检索结果-内蒙古大学图书馆

atomes: Analysis, visualization, edition and post-processing of 3D atomic scale models

COMPUTATIONAL MATERIALS SCIENCE 2025年 253卷

作者： Le Roux, Sebastien Univ Strasbourg CNRS Inst Phys & Chim Mat Strasbourg UMR 7504 23 Rue LoessBP 43 F-67034 Strasbourg 2 France

atomes is a cross-platform open source program developed to analyze, to visualize and to edit/create large three-dimensional atomic scale models. By regrouping advanced analysis techniques, 3D visualization and 3D edition, atomes introduces innovative 3D rendering possibilities and intuitive applications of the calculation results. atomes also provides an advanced input preparation system for further calculations using well known classical, ab-initio and QM-MM molecular dynamics codes. To prepare the input files for these calculations is likely to be the key, and most complicated step towards MD simulations. atomes offers a user-friendly assistant to help and guide the user step by step to achieve this crucial step.

关键词： Software Open source Atomic scale modeling 3D models Crystal builder Surface passivation model analysis model visualization model creation model edition

来源：评论

学校读者我要写书评

暂无评论

Development and validation of a multimodal model in predicting severe acute pancreatitis based on radiomics and deep learning

引用

INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS 2024年 184卷 105341-105341页

作者： Yin, Minyue Lin, Jiaxi Wang, Yu Liu, Yuanjun Zhang, Rufa Duan, Wenbin Zhou, Zhirun Zhu, Shiqi Gao, Jingwen Liu, Lu Liu, Xiaolin Gu, Chenqi Huang, Zhou Xu, Xiaodan Xu, Chunfang Zhu, Jinzhou Soochow Univ Affiliated Hosp 1 Dept Gastroenterol Suzhou 215006 Jiangsu Peoples R China Suzhou Clin Ctr Digest Dis Suzhou 215006 Jiangsu Peoples R China Jiangsu Univ Jintan Hosp Dept Gen Surg Changzhou 213299 Jiangsu Peoples R China Soochow Univ Sch Comp Sci & Technol Suzhou 215006 Jiangsu Peoples R China Soochow Univ Changshu Hosp Changshu Peoples Hosp 1 Dept Gastroenterol Suzhou 215500 Jiangsu Peoples R China Peoples Hosp Hunan Prov Dept Hepatobiliary Surg Changsha 410002 Hunan Peoples R China Soochow Univ Affiliated Hosp 2 Dept Obstet & Gynaecol Suzhou 215004 Jiangsu Peoples R China Soochow Univ Affiliated Hosp 1 Dept Radiol Suzhou 215006 Jiangsu Peoples R China Harbin Med Univ Affiliated Hosp 1 Minist Educ Key Lab Hepatosplen Surg Harbin 150000 Peoples R China Soochow Univ Changshu Affiliated Hosp Dept Gastroenterol 1 Shuyuan St Suzhou 215500 Jiangsu Peoples R China Soochow Univ Affiliated Hosp 1 Dept Gastroenterol 188 Shizi St Suzhou 215006 Jiangsu Peoples R China

Objective: Aim to establish a multimodal model for predicting severe acute pancreatitis (SAP) using machine learning (ML) and deep learning (DL). Methods: In this multicentre retrospective study, patients diagnosed with acute pancreatitis at admission were enrolled from January 2017 to December 2021. Clinical information within 24 h and CT scans within 72 h of admission were collected. First, we trained model alpha based on clinical features selected by least absolute shrinkage and selection operator analysis. Second, radiomics features were extracted from 3D-CT scans and model beta was developed on the features after dimensionality reduction using principal component analysis. Third, model gamma was trained on 2D-CT images. Lastly, a multimodal model, namely PrismSAP, was constructed based on aforementioned features in the training set. The predictive accuracy of PrismSAP was verified in the validation and internal test sets and further validated in the external test set. model performance was evaluated using area under the curve (AUC), accuracy, sensitivity, specificity, recall, precision and F1-score. Results: A total of 1,221 eligible patients were randomly split into a training set (n = 864), a validation set (n = 209) and an internal test set (n = 148). Data of 266 patients were for external testing. In the external test set, PrismSAP performed best with the highest AUC of 0.916 (0.873-0.960) among all models [model alpha: 0.709 (0.618-0.800);model beta: 0.749 (0.675-0.824);model gamma: 0.687 (0.592-0.782);MCTSI: 0.778 (0.698-0.857);RANSON: 0.642 (0.559-0.725);BISAP: 0.751 (0.668-0.833);SABP: 0.710 (0.621-0.798)]. Conclusion: The proposed multimodal model outperformed any single-modality models and traditional scoring systems.

关键词： Multimodal fusion Machine learning Deep learning Severe acute pancreatitis model visualization

来源：评论

学校读者我要写书评

暂无评论

Predicting the thermal protective performance of flame-retardant fabric based on machine learning

引用

INTERNATIONAL JOURNAL OF CLOTHING SCIENCE AND TECHNOLOGY 2024年第2期36卷 226-240页

作者： Li, Boyi Tian, Miao Liu, Xiaohan Li, Jun Su, Yun Ni, Jiaming Donghua Univ Coll Fash & Design Shanghai Peoples R China

PurposeThe purpose of this study is to predict the thermal protective performance (TPP) of flame-retardant fabric more economically using machine learning and analyze the factors affecting the TPP using model ***/methodology/approachA total of 13 machine learning models were trained by collecting 414 datasets of typical flame-retardant fabric from current literature. The optimal performance model was used for feature importance ranking and correlation variable analysis through model *** models with better performance were screened, all of which showed R2 greater than 0.96 and root mean squared error less than 3.0. Heat map results revealed that the TPP of fabrics differed significantly under different types of thermal exposure. The effect of fabric weight was more apparent in the flame or low thermal radiation environment. The increase in fabric weight, fabric thickness, air gap width and relative humidity of the air gap improved the TPP of the *** implicationsThe findings suggested that the visual analysis method of machine learning can intuitively understand the change trend and range of second-degree burn time under the influence of multiple variables. The established models can be used to predict the TPP of fabrics, providing a reference for researchers to carry out relevant ***/valueThe findings of this study contribute directional insights for optimizing the structure of thermal protective clothing, and introduce innovative perspectives and methodologies for advancing heat transfer modeling in thermal protective clothing.

关键词： Flame-retardant fabrics Thermal protective performance Machine learning model visualization

来源：评论

学校读者我要写书评

暂无评论

A novel method of modelling contact dynamics for spur gear transmission

引用

MECHANISM AND MACHINE THEORY 2024年 203卷

作者： Xu, Lixin Luo, Yuankui Hu, Ruhao Chongqing Univ State Key Lab Mech Transmiss Adv Equipment Chongqing 400044 Peoples R China Chongqing Univ Coll Mech & Vehicle Engn Chongqing 400044 Peoples R China

Taking a pair of spur gears as the research object, a contact dynamic model of the spur gear system was established based on the theories of contact mechanics and multi-body dynamics. The characteristics of the model are such that it can describe the dynamic contact behavior of a gear pairs, the meshing action of gear pairs no longer depends on the stiffness model of single and double teeth undergoing alternating meshing, and the model can be visualized in real time. In the process of modelling, firstly, the mathematical model of spur gear is established. The spur gear dynamic model is then built. Finally, the vibration responses obtained by the three methods (the propose method, the lumped parameter method and the experimental method) are compared. It is found that the proposed method is more consistent with the experimental method than the traditional lumped parameter method, which verifies the validity of the contact dynamic model of spur gear transmission. The proposed model and research results lay the foundation for research fields such as performance analysis, design optimization and fault diagnosis of gear systems.

关键词： Spur gear Contact dynamic model model visualization Vibration response Vibration test

来源：评论

学校读者我要写书评

暂无评论

Mechanistic population models for ecological risk assessment and decision support: The importance of good conceptual model diagrams

引用

INTEGRATED ENVIRONMENTAL ASSESSMENT AND MANAGEMENT 2024年第5期20卷 1566-1574页

作者： Forbes, Valery E. Accolla, Chiara Banitz, Thomas Crouse, Kristin Galic, Nika Grimm, Volker Raimondo, Sandy Schmolke, Amelie Vaugeois, Maxime Florida Atlantic Univ Dept Biol Sci Boca Raton FL 33431 USA Waterborne Environm Inc Leesburg VA USA UFZ Helmholtz Ctr Environm Res Dept Ecol Modelling Leipzig Germany Univ Minnesota Dept Ecol Evolut & Behav St Paul MN USA Syngenta Crop Protect AG Basel Switzerland US EPA Off Res & Dev Gulf Breeze FL USA Syngenta Crop Protect LLC Greensboro NC USA

The use of mechanistic population models as research and decision-support tools in ecology and ecological risk assessment (ERA) is increasing. This growth has been facilitated by advances in technology, allowing the simulation of more complex systems, as well as by standardized approaches for model development, documentation, and evaluation. Mechanistic population models are particularly useful for simulating complex systems, but the required model complexity can make them challenging to communicate. Conceptual diagrams that summarize key model elements, as well as elements that were considered but not included, can facilitate communication and understanding of models and increase their acceptance as decision-support tools. Currently, however, there are no consistent standards for creating or presenting conceptual model diagrams (CMDs), and both terminology and content vary widely. Here, we argue that greater consistency in CMD development and presentation is an important component of good modeling practice, and we provide recommendations, examples, and a free web app () for achieving this for population models used for decision support in ERAs. Integr Environ Assess Manag 2024;00:1-9. (c) 2023 SETAC Population models can be valuable tools for ecological risk assessment (ERA), and their use is growing together with improvements in modeling guidance. Communicating key features of complex population models to different stakeholders can be challenging. Standardization of conceptual model diagrams (CMDs) can facilitate model communication, evaluation, and acceptance. We propose a standard template and free web app for creating CMDs for population models used to support ERAs.

关键词： Good modeling practice Mechanistic effect models model visualization Pop-GUIDE

来源：评论

学校读者我要写书评

暂无评论

Interpreting machine-learning models in transformed feature space with an application to remote-sensing classification

引用

MACHINE LEARNING 2023年第9期112卷 3455-3471页

作者： Brenning, Alexander Friedrich Schiller Univ Jena Michael Stifel Ctr Jena MSCJ Data Driven & Simulat Loebdergraben 32 D-07743 Jena Germany Friedrich Schiller Univ Jena Dept Geog Geog Informat Sci Grp Loebdergraben 32 D-07743 Jena Germany

model-agnostic tools for the post-hoc interpretation of machine-learning models struggle to summarize the joint effects of strongly dependent features in high-dimensional feature spaces, which play an important role in semantic image classification, for example in remote sensing of landcover. This contribution proposes a novel approach that interprets machine-learning models through the lens of feature-space transformations. It can be used to enhance unconditional as well as conditional post-hoc diagnostic tools including partial-dependence plots, accumulated local effects (ALE) plots, permutation feature importance, or Shapley additive explanations (SHAP). While the approach can also be applied to nonlinear transformations, linear ones are particularly appealing, especially principal component analysis (PCA) and a proposed partial orthogonalization technique. Moreover, structured PCA and model diagnostics along user-defined synthetic features offer opportunities for representing domain knowledge. The new approach is implemented in the R package wiml, which can be combined with existing explainable machine-learning packages. A case study on remote-sensing landcover classification with 46 features is used to demonstrate the potential of the proposed approach for model interpretation by domain experts. It is most useful in situations where groups of feature are linearly dependent and PCA can provide meaningful multivariate data summaries.

关键词： Interpretable machine learning Dataset-level post-hoc interpretation Predictive modelling model visualization Feature-space transformation Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Performance Is Not Enough: The Story Told by a Rashomon Quartet

引用

JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS 2024年第3期33卷 1118-1121页

作者： Biecek, Przemyslaw Baniecki, Hubert Krzyzinski, Mateusz Cook, Dianne Warsaw Univ Technol MI2 AI Warsaw Poland Univ Warsaw MI2 AI Warsaw Poland Monash Univ Melbourne Australia

The usual goal of supervised learning is to find the best model, the one that optimizes a particular performance measure. However, what if the explanation provided by this model is completely different from another model and different again from another model despite all having similarly good fit statistics? Is it possible that the equally effective models put the spotlight on different relationships in the data? Inspired by Anscombe's quartet, this article introduces a Rashomon Quartet, that is a set of four models built on a synthetic dataset which have practically identical predictive performance. However, the visual exploration reveals distinct explanations of the relations in the data. This illustrative example aims to encourage the use of methods for model visualization to compare predictive models beyond their performance.

关键词： Data visualization Explanation model visualization Statistical learning

来源：评论

学校读者我要写书评

暂无评论

A Self-Learning Channel modeling Approach Based on Explainable Neural Network

引用

IEEE WIRELESS COMMUNICATIONS LETTERS 2023年第7期12卷 1289-1293页

作者： Xue, Pengfei Zhao, Youping Beijing Jiaotong Univ Inst Broadband Wireless Mobile Commun Sch Elect & Informat Engn Beijing 100044 Peoples R China

To improve the accuracy and generalization of channel modeling in complex scenarios, an explainable neural network (XNN)-enabled self-learning channel modeling approach is proposed. With the help of model visualization and feature importance analysis, it is shown that the XNN channel model can reveal the intrinsic relationship between the channel characteristics and system parameters. The output and input of the channel model can be represented by mathematical expressions, making the channel model more transparent and credible. The self-learning optimization training (SLOT) algorithm enables fine-tuning and self-optimization of the channel model to ensure scenario adaptation. Specifically, when predicting the path loss, the simulation results show that the root mean square error (RMSE) is consistently less than the predefined error threshold in various test scenarios at different buildings.

关键词： Machine learning explainable neural network channel modeling channel characteristics model visualization

来源：评论

学校读者我要写书评

暂无评论

Estimation of bond strength between UHPC and reinforcing bars using machine

引用

ENGINEERING STRUCTURES 2022年 262卷 1页

作者： Li, Zhijie Qi, Jianan Hu, Yuqing Wang, Jingquan Southeast Univ Sch Civil Engn Key Lab Concrete & Prestressed Concrete Struct Minist Educ Nanjing 211189 Peoples R China Southeast Univ Bridge Engn Res Ctr Southeast Univ Nanjing 211189 Peoples R China Southeast Univ Natl Prestress Engn Res Ctr Nanjing 211189 Peoples R China

Bond strength estimation plays an important role in structure engineering. This paper proposes to adopt machine learning approaches to conduct a data-driven analysis of bond strength between ultra-high perfor-mance concrete (UHPC) and reinforcing bars. To make up for the lack of experimental data, a new database is established by integrating 557 instances from several published works. A total of nine machine learning models which can be divided into three types are implemented to train the bond strength estimators based on the database, including linear models, tree models, and artificial neural networks. Four strong metrics, i.e. Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Coefficient of Determination (R2), and Ratio of Accurate Estimation (RACC), are used to evaluate the performance of models. Among them, Artificial Neural Network and Random Forest achieve great estimation performances in the top two, which far exceed the empirical formulas. They have 74% and 73% of estimated data to keep the relative error within 10%, respectively. The statistical relative importance of different factors from tree models consistently shows that the ratio of embedded depth to the diameter of reinforcing bars has a significant impact on the bond strength of UHPC, which is conformable with the observations in experiments.

关键词： Bond strength Machine learning UHPC Reinforcing bar model visualization

来源：评论

学校读者我要写书评

暂无评论

Keyhole status prediction based on voting ensemble convolutional neural networks and visualization by Grad-CAM in PAW

引用

JOURNAL OF MANUFACTURING PROCESSES 2022年 80卷 805-815页

作者： Zhou, Fangzheng Liu, Xinfeng Zhang, Xuehua Liu, Yang Jia, Chuanbao Wu, Chuansong Shandong Univ Inst Mat Joining MOE Key Lab Liquid Solid Struct Evolut & Mat Proc Jinan 250061 Peoples R China Shandong Jianzhu Univ Sch Comp Sci & Technol Jinan 250101 Peoples R China Shandong Coll Elect Technol Jinan 250200 Peoples R China

K-PAW (Keyhole Plasma Arc Welding) has a wide range of applications in welding medium-thick metal workpieces. However, the welding processes are vulnerable due to the fragile force balance on the liquid metal around the keyhole, and burn-through or lack of fusion might be caused. In order to optimize the welding quality, considerable work has been devoted to penetration/keyhole status prediction by visual sensing and deep learning algorithms. However, a single network model is challenging to extract comprehensive features of weakdiscrimination weld pool images. This paper focused on the correspondence between the topside weld pool images and the prediction/keyhole status. A novel prediction method has been proposed based on eight classical CNNs trained, compared, and fused. For these single models, the prediction accuracy is higher than 95 %, with the speed of faster than 10 frames per second (FPS). The model visualization by the Grad-CAM method was performed to show the focused feature regions clearly. Although regarded as black boxes, these prediction models are considered robust when the extracted features are consistent with the prior knowledge. KeyholeVot, a voting ensemble decision model, was established based on the selected three robust models (i.e., InceptionNetV3, InceptionResNetV2, and XceptionNet) and achieved 96.62 % evaluation accuracy.

关键词： Keyhole plasma arc welding Topside weld pool image Convolution neural network Majority voting model visualization

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：