NP-hard optimization problem due to multiple constraints such as task dependencies, execution time, and resource allocation. Metaheuristic algorithms have been widely used to tackle these challenges, yet existing approaches often suffer from premature convergence, poor exploration–exploitation balance, and inefficiencies in high-dimensional search spaces. To overcome these limitations, this study proposes an Improved Chicken Swarm Optimization with Differential Evolution (ICSODE), which integrates chaos-based adaptive parameter tuning to dynamically adjust the learning coefficient C for better convergence and Differential Evolution (DE)–based mutation and recombination to enhance population diversity and global search efficiency. A Dynamic Scheduling Framework (***) is also introduced, leveraging ICSODE to efficiently allocate independent tasks to virtual machines (VMs) in a cloud computing environment. The proposed ICSODE algorithm is first evaluated on CEC2017 benchmark functions, demonstrating superior mean error reduction compared to CSO, ICSO, ICSOCrossover, ICSOChaotic, and DE. In the second phase, ICSODE is applied within the *** scheduling framework and tested on the NASA-iPSC parallel workload dataset, where it significantly reduces execution time by an average of 15.36% and improves response time by an average of 38.65%. Experimental results confirm that ICSODE outperforms existing CSO variants and DE in both function optimization and dynamic task scheduling, establishing it as a highly effective solution for cloud-based scheduling challenges.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spatio-temporal Dynamics and Drivers of Ecological Quality in Yulin City Using the MRSEI Model

引用

Journal of Resources and Ecology 2025年第2期16卷 340-355页

作者： MU Weichen HE Zhilin CHEN Yanglong GAO Dongkai YUE Tianming QIN Fen College of Geographical Sciences Faculty of Geographical Science and EngineeringHenan UniversityZhengzhou450046China Key Laboratory of Geospatial Technology for the Middle and Lower Yellow River Regions Ministry of EducationHenan UniversityKaifengHenan 475004China Henan Industrial Technology Academy of Spatio-Temporal Big Data Henan UniversityKaifengHenan 475004China Henan Technology Innovation Center of Spatial-Temporal Big Data Henan UniversityZhengzhou 450046China.

Urbanization has resulted in growing ecological pressures on cities,necessitating assessments of urban ecological ***-term characterization of regional dynamics and drivers is critical for environmental *** study proposes an enhanced ecological quality model(MRSEI)incorporating vegetation cover and EVI rather than just *** MRSEI model was applied to analyse ecological quality in Yulin City during 2000-2018 using Landsat TM/OLI data on Google Earth *** detectors also quantified anthropo-genic and environmental influences on the study *** results are summarized as follows:(1)MRSEI showed an average correlation coefficient of 0.840 with other indices,demonstrating higher representativeness than indi-vidual *** principal component analysis indicated a 12.88%increase in explained *** also exhibited significantly improved identification of roads,villages,and unused lands over RSEI,better matching ground conditions,and suitability for regional ecological assessment.(2)During 2000-2020,the average MRSEI in Yulin City was 0.481,peaking at 0.518 in 2018,indicating general ecological improvement over ***,conditions were better in the southeast than *** 38.81%of the area showed significant improvement,10.15%exhibited significant deterioration,concentrated in western Dingbian and Jingbian counties,highlighting areas requiring enhanced protection.(3)Ecological conditions in Yulin City remained stable over ***-high clusters were concentrated in eastern counties(Qingjian,Wubao,Jia,Fugu)and central lower-altitude areas near Yokoyama and ***-low clusters predominated in the northern Yuyang desert and high-altitude western Dingbian regions.(4)Enhanced vegetation cover had the greatest influence in improving Yulin’s ecological *** was the most impactful environmental driver,while precipitation and land use change interactions showed the strongest combined *** cont

关键词： Google Earth Engine improved remote sensing-based ecological indicator temporal and spatial variation geographical detector

来源：评论

学校读者我要写书评

暂无评论

“Weibing” in traditional Chinese medicine—biological basis and mathematical representation of disease-susceptible state

引用

Acta Pharmaceutica Sinica B 2025年第5期15卷 2363-2371页

作者： Sun, Wan-Yang Wang, Rong Ouyang, Shu-Hua Liang, Wan-Li Duan, Junwei Gong, Wen-Yong Hu, Lian-Ting Chen, Xiu-Juan Li, Yi-Fang Kurihara, Hiroshi Yao, Xin-Sheng Gao, Hao He, Rong-Rong Institute of Traditional Chinese Medicine and Natural Products College of Pharmacy/Guangdong Engineering Research Center of Traditional Chinese Medicine & Disease Susceptibility/Guangdong Engineering Research Center of Traditional Chinese Medicine & Health Products/International Cooperative Laboratory of TCM Modernization and Innovative Drug Development of Chinese Ministry of Education (MOE)/Guangdong Province Key Laboratory of Pharmacodynamic Constituents of TCM and New Drugs Research/State Key Laboratory of Bioactive Molecules and Druggability Assessment Jinan University Guangzhou 510632 China State Key Laboratory of Quality Research in Chinese Medicine Macau University of Science and Technology Macau 999078 China College of Information Science and Technology Jinan University Guangzhou 510632 China Faculty of Data Science City University of Macau Macau 999078 China Medical Big Data Center Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou 510632 China The Data Center Wuhan Children's Hospital (Wuhan Maternal and Child Healthcare Hospital) Tongji Medical College Huazhong University of Science and Technology Wuhan 430016 China

“Weibing” is a fundamental concept in traditional Chinese medicine (TCM), representing a transitional state characterized by diminished self-regulatory abilities without overt physiological or social dysfunction. This perspective delves into the biological foundations and quantifiable markers of Weibing, aiming to establish a research framework for early disease intervention. Here, we propose the “Health Quadrant Classification” system, which divides the state of human body into health, sub-health, disease-susceptible state, and disease. We suggest the disease-susceptible stage emerges as a pivotal point for TCM interventions. To understand the intrinsic dynamics of this state, we propose laboratory and clinical studies utilizing time-series experiments and stress-induced disease susceptibility models. At the molecular level, bio-omics technologies and bioinformatics approaches are highlighted for uncovering intricate changes during disease progression. Furthermore, we discuss the application of mathematical models and artificial intelligence in developing early warning systems to anticipate and avert the transition from health to disease. This approach resonates with TCM's preventive philosophy, emphasizing proactive health maintenance and disease prevention. Ultimately, our perspective underscores the significance of integrating modern scientific methodologies with TCM principles to propel Weibing research and early intervention strategies forward. © 2025 The Authors

关键词： Disease-susceptible state Mathematical modeling Preventive medicine Traditional Chinese medicine Weibing

来源：评论

学校读者我要写书评

暂无评论

InTec: integrated things-edge computing A framework for distributing machine learning pipelines in edge AI systems

arXiv

引用

arXiv 2025年

作者： Larian, Habib Safi-Esfahani, Faramarz Faculty of Computer Engineering Najafabad Branch Islamic Azad University Najafabad Iran Big Data Research Center Najafabad Branch Islamic Azad University Najafabad Iran School of Information Systems and Modelling University of Technology Sydney Ultimo SydneyNSW Australia

With the rapid expansion of the Internet of Things (IoT), sensors, smartphones, and wearables have become integral to daily life, powering smart applications in home automation, healthcare, and intelligent transportation. However, these advancements face significant challenges due to latency and bandwidth constraints imposed by traditional cloud-based machine learning (ML) frameworks. The need for innovative solutions is evident as cloud computing struggles with increased latency and network congestion. Previous attempts to offload parts of the ML pipeline to edge and cloud layers have yet to fully resolve these issues, often worsening system response times and network congestion due to the computational limitations of edge devices. In response to these challenges, this study introduces the InTec (Integrated Things-Edge Computing) framework, a groundbreaking innovation in IoT architecture. Unlike existing methods, InTec fully leverages the potential of a three-tier architecture by strategically distributing ML tasks across the Things, Edge, and Cloud layers. This comprehensive approach enables real-time data processing at the point of data generation, significantly reducing latency, optimizing network traffic, and enhancing system reliability. InTec’s effectiveness is validated through empirical evaluation using the MHEALTH dataset for human motion detection in smart homes, demonstrating notable improvements in key metrics: an 81.56% reduction in response time, a 10.92% decrease in network traffic, a 9.82% improvement in throughput, a 21.86% reduction in edge energy consumption, and a 25.83% reduction in cloud energy consumption. These advancements establish InTec as a new benchmark for scalable, responsive, and energy-efficient IoT applications, demonstrating its potential to revolutionize how the ML pipeline is integrated into Edge-AI (EI) *** Codes 68M14, 68T05 © 2025, CC BY.

关键词： Traffic congestion

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：