检索结果-南通市图书馆

Chinese Geographical Science 2024年第5期34卷 899-916页

作者： LI Bo cao Gai Key Research Base of Humanities and Social Sciences of Ministry of Education Institute of Marine Sustainable DevelopmentLiaoning Normal UniversityDalian 116029China School of Maritime economics and management Dalian Maritime UniversityDalian 116026China

Data on discrete,isolated attributes of the marine economy are often used in traditional marine economic ***,as the focus of urban research shifts from internal static attributes to external dynamic linkages,the importance of marine economic net-work research is beginning to *** construction of the marine economic network in China’s coastal areas is necessary to change the flow of land and sea resources and optimize regional marine economic *** data from headquarters and branches of sea-related A-share listed enterprises to construct the marine economic network in China,we use social network analysis(SNA)to discuss the characteristics of its evolution as of 2010,2015,and 2020 and its *** following results were obtained.1)In terms of topological characteristics,the scale of the marine economic network in China’s coastal areas has accelerated and expan-ded,and the connections have become increasingly close;thus,this development has complex network characteristics.2)In terms of spatial structure,the intensity of the connection fluctuates and does not form stable development support;the group structure gradually becomes clear,but the overall pattern is fragmented;there are spatial differences in marine economic agglomeration radiation;the radi-ation effect of the eastern marine economic circle is obvious;and the polarization effect of northern and southern marine economic circles is *** this basis,we construct a framework for the governance of a marine economic network with the market,the government,and industry as the three governing *** clarifying the driving factors and building objectives of marine economic network construction,this study aims to foster the high-quality development of China’s marine economy.

关键词： marine economic network sea-related A-share listed companies social network analysis(SNA) network governance China’s coastal areas

维普期刊数据库

Identification of rural courtyards’utilization status using deep learning and machine learning methods on unmanned aerial vehicle images in north China

在线全文

学校读者我要写书评

暂无评论

Building Simulation 2024年第5期17卷 799-818页

作者： Maojun Wang Wenyu Xu Guangzhong cao Tao Liu college of Resource Environment and Tourism Capital Normal UniversityBeijing 100048China college of Urban and Environmental Sciences Peking UniversityBeijing 100871China

The issue of unoccupied or abandoned homesteads(courtyards)in China emerges given the increasing aging population,rapid urbanization and massive rural-urban *** the aspect of rural vitalization,land-use planning,and policy making,determining the number of unoccupied courtyards is *** and questionnaire-based surveys were currently the main approaches,but these traditional methods were often expensive and laborious.A new workflow is explored using deep learning and machine learning algorithms on unmanned aerial vehicle(UAV)***,features of the built environment were extracted using deep learning to evaluate the courtyard management,including extracting complete or collapsed farmhouses by Alexnet,detecting solar water heaters by YOLOv5s,calculating green looking ratio(GLR)by *** precisions exceeded 98%.Then,seven machine learning algorithms(Adaboost,binomial logistic regression,neural network,random forest,support vector machine,decision trees,and XGBoost algorithms)were applied to identify the rural courtyards’utilization *** Adaboost algorithm showed the best performance with the comprehensive consideration of most metrics(Accuracy:0.933,Precision:0.932,Recall:0.984,F1-score:0.957).Results showed that identifying the courtyards’utilization statuses based on the courtyard built environment is *** is transferable and cost-effective for large-scale village surveys,and may contribute to the intensive and sustainable approach to rural land use.

关键词： unoccupied homesteads courtyard built environment inner courtyard management GLR solar water heaters machine learning algorithms

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

生物质能源产业发展演化机制及障碍因子

林业经济问题 2024年第3期44卷 273-283页

作者：冯雪曹玉昆青岛理工大学商学院山东青岛266525 东北林业大学经济管理学院哈尔滨150040

以黑龙江重点国有林区为研究区域,基于2005—2017年面板数据,遵循DPSIR理论模型的分析范式,利用PLS-SEM解构生物质能源产业发展的演化机制和作用路径,运用障碍度模型识别影响生物质能源产业发展的主要障碍因子。结果表明:黑龙江重点国... 详细信息

以黑龙江重点国有林区为研究区域,基于2005—2017年面板数据,遵循DPSIR理论模型的分析范式,利用PLS-SEM解构生物质能源产业发展的演化机制和作用路径,运用障碍度模型识别影响生物质能源产业发展的主要障碍因子。结果表明:黑龙江重点国有林区生物质能源产业形成了“驱动力→压力→状态→影响”“响应→驱动力”以及“响应→影响”3条演化路径;2005—2017年影响黑龙江重点国有林区生物质能源产业发展的障碍因子变动较大,主要障碍因子从2005年的生物质发电并网装机容量、生物质发电量、农作物秸秆能源资源量、生物质能源专利和生物质能源研发投入强度等指标,转变为2017年的原油消耗量、原煤消耗量、天然气消耗量、万元GDP能耗和林业系统专业技术人员等指标,涉及技术水平指标一直是主要障碍因子。因此,加大技术创新力度和完善政策支撑体系是提升黑龙江重点国有林区生物质能源产业发展效率的有效途径。

关键词：生物质能源产业演化机制障碍因子 DPSIR理论模型 PLS-SEM

维普期刊数据库

Adaptive 5G-and-beyond network-enabled interpretable federated learning enhanced by neuroevolution

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第7期67卷 107-132页

作者： Bin cao Jianwei ZHAO Xin LIU Yun LI State Key Laboratory of Reliability and Intelligence of Electrical Equipment Hebei University of Technology School of Artificial Intelligence Hebei University of Technology School of economics and management Hebei University of Technology Industrial Artificial Intelligence Centre Shenzhen Institute for Advanced StudyUniversity of Electronic Science and Technology of China

Mobile telemedicine systems based on the next-generation communication will significantly enhance deep fusion of network automation and federated learning(FL), but data privacy is a paramount issue in sectors like healthcare. This work hence considers FL augments 5G-and-beyond networks by training deep learning(DL) models without the need to exchange raw data. The substantial communication loads imposed on by extensive parameters involved in DL models are managed through adaptive scheduling mechanisms effectively. To address the opaque nature of DL models and to improve the interpretability of FL models, we introduce a convolutional fuzzy rough neural network specifically designed for medical image processing. We also develop a multiobjective memetic evolutionary algorithm to streamline and optimize the neural network architectures. Our comprehensive FL framework integrates smart scheduling, interpretable fuzzy rough logic,and neuroevolution. This framework is shown to improve communication efficiency, increase interpretability of diagnosis with protected privacy, and generate low-complexity neural architectures.

关键词： 5G-and-beyond network interpretable federated learning mobile telemedicine system fuzzy rough set theory neuroevolution

A Hybrid Air Quality Prediction Model Based on Empirical Mode Decomposition

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2024年第1期29卷 99-111页

作者： Yuxuan cao Difei Zhang Shaoqi Ding Weiyi Zhong Chao Yan School of Computer Science Qufu Normal UniversityRizhao 276826China School of Mathematical Sciences Qufu Normal UniversityQufu 273165China School of Computer Science Qufu Normal UniversityRizhao 270826China college of Economic and management Shandong University of Science and TechnologyQingdao 250307China

Air pollution is a severe environmental problem in urban *** air quality prediction can help governments and individuals make proper decisions to cope with potential air *** a classic time series forecasting model,the AutoRegressive Integrated Moving Average(ARIMA)has been widely adopted in air quality ***,because of the volatility of air quality and the lack of additional context information,i.e.,the spatial relationships among monitor stations,traditional ARIMA models suffer from unstable prediction *** some deep networks can achieve higher accuracy,a mass of training data,heavy computing,and time cost are *** this paper,we propose a hybrid model to simultaneously predict seven air pollution indicators from multiple monitoring *** proposed model consists of three components:(1)an extended ARIMA to predict matrix series of multiple air quality indicators from several adjacent monitoring stations;(2)the Empirical Mode Decomposition(EMD)to decompose the air quality time series data into multiple smooth sub-series;and(3)the truncated Singular Value Decomposition(SvD)to compress and denoise the expanded *** results on the public dataset show that our proposed model outperforms the state-of-art air quality forecasting models in both accuracy and time cost.

关键词： air quality prediction Empirical Mode Decomposition(EMD) Singular Value Decomposition(SVD) AutoRegressive Integrated Moving Average(ARIMA)

Model-based offline reinforcement learning framework for optimizing tunnel boring machine operation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Underground Space 2024年第6期19卷 47-71页

作者： Yupeng cao Wei Luo Yadong Xue Weiren Lin Feng Zhang Department of Urban management Kyoto UniversityKyoto 615-8540Japan Department of Geotechnical Engineering College of Civil EngineeringTongji UniversityShanghai 200092China Key Laboratory of Geotechnical and Underground Engineering of Ministry of Education Tongji UniversityShanghai 200092China

Research on automation and intelligent operation of tunnel boring machine(TBM)is receiving more and more attention,benefiting from the increasing construction ***,most studies on TBM operations optimization were trained by the labels of human drivers’decisions,which were subjective and *** a result,the control parameters suggested by these models could hardly surpass the performance of a human driver,even the possibility of subjective incorrect *** that the geomechanical feedback to TBM under drivers’actions is objective,in this paper,a transformer-based model called the geological response for tunnel boring machine(GRTBM),is proposed to learn the relationship between operation-adjust and TBM monitoring ***,with the model-based offline reinforcement learning,this paper provided a novel approach to optimizing the TBM excavation *** decision processes,recorded in the Yin-song TBM project for a waterway tunnel in Jilin Province of China,were used for the validation of the *** adopting an implicit perception of geological conditions in the GRTBM model,the suggested method achieved the desired state within a single action,greatly outperformed the practical adjustments where 500 s were taken,revealing the fact that the proposed model has the potential to surpass the capability of human beings.

关键词： TBM Reinforcement learning Transformer Data mining

Spatial Differentiation and Convergence Trend of High-quality Development Level of China’s Tourism Economy

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Geographical Science 2024年第2期34卷 230-249页

作者： cao Shanshan HE Zhaoli NIU Jinlan WANG Songmao ZHAO Lei School of Geography and Ocean Science Nanjing UniversityNanjing 210046China School of Business Administration Nanjing University of Finance and EconomicsNanjing 210046China School of economics and management Shandong Agricultural Uni-versityTai’an 271018China School of Hotel management Shanghai Business SchoolShanghai 201400China School of Man-agement Zhejiang University of TechnologyHangzhou 310014China

This paper aims to interpret the connotation of high-quality development of tourism economy(HQTE)from the perspective of the new development concepts of innovation,coordination,green,openness and sharing,and then to evaluate the spatial differenti-ation of China’s HQTE based on provincial panel data from 2009 to ***,we employ the spatial convergence model to ex-plore the absolute and conditionalβconvergence trends of HQTE in the whole country and the eastern,central and western regions of *** empirical results reveal that:1)within the decade,from 2009 to 2018,regions of China with the highest HQTE index is its eastern region followed by the central region and then the western region,but the fastest growing one is the western region of China fol-lowed by the central region and then the eastern region.2)Whether or not the spatial effect is included,there are absolute and condition-alβconvergence in HQTE in the whole country and aforementioned three regions.3)The degree of government attention as well as the level of economic development and location accessibility are the positive driving factors for the convergence of HQTE in the whole country and the three *** degree of marketization and human capital have not passed the significance test either in the whole country or in the three *** above conclusions could deepen the understanding of the regional imbalance and spatial conver-gence characteristics of HQTE,clarify the primary development objects,and accomplish the goal of China’s HQTE.

关键词： new development concepts high-quality development of tourism economy(HQTE) spatial convergence China

维普期刊数据库

Double integral-enhanced Zeroing neural network with linear noise rejection for time-varying matrix inverse

在线全文

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第1期9卷 197-210页

作者： Bolin Liao Luyang Han Xinwei cao Shuai Li Jianfeng Li college of Computer Science and Engineering Jishou UniversityJishouChina School of management Shanghai UniversityShanghaiChina School of Engineering Swansea UniversitySwanseaUK

In engineering fields,time-varying matrix inversion(TVMI)issue is often *** neural network(ZNN)has been extensively employed to resolve the TVMI ***,the original ZNN(OZNN)and the integral-enhanced ZNN(IEZNN)usually fail to deal with the TVMI problem under unbounded noises,such as linear ***,a neural network model that can handle the TVMI under linear noise interference is urgently *** paper develops a double integral-enhanced ZNN(DIEZNN)model based on a novel integral-type design formula with inherent linear-noise ***,its convergence and robustness are verified by deriva-tion *** comparison and verification,the OZNN and the IEZNN models are adopted to resolve the TVMI under multiple identical noise *** experi-ments proved that the DIEZNN model has excellent advantages in solving TVMI problems under linear *** general,the DIEZNN model is an innovative work and is proposed for the first ***,the errors of DIEZNN are always less than 1�10−3 under linear noises,whereas the error norms of OZNN and IEZNN models are not convergent to *** addition,these models are applied to the control of the controllable permanent magnet synchronous motor chaotic system to indicate the superiority of the DIEZNN.

关键词： neural network real-time systems

Multi-user reinforcement learning based task migration in mobile edge computing

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2024年第4期18卷 161-173页

作者： Yuya CUI Degan ZHANG Jie ZHANG Ting ZHANG Lixiang cao Lu CHEN Tianjin Key Lab of Intelligent Computing and Novel Software Technology Tianjin University of TechnologyTianjin 300384China School of Internet of Things Engineering Jiangsu Vocational College of Information TechnologyWuxi 214153China School of Electronic and Information Engineering Beijing Jiaotong UniversityBeijing 100044China School of Sports economics and management Tianjin University of SportTianjin 301617China

Mobile Edge Computing(MEC)is a promising *** service migration is a key technology in *** order to maintain the continuity of services in a dynamic environment,mobile users need to migrate tasks between multiple servers in real *** to the uncertainty of movement,frequent migration will increase delays and costs and non-migration will lead to service ***,it is very challenging to design an optimal migration *** this paper,we investigate the multi-user task migration problem in a dynamic environment and minimizes the average service delay while meeting the migration *** order to optimize the service delay and migration cost,we propose an adaptive weight deep deterministic policy gradient(AWDDPG)*** distributed execution and centralized training are adopted to solve the high-dimensional *** show that the proposed algorithm can greatly reduce the migration cost and service delay compared with the other related algorithms.

关键词： mobile edge computing mobility service migration deep reinforcement learning deep deterministic policy gradient