检索结果-内蒙古大学图书馆

Blockchain federated learning with sparsity for IoMT devices

CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS 2025年第1期28卷 1-18页

作者： Ba, Abdoul Fatakhou Yingchi, Mao Muhammad, Abdullahi Uwaisu Samuel, Omaji Muazu, Tasiu Kumshe, Umar Muhammad Mustapha Hohai Univ Coll Comp & Informat Nanjing 210098 Peoples R China Hohai Univ Key Lab Water Big Data Technol Minist Water Resources Nanjing 210098 Peoples R China Fed Univ Dutse Dept Comp Sci Dutse Nigeria Edo State Univ Dept Math & Comp Sci Uzairue 312101 Nigeria

The recent advancements in the Internet of Medical Things (IoMT) have significantly contributed to improving personalized medicine and patient diagnosis and monitoring. Nonetheless, the implementation of IoMT may encounter obstacles due to security and privacy concerns. Federated learning emerges as a promising solution, enabling multiple devices to collaborate on training rich, heterogeneous datasets while preserving privacy. Despite its potential, traditional federated learning methods exhibit vulnerabilities such as single points of attack or failure and performance degradation with heterogeneous data. To this end, this paper proposes a blockchain federated learning system to address these limitations. In the proposed blockchain, a Proof-of-Contribution-Earned (PoCE) consensus protocol is designed for block propagation and miners' selection using an improved addition tic-tac-toe game. To overcome the challenge related to heterogeneous data, a reward system based on a cooperation strategy is proposed to ensure that high-quality data is shared among health institutions. We employ a Convolutional Neural Network (CNN) where we replace the fully connected layers with sparse ones to minimize the number of parameters using an exponential random graph while maintaining model accuracy. The experimental results on real-world heterogeneous data demonstrate that the proposed system outperforms existing state-of-the-art systems in terms of accuracy and convergence rate. Security analysis reveals that the proposed system is robust against existing security and privacy-related attacks.

关键词： Blockchain Federated learning IoMT Proof-of-contribution earned Heterogeneous data

来源：评论

学校读者我要写书评

暂无评论

A kind of intelligent dynamic industrial event knowledge graph and its application in process stability evaluation

引用

JOURNAL OF INTELLIGENT MANUFACTURING 2025年第3期36卷 1801-1818页

作者： Li, Qingzong Jiang, Pingyu Wang, Jianwei Yang, Maolin Yang, Yuqian Xi An Jiao Tong Univ State Key Lab Mfg Syst Engn Xian 710049 Shaanxi Peoples R China

Event knowledge graph (EKG) is a method of representing real-world entities, events, their attributes, and the relations between them in a graph structure. The EKG has been applied in manufacturing industry to empower intelligence manufacturing. But there are limitations of generic EKG in addressing manufacturing issues. Because in the manufacturing industry, there is not only text-type knowledge but also signals, images, videos, etc. In particular, some of the relations between entities/events of the knowledge are in the form of formulas, functions, and even trained artificial intelligence models. This kind of knowledge is called Functional Knowledge in this paper. The generic EKG is suitable for representing text-type knowledge but not Functional Knowledge. Thus, the research aims to present a new kind of EKG that has the ability to represent various types of knowledge, especially Functional Knowledge. In this regard, an intelligent dynamic Industrial Event Knowledge Graph (IEKG) is proposed. Firstly, Functional Relation, Functional Triple, and a knowledge representation model based on property graphs for the schema layer of IEKG are proposed for representing Functional Knowledge. Secondly, a dynamic construction method of the instance layer of IEKG based on the event triggering mechanism is proposed, which enables the IEKG to be constructed dynamically with the production operation. Third, the constructed IEKG is applied in production monitoring using a novel graph similarity-based process stability evaluation method. Finally, a web application encapsulating our theory was developed and applied on a kneading machine in a prebaked carbon anode factory. The result shows that our proposed method has the ability to represent Functional Knowledge. Compared to the existing EKG, it has a better and broader ability of knowledge representation. The application of process stability evaluation demonstrates the potential of IEKG in addressing manufacturing issues.

关键词： Event knowledge graph Knowledge graph representation Dynamic knowledge graph Process stability evaluation

来源：评论

学校读者我要写书评

暂无评论

Enhanced precision data center server power consumption model with temperature estimation based on CPU operating statues

引用

APPLIED ENERGY 2025年 394卷

作者： Yu, Lujie Liu, Donghao Zhu, Jiebei Zhou, Huan Li, Yunfeng Wang, Yongzhen Jia, Hongjie Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China State Grid Tianjin Mkt Serv Ctr Metrol Ctr Tianjin 300222 Peoples R China Changsha Univ Sci & Technol Sch Elect & Informat Engn Changsha 410114 Hunan Peoples R China Beijing Inst Technol Sch Mech Engn Beijing 100081 Peoples R China

To mitigate energy consumptions in data centers, the accurate establishment of a server power consumption model is imperative. Traditional server power consumption model, which rely solely on CPU utilization, often overlook the CPU temperature and operating statues inherent characteristics, resulting in substantial forecast errors. In response to this gap, a novel enhanced precision Power consumption Model based on Temperature estimation considering CPU working state (PMTC) model, is proposed based on the identification of CPU operating statuses. By incorporating temperature variables at the initial model construction phase, the PMTC model effectively captures the delayed dynamic characteristics of server power consumption changes that are influenced by the lagging adjustments in CPU core temperatures, thereby eliminating temperature-related modeling inaccuracies. In the subsequent power forecasting stage, the PMTC model accurately identifies specific CPU operating statues, which facilitate precise estimations of the CPU core temperature, thus circumventing the implementation challenges associated with additional measurements of temperature variables. To validate the efficacy of the proposed PMTC model against traditional server power consumption models, a dedicated server power consumption testbed was established. The results demonstrate that the PMTC model, by incorporating the temperature-related delayed dynamic characteristics of server power consumption change without augmenting the dimensions of input data, significantly reduces modeling calculation errors.

关键词： Data center Server power consumption model Thermoelectric coupling Temperature estimation Model accuracy

来源：评论

学校读者我要写书评

暂无评论

SS-YOLOv8: small-size object detection algorithm based on improved YOLOv8 for UAV imagery

引用

MULTIMEDIA SYSTEMS 2025年第1期31卷 1-17页

作者： Qu, Jinlong Li, Qi Pan, Jie Sun, Mingzheng Lu, Xingzheng Zhou, Ying Zhu, Hongliang QiLu Aerosp Informat Res Inst Jinan 250132 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Beijing 100190 Peoples R China

Unmanned aerial vehicle (UAV) image object detection has extensive applications across both civilian and military domains. However, the traditional YOLOv8 detection algorithm faces significant challenges in detecting small objects in UAV imagery, primarily due to a high missed detection rate and an excessive number of parameters. To address these issues, this paper introduces an enhanced small object detection approach, called Small-Size Object Detection Algorithm Based on Improved YOLOv8 for UAV Imagery (SS-YOLOv8). Firstly, considering the difficulties and stringent real-time requirements in detecting small objects in UAV aerial images, this work streamlines the model by eliminating the large object detection head and its associated redundant network layers, significantly limiting the parameter count. Furthermore, a specialized tiny object detection head is proposed. It is custom-designed for detecting small objects. To enhance the model's capacity for extracting fine features of small objects and mitigate information loss during feature extraction, the convolution module is replaced in the backbone with space-to-depth convolution (SPD-Conv). Moreover, in the neck section, the self created GCU module is incorporated as it effectively amalgamates deep semantic features with shallow positional ones. Finally, while maintaining consistent parameter costs, multi-scale features are meticulously reused and incorporated to achieve a more comprehensive and sophisticated feature fusion. The experimental results on the VisDrone2019 dataset showed that compared with YOLOv8, SS-YOLOv8 improved its MAP index by 6.9% on the validation set and 5.8% on the test set, while reducing the number of parameters and model size by 65.93% and 64.85%, respectively. Compared with the best performing comparison algorithm, SS-YOLOv8 has the highest detection accuracy, indicating the superiority of this method.

关键词： Lightweight network YOLO UAV Small object detection

来源：评论

学校读者我要写书评

暂无评论

Satellite-assisted 6G wide-area edge intelligence:dynamics-aware task offloading and resource allocation for remote IoT services

引用

Science china(Information Sciences) 2025年第2期68卷 248-268页

作者： Di ZHAO Rui DING Bin SONG State Key Laboratory of Integrated Services Networks Xidian University Hangzhou Institute of Technology Xidian University China Satellite Network Group Co. Ltd.

Future 6G networks will integrate non-terrestrial communication with mobile edge computing to enable wide-area edge intelligence, providing ubiquitous communication and computation services for everyone and everything. In this paper, we introduce the intelligent cloud-edge-device architecture into low Earth orbit(LEO) satellite-supported remote Internet of Things(IoT) networks to facilitate latency-sensitive and compute-intensive IoT applications. However, the dynamic spatio-temporal characteristics inherent in LEO satellite networks, such as the high volatility of task traffic and the high mobility of space nodes, pose severe challenges. For efficient task execution, we investigate the joint optimization of cross-region task offloading and cross-domain resource allocation, and innovatively propose a spatio-temporal attention-based proximal policy optimization(STA-PPO) algorithm. Specifically, the temporal attention-based actor network analyzes the timing dependencies of task arrival and makes time-variant decisions. Simultaneously, the spatial attention-based critic network captures the spatial variations of satellite motion and evaluates the topology-related value. We verify the effectiveness of the cloud-edge-device collaboration through extensive simulations. Numerical results demonstrate that the STA-PPO algorithm outperforms benchmarks, showing the lowest system delay and the highest link throughput.

关键词： 6G wide-area edge intelligence cross-region task offloading cross-domain resource allocation spatio-temporal attention proximal policy optimization

来源：评论

学校读者我要写书评

暂无评论

Climate and evolutionary history shape latitudinal patterns of angiosperm wood density

引用

Journal of Plant Ecology 2025年第1期18卷 229-248页

作者： Kilara Waris Markku Larjavaara Ao Luo Tong Lyu Yaoqi Li Wen Jia Zhiheng Wang Institute of Ecology and Key Laboratory for Earth Surface Processes of the Ministry of Education College of Urban and Environmental SciencesPeking UniversityBeijing 100871China Department of Forest Sciences University of HelsinkiHelsinki 00014Finland Faculty of Geographical Science Beijing Normal UniversityBeijing 100875China Department of Health and Environmental Sciences Xi'an Jiaotong-Liverpool UniversitySuzhou 215123China

Wood density(WD)indicates important plant functions and plays a key role in carbon cycling of forest ecosystems by affecting wood ***,how WD varies globally and how it evolved through the evolutionary history of angiosperms remain ***,by integrating data of WD,phylogeny and distributions for angiosperms worldwide,we estimated global spatiotemporal patterns of WD and their relationships with modern climate and *** found that mean WD decreased with latitude in the northern hemisphere but increased with latitude in the southern *** interspecific WD variation within each geographic unit did not show clear latitudinal *** was the best predictor of the global geographic pattern in mean WD,while the geographic variation in mean WD across high-temperature regions could be explained by geographic variation in precipitation and precipitation seasonality(PS).Since the Cenozoic(66 million years ago(Mya)),WD increased first(until 20 Mya)and then *** general,the Cenozoic WD was positively correlated with paleotemperature and negatively correlated with paleoprecipitation,especially during more arid ***,the evolutionary trends of WD on different continents differed,which corresponded to the divergence in WD patterns and their relationships with modern climate on different *** results highlight the dominant effect of environmental temperature on global variation in angiosperm WD with an additional strong effect of *** study also demonstrates the critical role of aridity and biogeographic idiosyncrasies in driving angiosperm WD evolution.

关键词： angiosperms Cenozoic global variation modern climate paleoclimate phylogeny trait evolution wood density

来源：评论

学校读者我要写书评

暂无评论

New Insights into Microplastic Contamination in Different Types of Leachates: Abundances, Characteristics, and Potential Sources

引用

Engineering 2024年第6期37卷 62-68页

作者： Lei Zhang Wentao Zhao Liang Zhang Zhenxiao Cai Ruiqi Yan Xia Yu Damià Barceló Qian Sui State Environmental Protection Key Laboratory of Environmental Risk Assessment and Control on Chemical Process School of Resources and Environmental EngineeringEast China University of Science and TechnologyShanghai 200237China State Key Laboratory of Pollution Control and Resource Reuse College of Environmental Science and EngineeringTongji UniversityShanghai 200092China Shanghai Institute of Pollution Control and Ecological Security Shanghai 200092China PerkinElmer Inc.Shanghai 201203China Maihai Environmental Protection Technology Co. Ltd.SuzhouJiangsu 215000China Department of Environmental Chemistry Institute of Environmental Assessment and Water ResearchSpanish Council for Scientific Research(IDAEA-CSIC)Barcelona 08034Spain

Municipal solid waste(MSW)is an important destination for abandoned *** the waste disposal process,large plastic debris is broken down into microplastics(MPs)and released into the ***,current research only focuses on landfill leachates,and the occurrence of MPs in other leachates has not been ***,herein,the abundance and characteristics of MPs in three types of leachates,namely,landfill leachate,residual waste leachate,and household food waste leachate,were studied,all leachates were collected from the largest waste disposal center in *** results showed that the average MP abundances in the different types of leachates ranged from(129±54)to(1288±184)MP particles per liter(particlesL1)and the household food waste leachate exhibited the highest MP abundance(p<0.05).Polyethylene(PE)and fragments were the dominant polymer type and shape in MPs,*** characteristic polymer types of MPs in individual leachates were ***,the conditional fragmentation model indicated that the landfilling process considerably affected the size distribution of MPs in leachates,leading to a higher percentage(>80%)of small MPs(20–100 lm)in landfill leachates compared to other *** the best of our knowledge,this is the first study discussing the sources of MPs in different leachates,which is important for MP pollution control during MSW disposal.

关键词： Microplastics Landfill leachate Residual waste leachate Household food waste leachate Source

来源：评论

学校读者我要写书评

暂无评论

Approach to Automated In-situ X-Ray Absorption Fine Structure Spectroscopy Characterization

引用

Chemical research in Chinese Universities 2025年第2期41卷 313-318页

作者： XIA Yinghao ZHANG Guikai LIU Wenchao CAI Guolei JIN Song AN Pengfei HUANG Huan ZHENG Lirong JI Hengxing CHU Shengqi ZHANG Jing Beijing Synchrotron Radiation Facility Institute of High Energy PhysicsChinese Academy of SciencesBeijing 100049P.R.China University of Chinese Academy of Sciences Beijing 100049P.R.China Hefei National Laboratory for Physical Sciences at the Microscale CAS Key Laboratory of Materials for Energy ConversionCollaborative Innovation Center of Chemistry for Energy Materials(iChEM)Department of Applied ChemistryUniversity of Science and Technology of ChinaHefei 230026P.R.China

In order to expand the range of synchrotron radiation structural characterization modes,an automated in-situ X-ray absorption fine structure(XAFS)spectroscopy characterization for electrochemical research has been *** in-situ control system equipped with an automatic trigger capability facilitates automated acquisition of XAFS and electrochemical ***,the quick scanning XAFS(QXAFS)terminal,in-situ server and data storage were all controlled by remote users,enabling remote measurement to be *** this system,the evolution of the local structure near Fe atoms during the charging and discharging of lithium-sulfur battery(LSB)cathode materials was observed,which provides deep insights into the sulfur reaction pathway in LSBs by leveraging structural *** system established here paves the way for fully automated and intelligent in-situ XAFS experiments.

关键词： Remote Automation In-situ X-ray absorption fine structure(XAFS)spectroscopy Electrochemical

来源：评论

学校读者我要写书评

暂无评论

Dual-phase synergistically enhancing mechanical properties and thermal conductivity of hot-extruded Mg-8Gd-1Er-8Zn-1Mn alloy

引用

Journal of Magnesium and Alloys 2025年第3期13卷 1176-1186页

作者： Xudong Li Wenbo Du Feng Lou Ning Ding Xian Du Shubo Li College of Materials Science and Engineering Beijing University of TechnologyBeijing 100124China

The contradiction between mechanical properties and thermal conductivity of magnesium alloys is a roadblock for their widespread *** this study,we developed a hot-extruded Mg-8Gd-1Er-8Zn-1Mn alloy with high-strength and high-thermal-conductivity via dual-phase,W-phase andα-Mn,synergistically *** alloy extruded at 300℃ exhibited the yield strength and elongation of 372 MPa and 12%,respectively,it simultaneously demonstrated a high thermal conductivity of 134.3W/(m·K).After extrusion,the original coarse W-phase in the alloy was broken into near-spheroidal particles,which reduced the probability of electron *** addition,a large number of solute atoms dynamically precipitated in the form of nanoscale rod-like W-phase andα-Mn,makingα-Mg matrix revert to a nearly periodic arrangement *** high yield strength of the alloy is predominantly determined by grain boundary strengthening as well as W-phase andα-Mn dual-phase ***,the strategy of dual-phase strengthening provides a valuable approach for developing structure-function integrated Mg alloys.

关键词： Mg-RE-Zn alloy W-phase α-Mn Thermal conductivity Strength

来源：评论

学校读者我要写书评

暂无评论

development and identification of two novel wheat-rye 6R derivative lines with adult-plant resistance to powdery mildew and high-yielding potential

引用

The Crop Journal 2024年第1期12卷 308-313页

作者： Guohao Han Jing Wang Hanwen Yan Tiantian Gu Lijun Cao Shiyu Liu Xiuquan Li Yilin Zhou Jieru Fan Zhipeng Shi Hong Liu Lihui Li Diaoguo An Center for Agricultural Resources Research Institute of Genetics and Developmental BiologyChinese Academy of SciencesShijiazhuang 050021HebeiChina The National Key Facility for Crop Gene Resources and Genetic Improvement Institute of Crop SciencesChinese Academy of Agricultural SciencesBeijing 100081China The State Key Laboratory for Biology of Plant Disease and Insect Pests Institute of Plant ProtectionChinese Academy of Agricultural SciencesBeijing 100193China

Powdery mildew,caused by Blumeria graminis ***(Bgt),is a devastating disease that seriously threatens wheat yield and *** control this disease,host resistance is the most effective *** with the resistance genes from common wheat,alien resistance genes can better withstand infection of this highly variable *** of elite alien germplasm resources with powdery mildew resistance and other key breeding traits is an attractive strategy in wheat *** this study,three wheat-rye germplasm lines YT4-1,YT4-2,and YT4-3 were developed through hybridization between octoploid triticale and common wheat,out of which the lines YT4-1 and YT4-2 conferred adult-plant resistance(APR)to powdery mildew while the line YT4-3 was susceptible to powdery mildew during all of its growth *** genomic in situ hybridization,multi-color fluorescence in situ hybridization,multi-color GISH,and molecular marker analysis,YT4-1,YT4-2,and YT4-3 were shown to be cytogenetically stable wheat-rye 6R addition and T1RS.1BL translocation line,6RL ditelosomic addition and T1RS.1BL translocation line,and T1RS.1BL translocation line,*** with previously reported wheat-rye derivative lines carrying chromosome 6R,YT4-1 and YT4-2 showed stable APR without undesirable pleiotropic effects on agronomic ***,these novel wheat-rye 6R derivative lines are expected to be promising bridge resources in wheat disease breeding.

关键词： Powdery mildew Secale cereale Triticum aestivum Wheat-rye 6R derivatives Agronomic performance

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：