检索结果-内蒙古大学图书馆

An integrated land change modeler and distributed hydrological model approach for quantifying future urban runoff dynamics

引用

science China Earth sciences 2024年第10期67卷 3288-3301页

作者： Asad Hussain MUHAMMAD Waseem MUHAMMAD Ajmal MUHAMMAD Atiq Ur Rehman Tariq MUHAMMAD Jiaqing XIAO Tao YANG Pengfei SHI Institute for Disaster Risk Management School of Geographical ScienceNanjing University of Information Science and TechnologyNanjing 210044China The National Key Laboratory of Water Disaster Prevention Hohai UniversityNanjing 210098China Yangtze Institute for Conservation and Development Hohai UniversityNanjing 210098China College of Hydrology and Water Resources Hohai UniversityNanjing 210098China Centre of Excellence in Water Resources Engineering University of Engineering and TechnologyLahore 54890Pakistan Department of Agricultural Engineering Faculty of CivilAgricultural and Mining EngineeringUniversity of Engineering and TechnologyPeshawar 25120Pakistan

Climate and land use changes have a significant impact on the runoff generation process in urban environments, and these effects could get worse in the future. The combined contributions of these changes have increased the risk of ***, there is a need for integrated modeling to better understand the runoff variability, especially in small urban catchments. To quantify and separate the effects of land-use changes and climate change on the hydrological response of urban catchments with a distributed hydrological model(Storm Water Management Model, SWMM), this study introduces a new integrated approach based on the Machine Learning based land use change modeler and climate change scenarios under *** on supervised classification and land use change model analysis, accumulated impervious area increase from 22%(in2023) to 33%(in 2060) was observed in the study area. Furthermore, integrating this projected increase in imperviousness with future climate change into SWMM by considering three different scenarios i.e., S1(Climate Change), S2(Combined Land Use and Climate Change), and S3(Land use Change) resulted that climate change could cause an increase in runoff from 13.2% to18.3% in peak runoff and the contribution of land use could range from 9.1% to 18.6%. Similarly, in response to the coupled effects of climate and land-use change, the runoff would likely change from 24.53% to 39.66%. Conclusively, the study showed that despite climate change, intensive urban development by the substitution of impervious surfaces could also have a severe impact on the microclimate and hydrology of small catchments. Lastly, this study could provide a way forward for the future planning and management of water resources in small catchments which could be extended to larger catchments.

关键词： Climate change Land-use modeling Runoff simulation Percent Imperviousness TerrSet

来源：评论

学校读者我要写书评

暂无评论

RESEARCH ON ACCIDENT PREDICTION OF NUCLEAR POWER PLANTS BASED ON DEEP LEARNING 31

RESEARCH ON ACCIDENT PREDICTION OF NUCLEAR POWER PLANTS BASE...

引用

2024 31st International Conference on Nuclear engineering, ICONE 2024

作者： Wei, Lv Tong, Li Bo, Wang Sichao, Tan Jiangkuan, Li Ruifeng, Tian Heilongjiang Provincial Key Laboratory of Nuclear Power System and Equipment College of Nuclear Science and Technology Harbin Engineering University Harbin150001 China Key Laboratory of Nuclear Safety and Advanced Nuclear Energy Technology School of Nuclear Science and Technology Harbin Engineering University Harbin150001 China

ISBN: (纸本)9780791888261

Based on the bidirectional long short-term memory network (BILSTM) and the long short-term memory network (LSTM), this paper uses the rolling update mechanism (RU) to obtain the time series training set data and test set data of the original data, and predicts the water level and pressure changes of the Pressurizer after the LOCA accident in nuclear power plants, so as to provide a certain reference for the prediction of LOCA accidents in nuclear power plants. Specifically, the following conclusions are obtained: Compared with the LSTM model, the BILSTM model has better prediction results and less prediction loss. Although the average error of the prediction results of the two models is 10-3 orders of magnitude, the average error of BILSTM is reduced by more than 20% compared with LSTM. © 2024 by ASME.

关键词： Nuclear reactor accidents

来源：评论

学校读者我要写书评

暂无评论

Weakly Aligned Multi-spectral Pedestrian Detection via Cross-Modality Differential Enhancement and Multi-scale Spatial Alignment 27th

Weakly Aligned Multi-spectral Pedestrian Detection via Cros...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Shao, Zhenzhou Chen, Yongxin Zou, Yibo Zhang, Jie Guan, Yong The College of Information Engineering Beijing Key Laboratory of Light Industrial Robot and Safety Verification Capital Normal University Beijing100048 China The School of Optoelectronic Science and Engineering Soochow University Suzhou China The College of Information Science and Technology University of Chemical Technology Beijing China

ISBN: (纸本)9783031781124

Multi-spectral pedestrian detection has attracted extensive attention in recent years. In particular, the combination of RGB and thermal infrared images allows the around-the-clock applications, even in the poor illumination conditions. Considering the fact that RGB and thermal infrared (RGB-T) image pairs are not well aligned, it leads to the inaccuracy of pedestrian detection. To this end, this paper proposes a Multi-scale Alignment and Differential Enhancement Network (MADENet) for multi-spectral pedestrian detection, consisting of Cross-Modality Differential Enhancement Module (CDEM) and Multi-scale Spatial Alignment Module (MSAM). CDEM module is embedded in the backbone to suppress the redundant features and extract complementary information between modalities, and MSAM module is designed to align the RGB-T features by the transformation of thermal features using features of RGB image as the reference. The proposed network is evaluated on the public KAIST dataset across different scenarios. Experimental results demonstrate that the proposed method outperforms the state-of-the-art methods. Miss rate using all test set can reach 8.01. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Effect of dissolved organic nitrogen on the bloom of Prorocentrum donghaiense and Karenia spp. in the East China Sea coastal waters

引用

Acta Oceanologica Sinica 2024年第6期43卷 71-85页

作者： Xiaoru Cui Guangming Zhen Jing Zhao Keqiang Li Xiulin Wang Key Laboratory of Marine Chemistry Theory and Technology/Frontiers Science Center for Deep Ocean Multispheres and Earth System of Ministry of Education Ocean University of ChinaQingdao 266100China College of Environmental Science and Engineering Ocean University of ChinaQingdao 266100China College of Chemistry and Chemical Engineering Ocean University of ChinaQingdao 266100China

Understan ding the mechanism of harmful algal bloom formation is vital for effectively preventing algal bloom outbreaks in coastal *** *** in the East China Sea show a significant correlation with nutrient ***,the impact of key components of nutrients,especially dissolved organic nitrogen(DON),on the blooms of Karenia *** not *** research is still *** this study,the cruise observations,field mesocosm-flask culture experiments,and a multinitrogen-tri-phytoplankton-detritus model(NTPD) are combined to reveal the quantitative influence of nutrient regimes on the shift of Prorocentrum donghaiense and Karenia *** the East China *** has a synchronism rhythm of *** spp.-diatom loop in the field culture experiment,which is consistent with the results of the cruise *** results showed that the processes of terrigenous DON(TeDON) and dissolved inorganic nitrogen(DIN:NO_(3)^(-)-N,NH_(4)^(+)-N) absorption promoted *** to become the dominant algae in the community;whereas the processes of DON from *** absorption promoted Karenia *** become the dominant algae in ambient DIN *** addition,the three-dimensional fluorescence components of humus C,tyrosine and fulvic acid can indicate the processes of growth and extinction of *** and Karenia spp.,*** study infers that *** and Karenia *** shift mechanism associated with the nutrient regime in coastal waters,which provides a scientific basis for the environmental management of coastal eco system health.

关键词： Karenia spp. Prorocentrum donghaiense nutrients multinitrogen-tri-phytoplankton-detritus model three-dimensional fluorescence

来源：评论

学校读者我要写书评

暂无评论

Robust AUC maximization for classification with pairwise confidence comparisons

引用

Frontiers of Computer science 2024年第4期18卷 73-83页

作者： Haochen SHI Mingkun XIE Shengjun HUANG College of Computer Science and Technology Nanjing University of Aeronautics and AstronauticsNanjing 211106China College of Electronic and Information Engineering Nanjing University of Aeronautics and AstronauticsNanjing 211106China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing 211106China

Supervised learning often requires a large number of labeled examples,which has become a critical bottleneck in the case that manual annotating the class labels is *** mitigate this issue,a new framework called pairwise comparison(Pcomp)classification is proposed to allow training examples only weakly annotated with pairwise comparison,i.e.,which one of two examples is more likely to be *** previous study solves Pcomp problems by minimizing the classification error,which may lead to less robust model due to its sensitivity to class *** this paper,we propose a robust learning framework for Pcomp data along with a pairwise surrogate loss called *** provides an unbiased estimator to equivalently maximize AUC without accessing the precise class ***,we prove the consistency with respect to AUC and further provide the estimation error bound for the proposed *** studies on multiple datasets validate the effectiveness of the proposed method.

关键词： method pairwise weakly

来源：评论

学校读者我要写书评

暂无评论

Analysis on the Influence of Regional Agricultural Planting Factors on Grain Yield Based on Genetic Feedback Process Neural Network 1

引用

15th International Conference on Genetic and Evolutionary Computing, ICGEC 2023

作者： Tian, Yuan Liang, Yongquan College of Computer Science and Engineering Shandong University of Science and Technology Shandong Qingdao China Provincial Key Laboratory for Information Technology of Wisdom Mining of Shandong Province Shandong University of Science and Technology Shandong Qingdao China

ISBN: (数字)9789819700684

ISBN: (纸本)9789819700677

With the accumulation of Agricultural Big Data, the management and decision-making of agricultural planting production based on single factor expose the problem of lack of comprehensive analysis. In this paper, considering the high dimensions and time-varying characteristics of agricultural big data, a new time series analysis model based on Genetic Feedback Process Neural Network (GFPNN) is proposed to analyze the influence of regional agricultural planting factors on grain yield. Take China as an example, the data of 11 agricultural planting factors in China from 1980 to 2020 constitute a time series. Analyze the time series by GFPNN to establish the influence model of agricultural planting factors on grain yield. Results show that this model can estimate grain yield with an accuracy of 97.83%, which is more accurate and efficient than traditional neural network. It can evaluate the influence of changes in agricultural planting factors on grain yield. It can be a reference for taking measures to deal with the change of grain yield and making grain policy;in the long run, developing and introducing appropriate agricultural machinery, popularizing efficient water-saving irrigation technology, further investing in rural education, and reducing planting costs can improve the grain yield to a certain extent. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Time series analysis

来源：评论

学校读者我要写书评

暂无评论

Compositional design and phase formation capability of high-entropy rare-earth disilicates from machine learning and decision fusion

引用

npj Computational Materials 2024年第1期10卷 2257-2271页

作者： Yun Fan Yuelei Bai Qian Li Zhiyao Lu Dong Chen Yuchen Liu Wenxian Li Bin Liu National Key Laboratory of Science and Technology on Advanced Composites in Special Environments and Center for Composite Materials and Structure Harbin Institute of TechnologyHarbin 150080China School of Materials Science and Engineering Shanghai UniversityShanghai 200444China National Engineering Research Center for Magnesium Alloy Chongqing UniversityChongqing 400044China School of Electronics and Information Engineering Harbin Institute of TechnologyHarbin 150080China UNSW Materials&Manufacturing Futures Institute School of Materials Science and EngineeringUniversity of New South WalesSydney NSW 2052Australia Institute of Coating Technology for Hydrogen Gas Turbines Liaoning Academy of MaterialsShenyang 110004China

A key strategy for designing environmental barrier coatings is to incorporate multiple rare-earth(RE)components intoβ-andγ-RE_(2)Si_(2)O_(7)to achieve multifunctional performance ***,the polymorphic phase presents s... 详细信息

关键词： rare earth silicate

来源：评论

学校读者我要写书评

暂无评论

High-Resolution Urban Flows Forecasting With Coarse-Grained Spatiotemporal Data

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第2期4卷 315-327页

作者： Xu, Zhenyi Kang, Yu Cao, Yang Hefei Comprehensive National Science Center Institute of Artificial Intelligence Hefei230088 China Department of Automation University of Science and Technology of China Hefei230026 China Chinese Academy of Sciences Key Laboratory of Technology in GeoSpatial Information Processing and Application System Beijing100192 China

Urban flow monitoring and forecasting systems play important roles in smart city management. However, due to the long-lasting and enormous deployment cost of ubiquitous traffic monitoring devices (e.g., loop detectors, traffic video detection), it is very difficult to predict flow in high-resolution (HR) with limited monitoring devices. The existing spatiotemporal network based methods usually predict the urban flow in the same spatial scale without considering the spatial correlations between coarse-grained and fine-grained urban flows. To tackle these issues, we propose a HR spatiotemporal transformer network (HRSTT) to predict fine-grained urban flow. Specifically, residual convolution units are employed to constructs the high-level features of three-view temporal (e.g., closeness, period, and trend) flow data. Then, a transformer block is designed to jointly learn the spatiotemporal dynamic features of each temporal flow with self-attention mechanism. For the external factors (e.g., holidays, weather conditions) are extracted by embedding dense networks, which are fused with high level coarse-grained flow feature maps with gated-fusion scheme. Finally, the coarse-grained fusion feature maps are transferred to the distributional upsampling module, generating the fined-grained flow map of target predicted time. Furthermore, the proposed model is evaluated with several baselines on real-world TaxiBJ datasets, demonstrating the state-of-the-art performance of our approach on the fine-grained urban flow forecasting problem. © 2020 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Low-Density Parity-Check Codes:Highway to Channel Capacity

引用

China Communications 2023年第2期20卷 235-256页

作者： Liyuan Song Shuyan Yu Qin Huang Fujian Provincial Engineering Technology Research Center of Photoelectric Sensing Application Key Laboratory of OptoElectronic Science and Technology for Medicine of Ministry of EducationFujian Normal UniversityFuzhou 350007China School of Electronic and Information Engineering Beihang UniversityBeijing 100191China

Low-density parity-check(LDPC)codes are not only capacity-approaching,but also greatly suitable for high-throughput ***,they are the most popular codes for high-speed data transmission in the past two *** to the low-density property of their parity-check matrices,the optimal maximum a posteriori probability decoding of LDPC codes can be approximated by message-passing decoding with linear complexity and highly parallel ***,it reveals that the approximation has to carry on Tanner graphs without short cycles and small trapping ***,it demonstrates that well-designed LDPC codes with the aid of computer simulation and asymptotic analysis tools are able to approach the channel ***,quasi-cyclic(QC)structure is introduced to significantly facilitate their high-throughput *** fact,compared to the other capacity-approaching codes,QC-LDPC codes can provide better area-efficiency and *** a result,they are widely applied in numerous communication systems,e.g.,Landsat satellites,Chang’e Chinese Lunar mission,5G mobile communications and so ***’s more,its extension to non-binary Galois fields has been adopted as the channel coding scheme for BeiDou navigation satellite system.

关键词： LDPC codes sparsity high-speed message-passing cycles trapping sets quasi-cyclic

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning-Based Approach for Anomaly Detection for Secure Cloud Computing Environments

A Machine Learning-Based Approach for Anomaly Detection for ...

引用

2023 International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2023

作者： Parameswarappa, Priya Shah, Taral Lanke, Govinda Rajulu University of the Cumberlands School of Technology United States Pace Univerty School of Information System United States Birla Institute of Technology and Science Data Science and Engineering India

ISBN: (纸本)9781665474511

The concept of "cloud computing"has been presented as a promising strategy for providing online service hosting and distribution. Despite the widespread adoption of cloud computing, security remains a top priority. Several secure methods have been devised to safeguard communication in such scenarios, with the majority of these solutions based on attack signatures. Unfortunately, these technologies cannot always detect every possible danger. A machine learning method was recently outlined. The judgment could be inaccurate if the training set is missing examples from a certain category. In this research, an innovative firewall strategy for safe cloud-based computing is presented using machine learning system. The proposed methods estimate the final assault category categorization by combining the judgments of the nodes from the past with the decision of the machine learning algorithm in the present, a technique termed most frequent decision. Both learning efficiency and system precision are improved by this method. Our results are based on UNSW-NB-15, a publicly available dataset. According to the evidence provided by our data, it improves anomaly detection by 97.68 percent. A Machine Learning-Based Approach for Anomaly Detection for Secure Cloud Computing Environments © 2023 IEEE.

关键词： Anomaly detection

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：