检索结果-内蒙古大学图书馆

Large-scale magnetic target state estimation using model parameter optimization

MEASUREMENT SCIENCE AND TECHNOLOGY 2024年第12期35卷 126125-126125页

作者： Lu, Binjie Zhang, Xiaobing Naval Univ Engn Coll Weap Wuhan 430033 Hubei Peoples R China 92279 Unit PLA Qingdao 266209 Shandong Peoples R China

Improved grey wolf optimizer-conjugate gradient least squares (IGWO-CGLS) algorithm is proposed to solve the state estimation problems of large-scale magnetic target location, target recognition and magnetic moment estimation. To address the state estimation problem of large-scale magnetic targets, a magnetic dipole array magnetic field observation model is established based on a single magnetic vector sensor, and the magnetic target model parameter inversion based on IGWO-CGLS is used to obtain the state of the magnetic target. The state of the target is obtained by inverting the parameters of the magnetic target model. Firstly, the signal preprocessing is carried out by thresholding and down sampling to extract the complete magnetic field passing characteristics, and then the IGWO is used to optimize the magnetic target position, speed, heading and length, and then the magnetic moment parameter is calculated by CGLS to obtain the state parameters of the magnetic target. And numerical experiments are designed to sublicense the influencing factors of state estimation accuracy. The numerical simulation results show that IGWO-CGLS has higher state estimation accuracy than particle swarm optimization-CGLS, artificial hummingbird algorithm-CGLS, artificial rabbits optimization-CGLS, GWO-CGLS, IGWO-stepwise regression. The ship model test results show that IGWO-CGLS can estimate the state parameters of the ship model better.

关键词： magnetic targets magnetic dipole array models target scaling state estimation model parameter optimization swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

Predictions of sheet molding compound composite structures using probabilistic finite element simulations with bimodal Weibull strength distributions

引用

JOURNAL OF COMPOSITE MATERIALS 2025年第4期59卷 495-510页

作者： Iqbal, Sakib Xiao, Xinran Gong, Xiaojing Michigan State Univ E Lansing MI USA Univ Toulouse III Paul Sabatier CNRS UMR 5312 Inst Clement Ader ICA Tarbes France

Due to the large scatters in Sheet Molding Compound (SMC) mechanical properties, the uncertainty in the prediction of mechanical responses of SMC composite structures is significantly high as compared to that for continuous fiber composite structures. Another challenge is the size effect resulting from the scatter in mechanical strengths, i.e., the measured material flexural strength is much higher than its tensile strength. As a result, classical approaches that rely on the mean tensile strength can substantially underpredict the flexural responses in Finite Element Analysis (FEA). This work investigates the use of a material model with bimodal Weibull distributions for its strength properties in Probabilistic FE (PFE) simulations. A Random Search-based optimization procedure was developed to obtain model parameters which are difficult to determine. The material model was verified by PFE simulations of standard experiments, and then examined in simulations of open-hole tension and disk bending tests.

关键词： Discontinuous fiber composites bimodal Weibull distributions probabilistic finite element (PFE) simulations model parameter optimization random search

来源：评论

学校读者我要写书评

暂无评论

A pseudo-3D coarse-to-fine architecture for 3D medical landmark detection

引用

NEUROCOMPUTING 2025年 614卷

作者： Cui, Li Liu, Boyan Xu, Guikun Guo, Jixiang Tang, Wei He, Tao Sichuan Univ Coll Comp Sci Chengdu Peoples R China West China Hosp Stomatol Dept Oral & Maxillofacial Surg Chengdu Peoples R China Army Med Univ Daping Hosp Dept Oral & Maxillofacial Surg Chongqing Peoples R China

The coarse-to-fine architecture is a benchmark method designed to enhance the accuracy of 3D medical landmark detection. However, incorporating 3D convolutional neural networks into the coarse-to-fine architecture leads to a significant increase in model parameters, making it costly for deployment in clinical applications. This paper introduces a novel lightweight pseudo-3D coarse-to-fine architecture, consisting of a Plane-wise Attention Pseudo-3D (PA-P3D) model and a Spatial Separation Pseudo-3D (SS-P3D) model. The PAP3D inherits the lightweight structure of the general pseudo-3D and enhances cross-plane feature interaction in 3D medical images. On the other hand, the SS-P3D replaces the 3D model with three spatially separated 2D models to simultaneously detect 2D landmarks on axial, sagittal, and coronal planes. In comparison to the conventional coarse-to-fine architecture, the proposed method requires only approximately a quarter of the model parameters (60% reduced by PA-P3D and 40% reduced by SS-P3D) while simultaneously improving landmark detection performance. Experimental results demonstrate the effectiveness of the proposed method, achieving state-of-the-art performance on both a public dataset for mandibular molar landmark detection and a private dataset for cephalometric landmark detection. Overall, this paper highlights the potential of the coarse-to-fine method for cost-effective model deployment, thanks to its lightweight model structure.

关键词： 3D medical landmark detection model parameter optimization Cross-plane feature interaction

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Attention-Based Convolutional Neural Networks for Fresh-Cut Flower Classification

引用

IEEE ACCESS 2023年 11卷 17283-17293页

作者： Fei, Yeqi Li, Zhenye Zhu, Tingting Ni, Chao Nanjing Univ Sci Technol ZiJin Coll Sch Intelligent Mfg Nanjing 210046 Peoples R China Nanjing Forestry Univ Coll Mech & Elect Engn Nanjing 210037 Jiangsu Peoples R China

In the process of classifying fresh-cut flowers, the classification accuracy of the algorithm plays a vital role in the control of quality stability, uniformity, and price of fresh-cut flowers, while the classification speed of an algorithm determines the possibility of industrial application. Currently, research on fresh-cut flower classification focuses on the breakthrough of classification accuracy, ignoring the real-time processing speed of the terminal, which seriously affects the use of fresh-cut flower online classification technology. In this study, RGB images and depth information data of 434 rose flowers were collected using a binocular stereo depth camera. Combined with the actual production line classification environment, a set of data argumentation solutions was developed under the condition of limited samples. The architecture was established and optimized based on the ShuffleNet V2 network backbone unit, transfer learning was performed, and an appropriate attention mechanism was invoked to classify flowers of five specifications. The experimental results showed that the proposed network structure had a competitive advantage in terms of parameter quantity, classification speed, and accuracy compared with traditional networks without an attention mechanism and other lightweight networks. The classification accuracy on the 3-channel (RGB channel) flower dataset and the 4-channel (RGB and depth channel) flower datasets were 98.891% and 99.915%, respectively, and the overall prediction classification speed can reach 0.020 seconds per flower. Compared to the fresh-cut flower classification machines currently on the market, the speed of the proposed method has a great advantage. These advantages are of great significance for the design and development of fresh-cut flower classification and grading systems, and the proposed method is instructive for the identification and application of multichannel data in the future.

关键词： Feature extraction Production Classification algorithms Image segmentation Plants Data visualization Computer architecture Fresh-cut flower grading lightweight network attention mechanism image augmentation model parameter optimization

来源：评论

学校读者我要写书评

暂无评论

An innovative information accumulation multivariable grey model and its application in China's renewable energy generation forecasting

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年第PartA期252卷

作者： Ren, Youyang Wang, Yuhong Xia, Lin Wu, Dongdong Jiangnan Univ Sch Business Wuxi 214122 Jiangsu Peoples R China Nankai Univ Coll Tourism & Serv Management Tianjin 300350 Peoples R China

Reducing greenhouse gas emissions is urgent for the global community with rising climates. Considering the importance of renewable energy in mitigating climate warming, forecasting renewable energy generation is vital for the Chinese government's future low-carbon and green development plan. This paper proposes a novel multivariable grey model based on historical data on China's renewable energy generation and three industries. A novel information accumulation mechanism with two adaptive factors is designed to improve the traditional multivariable grey modeling defect. Based on the proposed mechanism, this paper optimizes the initial and background values and nonlinear model structure with the whale optimization algorithm. The forecasting results show that the fitting MAPE is 1.13%, comprehensive MAPE is 2.60%, MSE is 50.86, and RMSE is 7.13, which significantly improve the forecasting accuracy of traditional GM(1,N) and are better than other compared models. The forecasting results show that China's renewable energy generation will gradually increase to 5834.02 TWh. The Chinese government should keep the previous Five-Year Plans rising trend of the three industries in the future Five-Year Plans to support renewable energy industries. In China's future energy system, it is necessary to promote incentive policies and capital investment for actively accelerated development to make renewable energy the leading force.

关键词： Multivariate grey model Data information accumulation model parameter optimization Renewable energy generation

来源：评论

学校读者我要写书评

暂无评论

Robot motion visual measurement based on RANSAC and weighted constraints method

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2024年第3期35卷 035012-035012页

作者： Wu, Lulu Deng, Xianglin Wang, Yuan Du, Xin Jiang, Benchi Anhui Polytech Univ Sch Artificial Intelligence Wuhu 241000 Peoples R China Anhui Polytech Univ Sch Mech Engn Wuhu 241000 Peoples R China

Precision of the coordinate transformation model parameters is crucial for the accuracy of the vision-based robot spatial motion measurement method. In this work, an optimization algorithm integrating RANSAC and iterative weighted singular value decomposition (IR-SVD) is proposed for improving the coordinate transformation model solution precision, aiming at enhancing the spatial motion measurement accuracy of the binocular vision system. Considering noises existing in reference transformation point pairs, the RANSAC algorithm is introduced to filter the raw measurement point pairs and extract inliers, thereby eliminating potential gross errors and realizing the cluster of advantageous points. An enhanced SVD method based on iterative weighted constraints is proposed to substitute traditional SVD. After calculating the coordinate transformation model parameters, the measurement errors of inliers are solved synchronously, and the weights are reallocated in light of the measurement errors value, subsequently recalculating the coordinate transformation model parameters repeatedly until the errors converge. The validation experiments are conducted on the self-built three-degree-of-freedom rectangular coordinate robot platform. The experimental results of discrete point-to-point motion and continuous trajectory motion measurement show that the proposed method can improve the coordinate transformation model parameters solution accuracy effectively, comparing with the traditional SVD method. Comparative experiment with existing commonly used coordinate transformation methods including Quaternion and iterative closest point indicates that the proposed method exhibits the best applicability and minimal errors in robot motion visual measurement. Both accuracy of the coordinate transformation model solution and the visual system's motion measurement are enhanced with this newly-proposed, optimized method.

关键词： robot spatial motion visual measurement model parameter optimization RANSAC IR-SVD

来源：评论

学校读者我要写书评

暂无评论

An efficient two-step optimization method for mass exchanger network synthesis

引用

CHEMICAL ENGINEERING SCIENCE 2023年第1期273卷

作者： Xu, Yue Cui, Guomin Shen, Shuqi Xiao, Yuan Zhang, Guanhua Yang, Qiguo Univ Shanghai Sci & Technol Sch Energy & Power Engn 516 Jungong Rd Shanghai 200093 Peoples R China

Mass exchanger networks have been considered a promising solution for reducing impurity in streams and maximizing energy recovery in the chemical industry. This paper adjusts two non-structural models with distinct optimization variables and a heuristic algorithm according to the MEN synthesis character-istics. Considering the requirement of the objective function, a two-step optimization method that com-bines these two models is proposed. In the first step, a feasible solution is determined by the model using the transferred mass as an optimization variable. In the second step, the aforementioned model is employed to maximize tray utilization by adopting the tray number as an optimization variable. The results of the two cases obtained by the proposed method are 406,330 $/yr and 329,326 $/yr, which are lower than the published results, and is verified on two cases regarding quality and efficiency. (c) 2023 Elsevier Ltd. All rights reserved.

关键词： Mass exchanger network Heat exchanger network Nodes-based non-structural model model parameter optimization Non-convex nature

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal analysis of illegal Coilia nasus fishing linked to suitable habitats modeled with MaxEnt in China

引用

Journal for Nature Conservation 2025年 86卷

作者： Wei, Suhang Zhong, Junjie Qiu, Songyin Sun, Xiaodong Pan, Mingjie Lin, Yingying Chen, Qin Niu, Bing School of Life Sciences Shanghai University Shanghai 200444 China Chinese Academy of Inspection and Quarantine Beijing 100176 China

Coilia nasus is an endangered freshwater fish in China. Due to overfishing and ecological environment deterioration, its resources are rapidly declining and even facing the risk of extinction. Therefore, conservation measures must be taken immediately to ensure the sustainable resources of C. nasus. The purpose of this study is to predict the suitable habitats of C. nasus in the Yangtze River and to make a spatiotemporal and geographical analysis of the illegal fishing cases of C. nasus in the Yangtze River as part of the conservation efforts. In this study, the MaxEnt model was used to predict the suitable habitats of C. nasus, and the distribution characteristics of illegal fishing cases involving C. nasus were revealed through a spatiotemporal geographic analysis. Based on the collected data of 19 climatic variables, three topographic variables and one flow accumulation variable, we constructed the MaxEnt model, optimized the parameter settings of the MaxEnt software, and called the R package Kuenm to screen and determine the optimal parameters from the MaxEnt model with 1240 different parameter combinations, and predicted the suitable habitats of the C. nasus in the Yangtze River Basin. The results showed that the main breeding areas of C. nasus were mainly concentrated in Chongqing in the upper reaches of the Yangtze River and Jiangsu Province and Shanghai in the middle and lower reaches of the Yangtze River, which had suitable hydrological and topographic conditions for C. nasus survival. In addition, river flow accumulation and temperature are the main variables affecting the distribution of C. nasus in the Yangtze River. At the same time, we analyzed the spatial and temporal distribution of illegal fishing cases of C. nasus and found that there were relatively serious illegal fishing activities in Chongqing and Shanghai, especially in highly suitable habitats areas, where illegal fishing cases broke out frequently, and suggested that high-suitability areas s

关键词： Ecological modeling Freshwater fish protection model parameter optimization Species distribution Yangtze River

来源：评论

学校读者我要写书评

暂无评论

Accurate classification of ECG arrhythmia using MOWPT enhanced fast compression deep learning networks

引用

JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING 2020年第5期14卷 5703-5720页

作者： Huang, Jing-Shan Chen, Bin-Qiang Zeng, Nian-Yin Cao, Xin-Cheng Li, Yang Xiamen Univ Sch Aerosp Engn Xiamen 361005 Fujian Peoples R China

Accurate classification of electrocardiogram (ECG) signals is of significant importance for automatic diagnosis of heart diseases. In order to enable intelligent classification of arrhythmias with high accuracy, an accurate classification method based intelligent ECG classifier using the fast compression residual convolutional neural networks (FCResNet) is proposed. In the proposed method, the maximal overlap wavelet packet transform (MOWPT), which provides a comprehensive time-scale paving pattern and possesses the time-invariance property, was utilized for decomposing the original ECG signals into sub-signal samples of different scales. Subsequently, the samples of the five arrhythmia types were utilized as input to the FCResNet such that the ECG arrhythmia types were identified and classified. In the proposed FCResNet model, a fast down-sampling module and several residual block structural units were incorporated. The proposed deep learning classifier can substantially alleviate the problems of low computational efficiency, difficult convergence and model degradation. parameter optimizations of the FCResNet were investigated via single-factor experiments. The datasets from MIT-BIH arrhythmia database were employed to test the performance of the proposed deep learning classifier. An averaged accuracy of 98.79% was achieved when the number of the wide-stride convolution in fast down-sampling module was set as 2, the batch size parameter was set as 20 and wavelet subspaces of low frequency bands in MOWPT were selected as input of the classifier. These analysis results were compared with those generated by some comparison methods to validate the superiorities and enhancements of the proposed method.

关键词： Electrocardiogram (ECG) Arrhythmia classification Maximal overlap wavelet packets transform (MOWPT) Fast compression Convolutional neural networks model parameter optimization

来源：评论

学校读者我要写书评

暂无评论

An adaptive non-equidistant grey model with four parameters and its applications in deformation monitoring

引用

Scientific reports 2025年第1期15卷 18700页

作者： Shuang Yang Changchun Li Jiao Fu Huanqin Ma College of Mathematics Education China West Normal University Nanchong 637009 China. School of Mathematics and Information China West Normal University Nanchong 637009 China.

The processing and analysis of deformation monitoring data, as well as the establishment of effective forecasting models, form the foundation for assessing whether deformation is within a safe range and for selecting appropriate preventive and disaster reduction measures. Conventional forecasting models are difficult to accurately forecast future phenomena by analyzing deformation data with non-equidistant characteristic, so a non-equidistant grey model has emerged. The article optimizes the traditional non-equidistant grey model from three aspects, thus proposing an adaptive non-equidistant grey model with four parameters, which contains nonlinear and linear terms as well as stochastic perturbation term. First, the nonlinear function is used as a new grey action quantity in order to comprehensively reflect the grey information that affects the development of the system. Second, the particle swarm optimization algorithm is used to optimize the background value so that it can be adaptively adjusted according to the sequence characteristics as well as to obtain a mutually matching model structure based on the integral theory. Third, the optimal selection of initial value with the minimum relative error sum of squares as the objective function further enhances the model optimization. Finally, the model is applied to forecast three kinds of deformation monitoring for high-rise building settlement, highway soft soil roadbed settlement, and mining area GNSS settlement. The results show that the performance of the novel model is significantly better than the existing model, thus verifying its effectiveness and superiority.

关键词： Deformation monitoring model parameter optimization model structure optimization Non-equidistant grey model

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：