检索结果-内蒙古大学图书馆

Riverine flood hazard map prediction by neural networks

HydroResearch 2025年 8卷 139-151页

作者： Yin, Zeda Leon, Arturo S. Department of Civil and Environmental Engineering College of Engineering and Computing Florida International University Miami FL United States

Severe flooding can pose significant risks to human lives, result in substantial economic losses, and contribute to environmental problems such as soil salinization. An accurate early flood prediction system can effectively minimize these losses. Numerical method was the dominant approach for predicting flood inundation maps in the past decades. However, high-fidelity two-dimensional numerical methods are typically time-consuming. Machine learning methods have gained popularity in recent years, but generating a flood map directly with a small sample of boundary conditions remains challenging and largely unexplored. In this paper, we have developed a machine learning framework capable of directly predicting the maximum flood inundation map from boundary conditions. In our model, time-series boundary conditions are embedded into a higher-dimensional shape and then processed by a transformer encoder. The feature maps, post-processed by the transformer encoder, will be coupled with geophysical information such as a digital elevation map and Manning's coefficient map before being passed to the U-Net structure to obtain the final results. Our proposed model demonstrated notably high accuracy when tested with historical hurricane events. The mean absolute error of our proposed method on all test sets is 0.00717 ft., and the root mean squared error is 0.03974 ft. Furthermore, we conducted parametric studies on the model architecture and observed that they are not as sensitive as input features. Lastly, we provided explanations on why some certain geophysical features are necessary to accurately predict flood inundation maps in this paper. © 2024 The Authors

关键词： Boundary conditions to image Deep learning Flood map prediction

来源：评论

学校读者我要写书评

暂无评论

A deep learning approach for recognizing and solving handwritten mathematical equations

引用

Neural computing and Applications 2025年第14期37卷 8759-8772页

作者： Yadav, Pavinder Shantilal, Sankhala Bhavik Kumar, Vipin Sihag, Parveen Sharma, Pawan Kumar Rana, Pankaj Department of Mathematics and Scientific Computing National Institute of Technology HP Hamirpur India Department of Civil Engineering Chandigarh University Punjab Mohali India Department of Physical Sciences Baba Mastnath University Asthal Bohar Haryana Rohtak India

Recognizing handwritten equations is considerably more challenging than identifying printed ones, primarily due to variations in writing styles. Even though there have been recent improvements in handwriting recognition for things like equation solvers and automation, it is still hard for machines to understand a handwritten mathematical expression (HME). This paper presents a deep learning model for recognizing and solving handwritten equations, as well as its graphical user interface (GUI). A manually constructed large dataset comprising approximately 66k images of digits, mathematical symbols, and characters is utilized, with a fine-tuned InceptionV3 model employed for image classification and segmentation. The system is designed to extract handwritten equations from an image, perform character recognition, and generate the roots of the polynomial equation up to degree four. According to the findings, the trained model achieves remarkable accuracy in recognizing and solving handwritten equations, with over 94% accuracy on the training set. By eliminating the possibility of human error, automatic handwritten equation solvers provide more accurate results than manual methods. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A System-of-Systems Approach for Deploying Containerized Construction Digital Twins Using Linked Data 20th

A System-of-Systems Approach for Deploying Containerized Con...

引用

20th International Conference on computing in civil and Building engineering, ICCCBE 2024

作者： Hagedorn, Philipp Petrova, Ekaterina König, Markus Computing in Engineering Department of Civil and Environmental Engineering Ruhr University Bochum Bochum44801 Germany Department of the Built Environment Eindhoven University of Technology Eindhoven5612 AZ Netherlands

ISBN: (纸本)9783031842078

Construction Digital Twins (CDTs) are pivotal in AECO;however, many recent publications offer non-standardized, monolithic frameworks. This research suggests adopting modular CDTs through standardized Information Containers for linked Document Delivery (ICDD) to promote high modularity and reusability. It proposes a way to couple multiple ICDDs in a System-of-Systems approach. Therefore, the data structure of ICDD is analyzed and extended towards a hierarchy of containers that can communicate horizontally and vertically. Standardized REST and SPARQL interfaces are used for horizontal communication. An extended data structure supports vertical integration of CDT modules within ICDD containers, subsidizing spatial, process, or life cycle criteria based on the standardized link-type specializations provided by the ICDD standard. Eventually, this paper presents a proof of concept for CDT module integration within ICDD, addressing the need for modular and standardized frameworks for deploying CDTs based on the use case of bridge condition assessment integrating inspection data and live data from structural health monitoring. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

Slime Mould Algorithm Enhanced Gradient Boosting Regressor for Prediction of Slope Stability 2nd

Slime Mould Algorithm Enhanced Gradient Boosting Regressor f...

引用

2nd International Conference on Geotechnical Issues in Energy, Infrastructure and Disaster Management, ICGEID 2024

作者： Kainthola, Ashutosh Pandey, Vishnu Himanshu Ratnam Singh, T.N. Geo-Engineering and Computing Laboratory Department of Geology Banaras Hindu University Uttar Pradesh Varanasi India Department of Civil and Environmental Engineering IIT Patna Bihar Patna India

ISBN: (纸本)9789819717569

Present research details the comparison of predictive efficiency of linear regression, gradient boosting regression, and slime mould algorithm optimised gradient boosting regression. These algorithms have been used to predict the factor of safety of cut slopes in lower Tons valley, Uttarakhand, India. Initially, 103 soil slopes were examined for their stability factor in finite difference code. Four parameters like cohesion, angle of internal friction, slope height, and slope angle were selected to develop the stability (factor of safety) prediction models. Based on the statistical accuracy indices like R2 and mean absolute error, the hyper-parameter optimized model based on slime mould algorithm (i.e., SMA-GBR) had the best prediction capability. And, the R2 for SMA-GBR model is 0.92 and mean absolute error is 0.063. The next better performer is linear regression model with value of 0.84 and 0.094 for R2 and mean absolute error respectively. And, the gradient boosting algorithm model has the least predictive capacity as compared to other two prediction models developed in the present work. However, its capability is significantly increased as its hyper-parameter are fine-tuned through slime mould algorithms (SMA). © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Classification and clustering analysis of standing dead trees and associated park asset wildfire vulnerability in Yellowstone National Park

引用

Forest Ecosystems 2025年第2期12卷 275-286页

作者： Carolyn Prescott Mehmet Ozdes Di Yang School of Computing Wyoming Geographic Information Science CenterUniversity of WyomingLaramieWY 82071USA Environmental Engineering Faculty of EngineeringTekirdag Namik Kemal UniversityTekirdag 59030Turkey Civil and Environmental Engineering Clarkson UniversityPotsdamNY 13699USA Department of Geography University of FloridaGainesvilleFL 32611USA

In the Rocky Mountain and Pacific Northwest regions of the United States,forests include extensive portions of standing dead *** regions showcase an intriguing phenomenon where the combined biomass of standing dead trees surpasses that of fallen and decomposing woody *** stems from a suite of factors including pest disturbances,management decisions,and a changing *** increasingly dry and hot conditions,dead timber on a landscape increases the probability that a fire will *** and characterizing the presence of standing dead trees on a landscape helps with forest management efforts including reductions in the wildfire hazard presented by the trees,and vulnerability of nearby park assets should the trees *** forest-based classification,exploratory data analysis,and cluster vulnerability analysis,this study characterized the occurrence and implications of standing dead trees within Yellowstone National *** findings show standing dead trees across the entire study area with varying *** clusters were cross-referenced with vulnerability parameters of distance to roads,distance to trails,distance to water,distance to buildings,and *** parameters inform fire ignition,propagation,and *** weighted sum of these parameters was used to determine the vulnerability incurred on the park assets by the clusters and showed the highest values nearest to park entrances and points of *** vulnerability clusters warrant priority management to reduce wildfire *** framework of this study can be applied to other sites and incorporate additional vulnerability variables to assess forest fuel and *** can provide a reference for management to prioritize areas for resource conservation and improve fire prevention and suppression efficiency.

关键词： Forest health Fire risk Rocky mountain and pacific northwest forests Park management Spatial autocorrelation Random Forest

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Explainable AI Based Blast Wave Pressure Prediction in IoV Applications 4

Deep Learning and Explainable AI Based Blast Wave Pressure P...

引用

4th International Conference on Evolutionary computing and Mobile Sustainable Networks, ICECMSN 2024

作者： Mir, Mahmood Hussain Antony, Judeson Mohamed, Sulaiman Syed Dhar, Soumi Pragya Fayaz, Danish Alliance School of Advanced Computing Alliance University Bangalore India Department of Civil Engineering Alliance College of Design Alliance University Bangalore India

Predicting blast wave pressure is crucial for enhancing safety and response strategies in Internet of Vehicles (IoV) applications, particularly in the context of urban environments and high-risk areas. This paper presents a novel deep learning model designed for predicting blast frequencies in BLEVE (Boiling Liquid Expanding Vapor Explosion) scenarios. The article evaluates several activation functions, including ReLU, Mish, ELU, Silu, and Leaky ReLU, to determine their effectiveness in improving model accuracy. The results indicate that the Mish activation function achieves slightly lower Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) scores on the test dataset, with Train RMSE at 0.075 and Test RMSE at 0.099. The Silu activation function also demonstrates strong performance, yielding a Train RMSE of 0.074 and Test RMSE of 0.095, alongside high R2 scores, indicating a good fit to the data. The paper further explores the interpretability of the model's predictions using the LIME framework, revealing insights into how sensor positions and vapor heights influence blast frequency predictions. This research explores the potential of deep learning techniques in enhancing safety measures and predictive capabilities in hazardous scenarios, contributing valuable insights to the field of risk assessment and management in IoV applications. © 2025 The Authors. Published by Elsevier B.V.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Efficiency of a cylindrical wave energy converter with different bottom shapes in a chambered breakwater

引用

Marine Systems and Ocean Technology 2025年第2期20卷 1-15页

作者： Aiswaria, K. Balaji, Ramakrishnan Krishnendu, P. Jodha, Shweta Department of Civil Engineering Indian Institute of Technology Bombay Mumbai400076 India School of Engineering Computing and Mathematics University of Plymouth Drake Circus PlymouthPL48AA United Kingdom Naval Architecture and Ocean Engineering Indian Maritime University Visakhapatnam Andhra Pradesh Visakhapatnam531035 India

Ocean waves are one of the high-density renewable energy resources and can work as a generous, sustainable, and clean energy source. The energy capturing of a floating point absorber system is designed to be maximum when it is close to resonance. Integrating coastal protection structures with a wave energy converter can be a promising solution to extract wave energy economically. This paper investigates the influence of bottom shapes on the hydrodynamic performance of a cylindrical heaving floating point absorber wave energy converter stand-alone and integrated with breakwater conditions. The study is carried out for constant mass and constant draft model cases, providing identical conditions for comparison. It is seen that a cylinder with a 90° conical bottom has better performance for the same waterline diameter than all the other models. After the integration with a chambered breakwater, the power performance of the wave energy device was found to increase by a maximum of 3.5 times more than that of the stand-alone case for all the models at quasi-resonance conditions, especially when the WEC is positioned at locations of amplified wave elevations inside the chamber. © The Author(s), under exclusive licence to Sociedade Brasileira de Engenharia Naval 2025.

关键词： Wave power

来源：评论

学校读者我要写书评

暂无评论

Optimized Convolutional Neural Networks with Multi-Scale Pyramid Feature Integration for Efficient Traffic Light Detection in Intelligent Transportation Systems

引用

Computers, Materials & Continua 2025年第2期82卷 3005-3018页

作者： Yahia Said Yahya Alassaf Refka Ghodhbani Taoufik Saidani Olfa Ben Rhaiem Department of Electrical Engineering College of EngineeringNorthern Border UniversityArar91431Saudi Arabia Center for Scientific Research and Entrepreneurship Northern Border UniversityArar73213Saudi Arabia Department of Civil Engineering College of EngineeringNorthern Border UniversityArar91431Saudi Arabia Faculty of Computing and Information Technology Northern Border UniversityRafha91911Saudi Arabia College of Science Northern Border UniversityArar91431Saudi Arabia

Transportation systems are experiencing a significant transformation due to the integration of advanced technologies, including artificial intelligence and machine learning. In the context of intelligent transportation systems (ITS) and Advanced Driver Assistance Systems (ADAS), the development of efficient and reliable traffic light detection mechanisms is crucial for enhancing road safety and traffic management. This paper presents an optimized convolutional neural network (CNN) framework designed to detect traffic lights in real-time within complex urban environments. Leveraging multi-scale pyramid feature maps, the proposed model addresses key challenges such as the detection of small, occluded, and low-resolution traffic lights amidst complex backgrounds. The integration of dilated convolutions, Region of Interest (ROI) alignment, and Soft Non-Maximum Suppression (Soft-NMS) further improves detection accuracy and reduces false positives. By optimizing computational efficiency and parameter complexity, the framework is designed to operate seamlessly on embedded systems, ensuring robust performance in real-world applications. Extensive experiments using real-world datasets demonstrate that our model significantly outperforms existing methods, providing a scalable solution for ITS and ADAS applications. This research contributes to the advancement of Artificial Intelligence-driven (AI-driven) pattern recognition in transportation systems and offers a mathematical approach to improving efficiency and safety in logistics and transportation networks.

关键词： Intelligent transportation systems(ITS) traffic light detection multi-scale pyramid feature maps advanced driver assistance systems(ADAS) real-time detection AI in transportation

来源：评论

学校读者我要写书评

暂无评论

Innovative Video Classification Method based on Deep Learning Approach

引用

Recent Patents on engineering 2025年第2期19卷 95-107页

作者： Hemamalini, V. Jayasutha, D. Vinothini, V.R. Devi, R. Manjula Kumar, A. Anitha, E. Department of Networking and Communications School of Computing SRM Institute of Science and Technology Chennai India Department of Computer Science and Engineering Arjun College of Technology Coimbatore Thamaraikulam India Department of Mathematics Bannari Amman Institute of Technology Sathyamangalam Erode638401 India Department of Computer Science and Design Kongu Engineering College Perundurai Erode638060 India Department of Civil Engineering University Institute of Engineering & Technology Maharshi Dayanand University Rohtak124001 India Department of Artificial Intelligence and Data Science Sri Eshwar College of Engineering Coimbatore641202 India

Background: The automated classification of videos through artificial neural networks is addressed in this work. To explore the concepts and measure the results, the data set UCF101 is used, consisting of video clips taken from YouTube to recognize actions. The study is carried out with the authors' resources to determine the feasibility of independent research in the area. Methods: This work was developed in the Python programming language using the Keras library with Tensorflow as the back-end. The objective is to develop a network that presents performance compatible with the state of the art in terms of classifying videos according to the actions taken. Results: Given the hardware limitations, there is considerable distance between the implementation possibilities in this work and what is known as the state-of-the-art. Conclusion: Throughout the work, some aspects in which this limitation influenced the development are presented, but it is shown that this realization is feasible and that obtaining expressive results is possible 98.6% accuracy is obtained in the UCF101 data set, compared to the 98 percentage points of the best result ever reported, using, however, considerably fewer resources. In addition, the importance of transfer learning in achieving expressive results as well as the different performances of each architecture are reviewed. Thus, this work may open doors to carry patent-based outcomes. © 2025 Bentham Science Publishers.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Sediment erosion mechanisms at a vertical pile in oscillatory flow 12th

Sediment erosion mechanisms at a vertical pile in oscillator...

引用

12th International Conference on Fluvial Hydraulics, River Flow 2024

作者： Chang, W.Y. Constantinescu, G. National Center for High Performance Computing National Applied Research Laboratories Hsinchu Taiwan Department of Civil and Environmental Engineering IIHR-Hydroscience and Engineering The University of Iowa Iowa City United States

ISBN: (纸本)9781032757216

Detached eddy simulations are used to investigate the role of turbulent struc tures generated by a vertical pile of circular cross section placed in oscillatory flow in inducing local scour. The study considers several cases with a Keulegan-Carpenter number in the range 1.5≤KC≤30.8 and unimodal forcing. It is found that the coherence of the horseshoe vortices increases with increasing KC and these vortices are present over part of the oscillatory cycle. The number of shed vortices in the wake over each half cycle also increases with KC and these vortices maintain a high coherence as they interact with the bed surface. Moreover, for suffi ciently large KC values, other vortices whose axes are parallel to the bed form in the wake. These vortices are induced by the interaction of the deformed cores of the vertical wake vortices with the bed surface. Assuming the depth-averaged velocity in the incoming (undisturbed) oscil latory flow is the same in simulations, the maximum sediment entrainment potential, measured by the mean (cycle-averaged) volumetric flux of sediment entrained from the bed over one oscillatory cycle, occurs for 8≤KC≤15.4. The paper also discusses the limitations of the RANS approach in predicting the correct amplification of the bed shear stress around the cylinder. © 2025 The Author(s).

关键词： Wakes

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：