检索结果-内蒙古大学图书馆

predictive model-Based Correction of Magnetic Sensor Array Sway Errors

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2024年 62卷

作者： Lu, Zhiyu Yang, Li Wang, Bin Wu, Kun Li, Yongxin Zheng, Xiaoping Southwest Minzu Univ Sch Elect & Informat Chengdu 610054 Peoples R China Tsinghua Univ Dept Automat Beijing 100084 Peoples R China

Magnetic sensor arrays are typically used to detect magnetic targets. Currently, research on sensor array calibration focuses on solving the problems of inconsistent sensitivity, zero offset, and non-orthogonality in individual sensors, and misalignment errors between sensors. However, in magnetic field detection, sensor arrays are usually mounted on a platform or carried as a handheld device and are prone to random swaying during the detection process, leading to changes in the attitude and position of the magnetic sensors, which in turn generates swaying errors. In this study, the source of swaying error in sensor arrays was first analyzed theoretically, and a swaying error model of a magnetic sensor was established. Second, a swaying error calibration method was proposed in combination with the classical prediction model-Gaussian process regression (GPR), backpropagation (BP) neural network, and support vector machine (SVM) in the field of artificial intelligence. The experimental results show that the prediction performance based on the BP neural network is the most outstanding. After correction, the relative error percentage of the swaying error in the magnetic field data decreased significantly from 165.50% to 9.35%, which is a significant improvement of the correction effect. In addition, we conducted model comparison experiments in different environments, and the results show that the BP model performs well in various environments, demonstrating its strong generalization ability and robustness. Finally, the distance error of the magnetic dipole position was significantly reduced after calibration, from 1.56, 1.12, and 2.50 m to 0.17, 0.04, and 0.04 m, respectively. Thus, the effectiveness of the calibration method was verified.

关键词： Magnetic field measurement Sensor arrays Magnetic resonance imaging Magnetic sensors Vectors Measurement uncertainty Magnetometers Calibration Measurement errors predictive models Error correction magnetic sensor array predictive model

来源：评论

学校读者我要写书评

暂无评论

predictive model of lunar soil drilling resistance considering axis inclination

引用

ADVANCES IN SPACE RESEARCH 2025年第1期75卷 1565-1584页

作者： Zhou, Jun Liu, Tianxi Zhao, Yang Harbin Inst Technol Sch Astronaut Harbin 150001 Peoples R China

The axis inclination of a slender spiral drill tool is inevitable while drilling and sampling lunar soil;this alters the stress situation of the drill tool. In this paper, the interaction process between the drill tool and lunar soil is simplified and equated to the process of cylindrical cavity expansion caused by bit penetration and the process of soil agitation caused by the inclined auger, and the predictive model of drilling resistance is constructed. The sensitivities of the main soil mechanical parameters are analyzed, and it indicates that cohesion, soil pressure coefficient, and gravitational acceleration have an obvious positive effect on drilling resistance. A simulated lunar soil drilling test is conducted, and the effectiveness of the drilling resistance predictive model are verified by comparing the test and simulation results, providing theoretical support for technological breakthroughs in other extraterrestrial drilling and sampling missions. (c) 2024 COSPAR. Published by Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.

关键词： Lunar soil drilling and sampling Drilling resistance predictive model Ground test

来源：评论

学校读者我要写书评

暂无评论

predictive model for assessing the nonlinear surface displacement and mechanical response of shallowly buried tunnels under dip-slip fault dislocation

引用

SOIL DYNAMICS AND EARTHQUAKE ENGINEERING 2025年 191卷

作者： Wang, Mingnian Yang, Henghong Yu, Li Zhang, Xiao Southwest Jiaotong Univ Sch Civil Engn Chengdu 610036 Peoples R China Southwest Jiaotong Univ State Key Lab Intelligent Geotech & Tunnelling Chengdu 610036 Peoples R China

The fault dislocation induces permanent ground surface displacement, leading to severe damage to tunnels. However, there is a notable scarcity of predictive models for nonlinear surface displacement and tunnel response under dip-slip fault dislocation. Previous analytical models have oversimplified surface displacement to a constant value. To this end, first, a predictive model for assessing the mechanical response of shallowly buried tunnels under dip-slip fault dislocation is established. Then, through a mathematical statistical analysis of field- measured data, a prediction method of nonlinear dip-slip surface displacement has been developed, and the nonlinear dip-slip surface displacement is introduced into the predictive model. The predictive model incorporates nonlinear surface displacement, fault zone width, and geometric nonlinearity, thereby markedly enhancing the accuracy of the calculation results. Secondly, the prediction model undergoes validation through experimental tests and numerical simulations, revealing a maximum error of 3.7 %. In contrast, neglecting nonlinear surface displacement can result in calculation errors as high as 517.5 %. Finally, the proposed predictive model is applied to conduct a parameter analysis, such as maximum surface displacement (Delta dmax), dip angle (alpha), and fault zone width (WF). The results shown that the maximum axial force (Nmax), maximum shear force (Vzmax), and maximum bending moment (Mzmax) of the tunnel increase with the augmentation of Delta dmax. For each incremental increase of 0.2 m in Delta dmax, the Nmax, Vzmax, and Mzmax exhibit an approximate increase of 22.1 %-100.3 %. The Nmax and decreases with the increasing alpha, whereas both the Vzmax and the Mzmax increase as alpha rises. With each incremental increase of 10 degrees in alpha, the Nmax diminishes by approximately 16.1 %-49.2 %, while both the Vzmax and Mzmax experience an increase ranging from about 4.6 % to 19.1 %. An increase in WF results i

关键词： Dip-slip faults Tunnel engineering predictive model Tunnel response Nonlinear surface displacement

来源：评论

学校读者我要写书评

暂无评论

predictive model-based multi-objective optimization with life-long meta-learning for designing unreliable production systems

引用

COMPUTERS & OPERATIONS RESEARCH 2025年 178卷

作者： Mahmoodi, Ehsan Fathi, Masood Ng, Amos H. C. Dolgui, Alexandre Univ Skovde Sch Engn Sci Div Intelligent Prod Syst Skovde 54128 Sweden Uppsala Univ Dept Civil & Ind Engn Div Ind Engn & Management Uppsala Sweden CNRS IMT Atlant LS2N La Chantrerie4rue Alfred Kastler F-44307 Nantes 3 France

Owing to the realization of advanced manufacturing systems, manufacturers have more flexibility in improving their processes through design decisions. Design decisions in production lines primarily involve two complex problems: buffer and resource allocation (B&RA). The main aim of B&RA is to determine the best location and size of buffers in the production line and optimally allocate production resources, such as operators and machines, to workstations. Inspired by a real-world case from the marine engine production industry, this study addresses B&RA in high-mix, low-volume hybrid flow shops (HFSs) with feed-forward quality inspection. These HFSs can be characterized by uncertainties in demand, material handling, processing times, and quality control. In this study, the production environment is modeled via discrete-event simulation, which reflects the features of the actual system without requiring unreasonable or restrictive assumptions. To replace the expensive simulation runs, five widely used regressor machine learning algorithms in manufacturing are trained on data sampled from the simulation model, and the best-performing algorithm is selected as the predictive model. To obtain high-quality solutions, the predictive model is coupled with an enhanced non-dominated sorting genetic algorithm (En-NSGA-II) that incorporates lifelong meta-learning and features a customized representation and a variable neighborhood search. Additionally, a post-optimality analysis using a pattern-mining algorithm is performed to generate knowledge for allocating buffers and operators based on the optimization results, thus providing promising managerial insights.

关键词： Multi-objective optimization Simulation predictive model Meta-learning Buffer allocation Resource allocation

来源：评论

学校读者我要写书评

暂无评论

predictive model in silicon and pathogenicity mechanism of metabolic syndrome: Impacts of heavy metal exposure

引用

JOURNAL OF ENVIRONMENTAL MANAGEMENT 2025年 373卷 124001页

作者： Zhou, Jing-Xuan Zheng, Zi-Yi Peng, Zhao-Xing Yang, Yu-Ting Ni, Hong-Gang Peking Univ Shenzhen Grad Sch Sch Urban Planning & Design Shenzhen 518055 Peoples R China

Although the association between heavy metals in human and the development of metabolic syndrome (MetS) have been extensively studied, the pathogenic mechanism of MetS affected by metals is not clear to date. In this study, a predictive model was developed with machine learning base on the large-scale dataset. These proposed models were evaluated via comparatively analysis of their accuracy and robustness. With the optimal model, two metals significantly correlated with MetS were screened and were employed to infer the pathogenicity mechanism of MetS via molecular docking. Significant associations between heavy metals and MetS were found. Molecular docking provided insights into the interactions between metal ions and key protein receptors involved in metabolic regulation, suggesting a mechanism by which heavy metals interfere with metabolic functions. Specifically, Ba and Cd affect the development of MetS thru their interactions with insulin and estrogen receptors. This study attempted to explore heavy metals' potential roles in MetS at the molecular level. These findings emphasize the importance of addressing environmental exposures in the prevention and treatment of MetS.

关键词： predictive model Metabolic syndrome Heavy metal Pathogenesis Molecular docking

来源：评论

学校读者我要写书评

暂无评论

predictive model for Bark Beetle Outbreaks in European Forests

引用

FORESTS 2024年第7期15卷 1114页

作者： Fernandez-Carrillo, Angel Franco-Nieto, Antonio Yague-Ballester, Maria Julia Gomez-Gimenez, Marta GMV Remote Sensing & Geospatial Analyt Isaac Newton 11 Tres Cantos 28760 Spain

Bark beetle outbreaks and forest mortality have rocketed in European forests because of warmer winters, intense droughts, and poor management. The methods developed to predict a bark beetle outbreak have three main limitations: (i) a small-spatial-scale implementation;(ii) specific field-based input datasets that are usually hard to obtain at large scales;and (iii) predictive models constrained by coarse climatic factors. Therefore, a methodological approach accounting for a comprehensive set of environmental traits that can predict a bark beetle outbreak accurately is needed. In particular, we aimed to (i) analyze the influence of environmental traits that cause bark beetle outbreaks;(ii) compare different machine learning architectures for predicting bark beetle attacks;and (iii) map the attack probability before the start of the bark beetle life cycle. Random Forest regression achieved the best-performing results. The predicted bark beetle damage reached a high robustness in the test area (F1 = 96.9, OA = 94.4) and showed low errors (CE = 2.0, OE = 4.2). Future improvements should focus on including additional variables, e.g., forest age and validation sites. Remote sensing-based methods contributed to detecting bark beetle outbreaks in large extensive forested areas in a cost-effective and robust manner.

关键词： remote sensing bark beetles forest pest management machine learning predictive model predisposition disturbance

来源：评论

学校读者我要写书评

暂无评论

predictive model of Endodontic Access in Maxillary Central Incisors Using Cone Beam Computed Tomography

ENGINEERING REPORTS

引用

ENGINEERING REPORTS 2025年第5期7卷

作者： Llacer-Martinez, Maria Sanz, Maria T. Jovani-Sancho, Mar Biedma, Benjamin Martin Radford, Elisabet Palazon Univ Cardenal Herrera CEU Fac Ciencias Salud Dept Odontol Valencia Spain Univ Valencia Dept Didact Matemat Valencia Spain Univ Santiago De Compostela Dept Cirugia & Especial Med Quirurg Santiago De Compostela Spain

Root canal access is essential for successful root canal treatment, yet it poses significant risks in teeth with calcified or constricted canals, such as root perforation or excessive loss of healthy dentin. The aim of this study was to develop a predictive model that could guide the design of a conservative, accurate endodontic access in maxillary central incisors using cone beam computed tomography (CBCT). In this retrospective cross-sectional study, CBCT scans from 135 maxillary central incisors were analyzed to obtain anatomical and demographic data. Twenty-four variables significantly correlated with three key aspects of access design-access starting point, depth to the pulp horn, and access angle (target variables). Mathematical functions were formulated using non-linear regression, and the resultant model was validated for the three target variables with a new set of 18 maxillary central incisors (R-2 > 0.68, W > 0.90). The results showed that age, tooth length, and specific CBCT-derived parameters, such as starting point, angle, and depth, which are related to the tooth's access opening, strongly influenced the predicted access cavity parameters. This predictive model has the potential to be integrated into dynamic navigation software, optimizing endodontic access and reducing iatrogenic errors for practitioners.

关键词： cone beam computed tomography endodontic access cavity endodontic planning and root canal treatment navigation system predictive model

来源：评论

学校读者我要写书评

暂无评论

predictive model for the interface bond strength of geosynthetic-reinforced asphalt layers

引用

GEOTEXTILES AND GEOMEMBRANES 2024年第4期52卷 841-854页

作者： Silva, M. P. S. Zornberg, J. G. Correia, N. S. Univ Fed Sao Carlos Civil Engn Dept Washington Luis Rdkm 235 BR-13565905 Sao Carlos SP Brazil Univ Texas Austin Civil Engn Dept Univ Stn C1792 Austin TX 78712 USA

Innovation in the use of geosynthetics in roadway applications has resulted in the development of several different products, such as asphalt reinforcement geogrids and paving mats to minimize reflective cracks and limit moisture infiltration. For a proper performance of the reinforced asphalt systems, an adequate interface bond strength has proven to be crucial. However, the influence of the different paving interlayer characteristics, combined with tack coat types, and tack coat rates on the interface bond strength remains unclear. In this study, a comprehensive program of interface shear tests was conducted using Leutner shear device and laboratoryprepared reinforced asphalt specimens. The program involved eight geosynthetic types, two tack coat types, and three application rates. Results revealed that the geosynthetic type, tack coat type and rate, as well as the interactions among the parameters significantly affect interface bond strength. Multiple linear regression analysis indicated that geogrid aperture area, geosynthetic thickness, geotextile backing thickness, and the presence of bitumen coating are the most affecting parameters on bond strength. A predictive model for the bond strength based on geosynthetic parameters is presented. Based on literature results for specimens extracted from the field, the proposed predictive models were found to adequately predict interface bond strength.

关键词： Geosynthetics Asphalt layer Reinforced asphalt system Interface bond strength Geosynthetics parameters predictive model

来源：评论

学校读者我要写书评

暂无评论

predictive model for initial response to first-line treatment in children with infantile epileptic spasms syndrome

引用

ITALIAN JOURNAL OF PEDIATRICS 2025年第1期51卷 1-12页

作者： Ge, Wenrong Wan, Lin Wang, Zong Fu, Lijun Yang, Guang Capital Med Univ Beijing Friendship Hosp Dept Paediat Beijing Peoples R China Peoples Liberat Army Gen Hosp Senior Dept Pediat Med Ctr 7 Beijing 100000 Peoples R China Chinese Peoples Liberat Army Gen Hosp Med Ctr 1 Dept Paediat Beijing Peoples R China Chinese Acad Sci Shenyang Inst Comp Technol Shenyang 110168 Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Shandong Univ Lab Big Data & Artificial Intelligence Technol Jinan Peoples R China Chinese Peoples Liberat Army Med Sch Beijing Peoples R China Southern Med Univ Sch Clin Med 2 Guangzhou Peoples R China

BackgroundPrevious studies have suggested that factors such as the treatment interval and aetiology may influence the initial response rate to first-line treatment for infantile epileptic spasms syndrome (IESS). However, few children with IECSS have undergone clinically accessible tests to determine the *** a dataset from our previously published research, we constructed and tested a predictive model for the initial response to first-line treatment in children with IESS. Random sampling and 5-fold cross-validation were performed, with synthetic minority oversampling technique to correct data imbalance. Machine learning algorithms and evaluation metrics optimised model accuracy and *** study included 532 children with IESS who had completed monotherapy first-line treatment, of whom 160 achieved an initial response. The model's accuracy, F1 score, and area under the curve (AUC) in the validation set were 0.7836 +/- 0.0229 (ranging from 0.75167 to 0.80536), 0.7833 +/- 0.0229 (ranging from 0.75145 to 0.80531), and 0.8516 +/- 0.0165 (ranging from 0.82468 to 0.86936), respectively. Factors such as the age of seizure onset, age of spasm onset, lead time, MRI subtype, treatment choice, and age at treatment consistently ranked in the top six for importance in contributing to the *** study findings suggest that this model may help effectively predict the initial response to first-line treatment, supporting clinical decision-making for children with IESS. Key predictors such as the age of seizure onset and MRI subtype enable early, data-driven intervention strategies in clinical practice.

关键词： Infantile epileptic spasms syndrome (IESS) First-line treatment Initial response predictive model

来源：评论

学校读者我要写书评

暂无评论

predictive model for resistant starch (RS) in rice (Oryza sativa L.) based on digestibility factors

引用

JOURNAL OF PLANT BIOCHEMISTRY AND BIOTECHNOLOGY 2025年 1-18页

作者： Rahaman, Sohel Awana, Monika Goswami, Deepanyeta Kumari, Sweta Bollinedi, Haritha Anand, Anjali Dash, Sukanta Rao, Mahesh Singh, Archana Singh, A. K. Krishnan, Veda ICAR Indian Agr Res Inst Div Biochem Food Matrix Lab New Delhi India ICAR Indian Agr Res Inst Div Genet New Delhi India ICAR Indian Agr Res Inst Div Plant Physiol New Delhi India ICAR Indian Agr Stat Res Inst Div Design Expt New Delhi India Natl Inst Plant Biotechnol NIPB New Delhi India

Altering the digestibility of starch to enhance the resistance to digestion, specifically targeting the creation of resistant starch (RS), holds significant importance in the fields of agriculture, food, and nutrition. This modification not only restricts the amplitude of glycemic response but also promotes gut health. Traditionally, quantifying RS has relied on complex, time-consuming, and costly human digestion simulation assays. Acknowledging the association between starch digestibility and various factors, such as microstructure, gelatinization temperature, total starch (TS), total amylose, and amylopectin, this study aimed to establish a fundamental relationship among these explanatory variables and RS through the development of a forecasting model known as the starch quality matrix (SQM). Constructed using Pearson's correlation, the SQM proved to be significant based on model statistics, and the regression model's adequacy was confirmed through residual diagnosis. Notably, both TS and total amylose content exhibited a significantly positive impact on RS, with coefficients of 0.030 and 0.024, respectively. model validation utilized root mean square error and mean absolute error. The correlation between RS and inherent glycemic potential was further verified through in-house developed in-vitro starch hydrolyzation kinetics. This study unveils, for the first time, a perspective on the relationship influencing starch digestibility and introduces the SQM tool. This tool is poised to facilitate future efforts in breeding high-RS rice varieties with a low glycemic index.

关键词： Starch quality Resistant starch Starch quality matrix predictive model Glycemic potential

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：