Computer-Aided Civil and Infrastructure Engineering最新文献

英文中文

Asphalt property prediction through high‐throughput molecular dynamics simulation 通过高通量分子动力学模拟预测沥青特性

IF 11.775 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2024-08-17 DOI: 10.1111/mice.13325

Meng Wu, Miaomiao Li, Zhanping You

The relationship between saturate, aromatic, resin, and asphaltene (SARA) contents and asphalt properties remains unclear. This study aimed to propose a high‐throughput molecular dynamics simulation framework and demonstrate its application in rapidly building asphalt molecular models of various SARA ratios and predicting their properties, using density as an example. Based on the framework, 400 models with varying SARA ratios with different aging degrees were generated to calculate their densities and used to train machine learning algorithms. The ordinary least squares model achieved R2 values exceeding 80%, and quantitative formulas linking asphalt density to SARA ratios were derived. It was found that saturate content negatively correlates with asphalt density, while resin content positively correlates with asphalt density. Additionally, asphalt density and viscosity increase with aging, influenced simultaneously by the SARA ratio and aging degree. Overall, this paper creates a rapid, high‐throughput molecular simulation pathway to predict asphalt behavior.

饱和度、芳烃、树脂和沥青质（SARA）含量与沥青性能之间的关系仍不明确。本研究旨在提出一种高通量分子动力学模拟框架，并以密度为例，展示其在快速建立不同 SARA 比率的沥青分子模型并预测其性能方面的应用。基于该框架，生成了 400 个不同 SARA 比率、不同老化程度的模型，计算出它们的密度，并用于训练机器学习算法。普通最小二乘法模型的 R2 值超过了 80%，并得出了将沥青密度与 SARA 比率联系起来的定量公式。研究发现，饱和含量与沥青密度呈负相关，而树脂含量与沥青密度呈正相关。此外，沥青密度和粘度会随着老化而增加，同时受到 SARA 比率和老化程度的影响。总之，本文创建了一种快速、高通量的分子模拟途径来预测沥青行为。

引用次数: 0

A multi-phase mechanical model of biochar–cement composites at the mesoscale 中尺度生物炭-水泥复合材料的多相力学模型

IF 8.5 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2024-08-16 DOI: 10.1111/mice.13307

Muduo Li, Xiaohong Zhu, Yuying Zhang, Daniel C. W. Tsang

This study presents a five-phase mesoscale modeling framework specifically developed to investigate crack propagation and mechanical properties of biochar–cement composites. The multi-phase model includes porous biochar particles with precise geometric construction, sand aggregates, cement matrix, and interfacial transition zone adjunct to both the biochar particles and sand aggregates. The 3D porous biochar library was first proposed and established in this study, which could provide an external interface for describing different pore shapes, wall thicknesses, and pore areas. All the simulation results were experimentally validated using a digital image correlation. Through precise geometric modeling, the unique failure modes and timing of biochar particles within the mortar were identified. This is analogous to the “strong column–weak beam” concept, accounting for the enhanced ductility observed in the biochar–cement composites under compression test. This work can advance the geometric modeling of porous aggregates broadly and elucidate their mesoscopic failure mechanisms in cementitious materials, thus providing new insights for developing high-ductility and lightweight cement composites.

本研究提出了一个五相中尺度建模框架，专门用于研究生物炭-水泥复合材料的裂纹扩展和力学性能。多相模型包括具有精确几何结构的多孔生物炭颗粒、砂集料、水泥基体以及生物炭颗粒和砂集料的界面过渡区。本研究首次提出并建立了三维多孔生物炭库，为描述不同的孔隙形状、壁厚和孔隙面积提供了外部接口。所有模拟结果都通过数字图像相关实验进行了验证。通过精确的几何建模，确定了砂浆中生物炭颗粒的独特破坏模式和时间。这类似于 "强柱-弱梁 "的概念，是生物炭-水泥复合材料在压缩试验中延展性增强的原因。这项工作可广泛推进多孔集料的几何建模，并阐明其在水泥基材料中的中观破坏机制，从而为开发高延展性和轻质水泥复合材料提供新的见解。

{"title":"A multi-phase mechanical model of biochar–cement composites at the mesoscale","authors":"Muduo Li, Xiaohong Zhu, Yuying Zhang, Daniel C. W. Tsang","doi":"10.1111/mice.13307","DOIUrl":"10.1111/mice.13307","url":null,"abstract":"<p>This study presents a five-phase mesoscale modeling framework specifically developed to investigate crack propagation and mechanical properties of biochar–cement composites. The multi-phase model includes porous biochar particles with precise geometric construction, sand aggregates, cement matrix, and interfacial transition zone adjunct to both the biochar particles and sand aggregates. The 3D porous biochar library was first proposed and established in this study, which could provide an external interface for describing different pore shapes, wall thicknesses, and pore areas. All the simulation results were experimentally validated using a digital image correlation. Through precise geometric modeling, the unique failure modes and timing of biochar particles within the mortar were identified. This is analogous to the “strong column–weak beam” concept, accounting for the enhanced ductility observed in the biochar–cement composites under compression test. This work can advance the geometric modeling of porous aggregates broadly and elucidate their mesoscopic failure mechanisms in cementitious materials, thus providing new insights for developing high-ductility and lightweight cement composites.</p>","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"39 23","pages":"3552-3572"},"PeriodicalIF":8.5,"publicationDate":"2024-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/mice.13307","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141994463","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Announcing the 2023 Hojjat Adeli Award for Innovation in Computing 宣布 2023 年 "霍贾特-阿德利计算机创新奖

IF 8.5 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2024-08-05 DOI: 10.1111/mice.13316

Gillian Greenough

引用次数: 0

Cover Image, Volume 39, Issue 16 封面图片，第 39 卷第 16 期

IF 8.5 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2024-08-05 DOI: 10.1111/mice.13318

The cover image is based on the Research Article Automated signal-based evaluation of dynamic cone resistance via machine learning for subsurface characterization by Samuel Olamide Aregbesola and Yong-Hoon Byun, https://doi.org/10.1111/mice.13294.

封面图像基于 Samuel Olamide Aregbesola 和 Yong-Hoon Byun 的研究文章《通过机器学习自动评估基于信号的动态锥体阻力，用于地下表征》，https://doi.org/10.1111/mice.13294。

引用次数: 0

Cover Image, Volume 39, Issue 16 封面图片，第 39 卷第 16 期

IF 8.5 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2024-08-05 DOI: 10.1111/mice.13317

The cover image is based on the Research Article Railway sleeper vibration measurement by trainborne laser Doppler vibrometer and its speed-dependent characteristics by Y. Zeng et al., https://doi.org/10.1111/mice.13150.

封面图片来自曾玉华等人的研究文章《列车机载激光多普勒测振仪测量铁路枕木振动及其随速度变化的特性》，https://doi.org/10.1111/mice.13150。

引用次数: 0

Self-training with Bayesian neural networks and spatial priors for unsupervised domain adaptation in crack segmentation 利用贝叶斯神经网络和空间先验进行自我训练，实现裂缝分割中的无监督域适应

IF 8.5 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2024-07-29 DOI: 10.1111/mice.13315

Pang-jo Chun, Toshiya Kikuta

This study proposes a novel self-training framework for unsupervised domain adaptation in the segmentation of concrete wall cracks using accumulated crack data. The proposed method incorporates Bayesian neural networks for uncertainty estimation of pseudo-labels, and spatial priors of cracks for screening noisy labels. Experiments demonstrate that the proposed approach achieves significant improvements in F1 score. Comparing the F1 scores, Bayesian DeepLabv3+ and Bayesian U-Net showed performance improvements of 0.0588 and 0.1501, respectively, after domain adaptation. Furthermore, the integration of Stable Diffusion for few-shot image generation enhances domain adaptation performance by 0.0332. The proposed framework enables high-precision crack segmentation with as few as 100 target images, which can be easily obtained at the site, reducing the cost of model deployment in infrastructure maintenance. The study also investigates the optimal number of iterations for domain adaptation based on the uncertainty score, providing insights for practical implementation. The proposed method contributes to the development of efficient and automated structural health monitoring using AI.

本研究提出了一种新颖的自我训练框架，用于利用累积的裂缝数据对混凝土墙裂缝进行无监督领域适应性分割。所提出的方法结合了贝叶斯神经网络来估计伪标签的不确定性，并结合了裂缝的空间先验来筛选噪声标签。实验证明，所提出的方法显著提高了 F1 分数。比较 F1 分数，贝叶斯 DeepLabv3+ 和贝叶斯 U-Net 经过领域适应后，性能分别提高了 0.0588 和 0.1501。此外，将稳定扩散整合到少帧图像生成中，域适应性能提高了 0.0332。所提出的框架只需 100 张目标图像就能实现高精度的裂缝分割，这些图像可在现场轻松获取，从而降低了在基础设施维护中部署模型的成本。该研究还根据不确定性得分研究了领域适应的最佳迭代次数，为实际应用提供了启示。所提出的方法有助于利用人工智能开发高效、自动化的结构健康监测。

{"title":"Self-training with Bayesian neural networks and spatial priors for unsupervised domain adaptation in crack segmentation","authors":"Pang-jo Chun, Toshiya Kikuta","doi":"10.1111/mice.13315","DOIUrl":"10.1111/mice.13315","url":null,"abstract":"<p>This study proposes a novel self-training framework for unsupervised domain adaptation in the segmentation of concrete wall cracks using accumulated crack data. The proposed method incorporates Bayesian neural networks for uncertainty estimation of pseudo-labels, and spatial priors of cracks for screening noisy labels. Experiments demonstrate that the proposed approach achieves significant improvements in F1 score. Comparing the F1 scores, Bayesian DeepLabv3+ and Bayesian U-Net showed performance improvements of 0.0588 and 0.1501, respectively, after domain adaptation. Furthermore, the integration of Stable Diffusion for few-shot image generation enhances domain adaptation performance by 0.0332. The proposed framework enables high-precision crack segmentation with as few as 100 target images, which can be easily obtained at the site, reducing the cost of model deployment in infrastructure maintenance. The study also investigates the optimal number of iterations for domain adaptation based on the uncertainty score, providing insights for practical implementation. The proposed method contributes to the development of efficient and automated structural health monitoring using AI.</p>","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"39 17","pages":"2642-2661"},"PeriodicalIF":8.5,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/mice.13315","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141794753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Integrated vision language and foundation model for automated estimation of building lowest floor elevation 用于自动估算建筑物最低层标高的综合视觉语言和基础模型

IF 11.775 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2024-07-26 DOI: 10.1111/mice.13310

Yu‐Hsuan Ho, Longxiang Li, Ali Mostafavi

Street view imagery has emerged as a valuable resource for urban analytics research. Recent studies have explored its potential for estimating lowest floor elevation (LFE), offering a scalable alternative to traditional on‐site measurements, crucial for assessing properties' flood risk and damage extent. While existing methods rely on object detection, the introduction of image segmentation has expanded the utility of street view images for LFE estimation, although challenges still remain in segmentation quality and capability to distinguish front doors from other doors. To address these challenges in LFE estimation, this study integrates the Segment Anything model, a segmentation foundation model, with vision language models (VLMs) to conduct text‐prompt image segmentation on street view images for LFE estimation. By evaluating various VLMs, integration methods, and text prompts, the most suitable model was identified for street view image analytics and LFE estimation tasks, thereby improving the coverage of the current LFE estimation model based on image segmentation from 33% to 56% of properties. Remarkably, our proposed method, ELEV‐VISION‐SAM, significantly enhances the availability of LFE estimation to almost all properties in which the front door is visible in the street view image. In addition, the findings present the first baseline and quantified comparison of various vision models for street view image‐based LFE estimation. The model and findings not only contribute to advancing street view image segmentation for urban analytics but also provide a novel approach for image segmentation tasks for other civil engineering and infrastructure analytics tasks.

街景图像已成为城市分析研究的宝贵资源。最近的研究探索了街景图像在估算最低楼层标高（LFE）方面的潜力，为传统的现场测量提供了一种可扩展的替代方法，这对于评估物业的洪水风险和损坏程度至关重要。虽然现有方法依赖于物体检测，但图像分割技术的引入扩大了街景图像在估算最低楼层标高方面的用途，不过在分割质量和区分前门与其他门的能力方面仍存在挑战。为了解决 LFE 估算中的这些挑战，本研究将分割基础模型 Segment Anything 模型与视觉语言模型（VLM）相结合，对街景图像进行文本提示图像分割，以用于 LFE 估算。通过评估各种 VLM、集成方法和文本提示，确定了最适合街景图像分析和 LFE 估算任务的模型，从而将当前基于图像分割的 LFE 估算模型的覆盖率从 33% 提高到 56%。值得注意的是，我们提出的 ELEV-VISION-SAM 方法显著提高了 LFE 估算的可用性，几乎适用于街景图像中可见前门的所有物业。此外，研究结果首次对基于街景图像的低频反射估算的各种视觉模型进行了基线和量化比较。该模型和研究结果不仅有助于推进城市分析中的街景图像分割，还为其他土木工程和基础设施分析任务中的图像分割任务提供了一种新方法。

{"title":"Integrated vision language and foundation model for automated estimation of building lowest floor elevation","authors":"Yu‐Hsuan Ho, Longxiang Li, Ali Mostafavi","doi":"10.1111/mice.13310","DOIUrl":"https://doi.org/10.1111/mice.13310","url":null,"abstract":"Street view imagery has emerged as a valuable resource for urban analytics research. Recent studies have explored its potential for estimating lowest floor elevation (LFE), offering a scalable alternative to traditional on‐site measurements, crucial for assessing properties' flood risk and damage extent. While existing methods rely on object detection, the introduction of image segmentation has expanded the utility of street view images for LFE estimation, although challenges still remain in segmentation quality and capability to distinguish front doors from other doors. To address these challenges in LFE estimation, this study integrates the Segment Anything model, a segmentation foundation model, with vision language models (VLMs) to conduct text‐prompt image segmentation on street view images for LFE estimation. By evaluating various VLMs, integration methods, and text prompts, the most suitable model was identified for street view image analytics and LFE estimation tasks, thereby improving the coverage of the current LFE estimation model based on image segmentation from 33% to 56% of properties. Remarkably, our proposed method, ELEV‐VISION‐SAM, significantly enhances the availability of LFE estimation to almost all properties in which the front door is visible in the street view image. In addition, the findings present the first baseline and quantified comparison of various vision models for street view image‐based LFE estimation. The model and findings not only contribute to advancing street view image segmentation for urban analytics but also provide a novel approach for image segmentation tasks for other civil engineering and infrastructure analytics tasks.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"109 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141768576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A domain adaptation methodology for enhancing the classification of structural condition states in continuously monitored historical domes 增强连续监测历史穹顶结构状态分类的领域适应方法

IF 11.775 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2024-07-26 DOI: 10.1111/mice.13313

V. Cavanni, R. Ceravolo, G. Miraglia

The unavailability of labeled data has always been the main limitation of data‐driven solutions for monitoring the health state of full‐scale structures. In this area, domain adaptation (DA) solutions have occasionally been proposed in recent years, which allow the sharing of data sets between distinct but similar systems. This paper presents a novel computational methodology to evaluate the condition state of historical buildings subjected to continuous monitoring. The DA method, specifically transfer component analysis, is used to maintain correlations between two data domains with low relevance, thereby improving the accuracy of classification models. Additionally, it is shown that the kernelized Bayesian transfer learning can enhance classification accuracy beyond what is achievable with a support vector machine. The paper is completed with a real‐world application to the classification of data sets from two Italian Baroque churches, both characterized by imposing oval masonry domes, but equipped with very different monitoring systems.

无法获得标注数据一直是数据驱动型解决方案在监测大型结构健康状况方面的主要限制因素。在这一领域，近年来偶尔会有人提出领域适应（DA）解决方案，允许不同但相似的系统共享数据集。本文介绍了一种新颖的计算方法，用于评估接受连续监测的历史建筑的状态。利用 DA 方法，特别是转移分量分析，可以保持两个相关性较低的数据域之间的相关性，从而提高分类模型的准确性。此外，研究还表明，核化贝叶斯迁移学习可以提高分类准确性，超过支持向量机的分类准确性。论文最后介绍了两个意大利巴洛克式教堂数据集分类的实际应用，这两个教堂都是气势恢宏的椭圆形砖石穹顶，但却配备了截然不同的监控系统。

引用次数: 0

Multifidelity graph neural networks for efficient and accurate mesh‐based partial differential equations surrogate modeling 多保真度图神经网络用于高效、精确的基于网格的偏微分方程代理建模

IF 11.775 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2024-07-26 DOI: 10.1111/mice.13312

Mehdi Taghizadeh, Mohammad Amin Nabian, Negin Alemazkoor

Accurately predicting the dynamics of complex systems governed by partial differential equations (PDEs) is crucial in various applications. Traditional numerical methods such as finite element methods (FEMs) offer precision but are resource‐intensive, particularly at high mesh resolutions. Machine learning–based surrogate models, including graph neural networks (GNNs), present viable alternatives by reducing computation times. However, their accuracy is significantly contingent on the availability of substantial high‐fidelity training data. This paper presents innovative multifidelity GNN (MFGNN) frameworks that efficiently combine low‐fidelity and high‐fidelity data to train more accurate surrogate models for mesh‐based PDE simulations, while reducing training computational cost. The proposed methods capitalize on the strengths of GNNs to manage complex geometries across different fidelity levels. Incorporating a hierarchical learning strategy and curriculum learning techniques, the proposed models significantly reduce computational demands and improve the robustness and generalizability of the results. Extensive validations across various simulation tasks show that the MFGNN frameworks surpass traditional single‐fidelity GNN models. The proposed approaches, hence, provide a scalable and practical solution for conducting detailed computational analyses where traditional high‐fidelity simulations are time‐consuming.

准确预测由偏微分方程（PDE）控制的复杂系统的动力学特性在各种应用中至关重要。有限元法（FEM）等传统数值方法精度高，但资源密集，尤其是在高网格分辨率下。基于机器学习的代用模型，包括图神经网络（GNN），通过减少计算时间提供了可行的替代方法。然而，它们的准确性在很大程度上取决于大量高保真训练数据的可用性。本文提出了创新的多保真度 GNN（MFGNN）框架，可有效结合低保真度和高保真度数据，为基于网格的 PDE 仿真训练更精确的代理模型，同时降低训练计算成本。所提出的方法利用了 GNN 的优势来管理不同保真度级别的复杂几何图形。结合分层学习策略和课程学习技术，所提出的模型大大降低了计算需求，提高了结果的鲁棒性和通用性。各种仿真任务的广泛验证表明，MFGNN 框架超越了传统的单一保真度 GNN 模型。因此，在传统高保真模拟耗时的情况下，所提出的方法为进行详细的计算分析提供了可扩展的实用解决方案。

{"title":"Multifidelity graph neural networks for efficient and accurate mesh‐based partial differential equations surrogate modeling","authors":"Mehdi Taghizadeh, Mohammad Amin Nabian, Negin Alemazkoor","doi":"10.1111/mice.13312","DOIUrl":"https://doi.org/10.1111/mice.13312","url":null,"abstract":"Accurately predicting the dynamics of complex systems governed by partial differential equations (PDEs) is crucial in various applications. Traditional numerical methods such as finite element methods (FEMs) offer precision but are resource‐intensive, particularly at high mesh resolutions. Machine learning–based surrogate models, including graph neural networks (GNNs), present viable alternatives by reducing computation times. However, their accuracy is significantly contingent on the availability of substantial high‐fidelity training data. This paper presents innovative multifidelity GNN (MFGNN) frameworks that efficiently combine low‐fidelity and high‐fidelity data to train more accurate surrogate models for mesh‐based PDE simulations, while reducing training computational cost. The proposed methods capitalize on the strengths of GNNs to manage complex geometries across different fidelity levels. Incorporating a hierarchical learning strategy and curriculum learning techniques, the proposed models significantly reduce computational demands and improve the robustness and generalizability of the results. Extensive validations across various simulation tasks show that the MFGNN frameworks surpass traditional single‐fidelity GNN models. The proposed approaches, hence, provide a scalable and practical solution for conducting detailed computational analyses where traditional high‐fidelity simulations are time‐consuming.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"302 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141768571","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Telescopic broad Bayesian learning for big data stream 针对大数据流的远景广义贝叶斯学习

IF 11.775 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2024-07-24 DOI: 10.1111/mice.13305

Ka‐Veng Yuen, Sin‐Chi Kuok

In this paper, a novel telescopic broad Bayesian learning (TBBL) is proposed for sequential learning. Conventional broad learning suffers from the singularity problem induced by the complexity explosion as data are accumulated. The proposed TBBL successfully overcomes the challenging issue and is feasible for sequential learning with big data streams. The learning network of TBBL is reconfigurable to adopt network augmentation and condensation. As time evolves, the learning network is augmented to incorporate the newly available data and additional network components. Meanwhile, the learning network is condensed to eliminate the network connections and components with insignificant contributions. Moreover, as a benefit of Bayesian inference, the uncertainty of the estimates can be quantified. To demonstrate the efficacy of the proposed TBBL, the performance on highly nonstationary piecewise time series and complex multivariate time series with 100 million data points are presented. Furthermore, an application for long‐term structural health monitoring is presented.

本文提出了一种用于序列学习的新型伸缩广义贝叶斯学习法（TBBL）。传统的广义贝叶斯学习存在奇异性问题，这是由于随着数据的积累，复杂性爆炸所引起的。所提出的 TBBL 成功克服了这一挑战性问题，适用于大数据流的序列学习。TBBL 的学习网络是可重构的，可采用网络增强和压缩。随着时间的推移，学习网络会不断扩大，以纳入新的可用数据和额外的网络组件。同时，对学习网络进行压缩，以消除贡献不大的网络连接和组件。此外，贝叶斯推理的一个好处是可以量化估计值的不确定性。为了证明所提出的 TBBL 的有效性，我们展示了它在高度非平稳的片断时间序列和包含 1 亿个数据点的复杂多变量时间序列上的表现。此外，还介绍了长期结构健康监测的应用。

引用次数: 0

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Computer-Aided Civil and Infrastructure Engineering

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀