期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到4,685篇文章
< 1 2 … 235 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
Extreme Attitude Prediction of Amphibious Vehicles Based on Improved Transformer Model and Extreme Loss Function 认领 引用
1
作者 Qinghuai Zhang Boru Jia +3 位作者 Zhengdao Zhu Jianhua Xiang Yue Liu Mengwei Li 《哈尔滨工程大学学报（英文版）》 CSCD 2026年第1期228-238,共11页
Amphibious vehicles are more prone to attitude instability compared to ships,making it crucial to develop effective methods for monitoring instability risks.However,large inclination events,which can lead to instabili... Amphibious vehicles are more prone to attitude instability compared to ships,making it crucial to develop effective methods for monitoring instability risks.However,large inclination events,which can lead to instability,occur frequently in both experimental and operational data.This infrequency causes events to be overlooked by existing prediction models,which lack the precision to accurately predict inclination attitudes in amphibious vehicles.To address this gap in predicting attitudes near extreme inclination points,this study introduces a novel loss function,termed generalized extreme value loss.Subsequently,a deep learning model for improved waterborne attitude prediction,termed iInformer,was developed using a Transformer-based approach.During the embedding phase,a text prototype is created based on the vehicle’s operation log data is constructed to help the model better understand the vehicle’s operating environment.Data segmentation techniques are used to highlight local data variation features.Furthermore,to mitigate issues related to poor convergence and slow training speeds caused by the extreme value loss function,a teacher forcing mechanism is integrated into the model,enhancing its convergence capabilities.Experimental results validate the effectiveness of the proposed method,demonstrating its ability to handle data imbalance challenges.Specifically,the model achieves over a 60%improvement in root mean square error under extreme value conditions,with significant improvements observed across additional metrics. 展开更多
关键词 Amphibious vehicle Attitude prediction Extreme value loss function Enhanced transformer architecture External information embedding
暂未订购 下载PDF
Physics-informed neural network-based digital twins for thermal energy systems:A review of solvability and loss function design 认领 引用
2
作者 Sadegh Ataee Mehran Ameri 《ENGINEERING Energy》 SCIE EI CAS CSCD 2026年第3期51-76,共26页
Thermal energy systems(TES)are an essential part of industries that have evolved over time through the engagement of managers and researchers.The development of digital twin(DT)technology has enabled accurate predicti... Thermal energy systems(TES)are an essential part of industries that have evolved over time through the engagement of managers and researchers.The development of digital twin(DT)technology has enabled accurate prediction of their performance.The inherent limitations of complex thermal systems,such as noisy input data and occasional lack of measurement data or boundary conditions,have recently created opportunities to apply physics-based problem-solving alongside DT technology.This paper aims to systematically review the novel physics-informed neural network-digital twin(PINN-DT)methodology as a potential solution to these challenges,and to present a taxonomy for problem-solving.The outcome of this study provides valuable guidance in selecting PINN-DT technology in thermal energy system(TES)modeling.A review of the proposed loss functions demonstrates that their design is critical for achieving precise outcomes in this technology,effectively serving as the foundational core of PINN-DT.As a result,it is recommended that the construction of the loss function be fundamentally guided by two principal considerations:forecasting accuracy and compliance with physical principles,which serve as foundational pillars in the surrogate model design framework.A significant gap exists in applying this technology to industries that use discrete sampling for quality control.Implementing the PINN-DT framework could address this issue by determining optimal sampling intervals,thereby offering vital decision-making support.Moreover,the absence of exergy analysis in formulating the physical loss component of the loss function represents a significant research gap.Future studies should therefore incorporate the exergy concept into the design of the loss function. 展开更多
关键词 Physics-informed neural network-digital twin(PINN-DT) Loss functions Thermal energy system Exergy analysis Physics-informed loss functions
暂未订购 下载PDF
Adaptive Meta-Loss Networks:Learning Task-Agnostic Loss Functions via Evolutionary Optimization 认领 引用
3
作者 Mirna Yunita Xiabi Liu +1 位作者 Zhaoyang Hai Rachmat Muwardi 《Computers, Materials & Continua》 SCIE EI 2026年第5期1931-1949,共19页
Designing appropriate loss functions is critical to the success of supervised learning models.However,most conventional losses are fixed and manually designed,making them suboptimal for diverse and dynamic learning sc... Designing appropriate loss functions is critical to the success of supervised learning models.However,most conventional losses are fixed and manually designed,making them suboptimal for diverse and dynamic learning scenarios.In this work,we propose an Adaptive Meta-Loss Network(Adaptive-MLN)that learns to generate taskagnostic loss functions tailored to evolving classification problems.Unlike traditional methods that rely on static objectives,Adaptive-MLN treats the loss function itself as a trainable component,parameterized by a shallow neural network.To enable flexible,gradient-free optimization,we introduce a hybrid evolutionary approach that combines GeneticAlgorithms(GA)for global exploration and Evolution Strategies(ES)for local refinement.This co-evolutionary process dynamically adjusts the loss landscape,improvingmodel generalization without relying on analytic gradients or handcrafted heuristics.Experimental evaluations on synthetic tasks and the CIFAR-10 andMNIST datasets demonstrate that our approach consistently outperforms standard losses such as Cross-Entropy and Mean Squared Error in terms of accuracy,convergence,and adaptability. 展开更多
关键词 Meta-learning adaptive loss function task-agnostic optimization evolutionary strategy genetic algorithm classification
暂未订购 下载PDF
Prediction of the Timing Selection of NIPT and Abnormality Determination of Fetus Based on Logistic Regression and Comprehensive Loss Function 认领 引用 被引量：1
4
作者 Guohao Luo 《Journal of Electronic Research and Application》 2026年第2期159-168,共10页
Chromosomal abnormalities are categorized into chromosomal-level(ROH,polyploidy,aneuploidy),local copy number,and gene-level(insertion/deletion)types.Unlike invasive prenatal diagnostics with miscarriage risks,NIPT is... Chromosomal abnormalities are categorized into chromosomal-level(ROH,polyploidy,aneuploidy),local copy number,and gene-level(insertion/deletion)types.Unlike invasive prenatal diagnostics with miscarriage risks,NIPT is noninvasive,reducing medical risks and maternal anxiety.This study addresses clinical NIPT bottlenecks(inaccurate timing,inconsistent abnormality determination)using high BMI pregnant women’s data via three core approaches:Spearman correlation and mixed-effects models confirm gestational age’s weak positive(rs=0.084,p<0.01)and BMI’s weak negative(rs=-0.155,p<0.001)correlation with fetal Y chromosome concentration;BMI grouping+Logistic regression+comprehensive loss function identifies robust optimal detection timing for each group;K-means clustering(4 groups)+three-layer weighted risk model(accuracy 0.4,timeliness 0.4,stability 0.2)optimizes multi-factor timing.Rational timing and multivariate models improve detection accuracy,supporting early clinical decisions. 展开更多
关键词 Logistic regression Comprehensive loss function Optimal detection time point Robustness analysis
暂未订购 下载PDF
Deep learning framework with hybrid loss function for seismic velocity inversion of natural gas hydrate reservoirs 认领 引用
5
作者 Zhen-wei Guo Jun Lei +3 位作者 Bo-chen Wang Yan-yi Wang Yan-jun Chen Jian-xin Liu 《China Geology》 CAS CSCD 2026年第3期502-518,共17页
Natural gas hydrate(NGH)has attracted increasing attention as a promising unconventional energy resource owing to its high volumetric storage capacity,yet its development is accompanied by significant greenhouse gas r... Natural gas hydrate(NGH)has attracted increasing attention as a promising unconventional energy resource owing to its high volumetric storage capacity,yet its development is accompanied by significant greenhouse gas risks.Therefore,accurate reservoir characterization is vital for marine resource exploration and sustainable development.Full waveform inversion(FWI)offers high-resolution imaging,yet suffers from heavy computation,sensitivity to initial models and non-uniqueness.Recent deep learning(DL)methods improve efficiency and accuracy,nevertheless,still struggle with clear boundary extraction and multi-level semantic representation.The authors propose a novel deep architecture(SC-UNeXt)designed to learn a mapping from seismic records to velocity models,which integrates a U-Net backbone,ConvNeXt residual blocks,spatial-channel squeeze-and-excitation attention and pixel shuffle up-sampling.Furthermore,a hybrid loss integrating mean squared error,multi-scale structural similarity,and perceptual discrepancy simultaneously optimizes pixel-wise accuracy,structural fidelity,and semantic consistency.Comprehensive tests on both synthetic NGH data and the 3D SEG/EAGE marine overthrust model with NGH demonstrate that SC-UNeXt outperforms FWI and advanced DL methods in boundary delineation,structural preservation,noise robustness,and computational efficiency.These results highlight SC-UNeXt as a reliable tool for high-resolution seismic characterization of NGH reservoirs,thereby supporting sustainable exploration and risk assessment of marine hydrate resources. 展开更多
关键词 Natural gas hydrate Clean energy Combustible ice Unconventional energy Seismic velocity inversion Deep learning Hybrid loss function U-Net-like architecture Full waveform inversion Gas hydrate exploration Risk assessment
暂未订购 下载PDF
An Improved Solov2 Based on Attention Mechanism and Weighted Loss Function for Electrical Equipment Instance Segmentation 认领 引用
6
作者 Junpeng Wu Zhenpeng Liu +2 位作者 Xingfan Jiang Xinguang Tao Ye Zhang 《Computers, Materials & Continua》 SCIE EI 2024年第1期677-694,共18页
The current existing problem of deep learning framework for the detection and segmentation of electrical equipment is dominantly related to low precision.Because of the reliable,safe and easy-to-operate technology pro... The current existing problem of deep learning framework for the detection and segmentation of electrical equipment is dominantly related to low precision.Because of the reliable,safe and easy-to-operate technology provided by deep learning-based video surveillance for unmanned inspection of electrical equipment,this paper uses the bottleneck attention module(BAM)attention mechanism to improve the Solov2 model and proposes a new electrical equipment segmentation mode.Firstly,the BAM attention mechanism is integrated into the feature extraction network to adaptively learn the correlation between feature channels,thereby improving the expression ability of the feature map;secondly,the weighted sum of CrossEntropy Loss and Dice loss is designed as the mask loss to improve the segmentation accuracy and robustness of the model;finally,the non-maximal suppression(NMS)algorithm to better handle the overlap problem in instance segmentation.Experimental results show that the proposed method achieves an average segmentation accuracy of mAP of 80.4% on three types of electrical equipment datasets,including transformers,insulators and voltage transformers,which improve the detection accuracy by more than 5.7% compared with the original Solov2 model.The segmentation model proposed can provide a focusing technical means for the intelligent management of power systems. 展开更多
关键词 Deep learning electrical equipment attention mechanism weighted loss function
暂未订购 下载PDF
Economic Design of  & S Control Charts Based on Taguchi's Loss Function and Its Optimization 认领 引用
7
作者 GUO Yu YANG Wen'an +1 位作者 LIAO Wenhe GAO Shiwen 《Chinese Journal of Mechanical Engineering》 SCIE EI CAS CSCD 2012年第3期576-586,共11页
Much research effort has been devoted to economic design of X ＆ S control charts,however,there are some problems in usual methods.On the one hand,it is difficult to estimate the relationship between costs and other... Much research effort has been devoted to economic design of X ＆ S control charts,however,there are some problems in usual methods.On the one hand,it is difficult to estimate the relationship between costs and other model parameters,so the economic design method is often not effective in producing charts that can quickly detect small shifts before substantial losses occur;on the other hand,in many cases,only one type of process shift or only one pair of process shifts are taken into consideration,which may not correctly reflect the actual process conditions.To improve the behavior of economic design of control chart,a cost ＆ loss model with Taguchi＇s loss function for the economic design of X ＆ S control charts is embellished,which is regarded as an optimization problem with multiple statistical constraints.The optimization design is also carried out based on a number of combinations of process shifts collected from the field operation of the conventional control charts,thus more hidden information about the shift combinations is mined and employed to the optimization design of control charts.At the same time,an improved particle swarm optimization（IPSO） is developed to solve such an optimization problem in design of X ＆ S control charts,IPSO is first tested for several benchmark problems from the literature and evaluated with standard performance metrics.Experimental results show that the proposed algorithm has significant advantages on obtaining the optimal design parameters of the charts.The proposed method can substantially reduce the total cost（or loss） of the control charts,and it will be a promising tool for economic design of control charts. 展开更多
关键词 statistical process control control charts Taguchi＇s loss function optimization particle swarm optimization
暂未订购 下载PDF
ANALYSIS TO NEYMAN-PEARSON CLASSIFICATION WITH CONVEX LOSS FUNCTION 认领 引用
8
作者 Min Han Dirong Chen Zhaoxu Sun 《Analysis in Theory and Applications》 2008年第1期18-28,共11页
Neyman-Pearson classification has been studied in several articles before. But they all proceeded in the classes of indicator functions with indicator function as the loss function, which make the calculation to be di... Neyman-Pearson classification has been studied in several articles before. But they all proceeded in the classes of indicator functions with indicator function as the loss function, which make the calculation to be difficult. This paper investigates Neyman- Pearson classification with convex loss function in the arbitrary class of real measurable functions. A general condition is given under which Neyman-Pearson classification with convex loss function has the same classifier as that with indicator loss function. We give analysis to NP-ERM with convex loss function and prove it＇s performance guarantees. An example of complexity penalty pair about convex loss function risk in terms of Rademacher averages is studied, which produces a tight PAC bound of the NP-ERM with convex loss function. 展开更多
关键词 Neyman-Pearson lemma convex loss function Neyman-Pearson classifica-tion NP-ERM Rademacher average
暂未订购 下载PDF
Evolution and Effectiveness of Loss Functions in Generative Adversarial Networks 认领 引用 被引量：1
9
作者 Ali Syed Saqlain Fang Fang +2 位作者 Tanvir Ahmad Liyun Wang Zain-ul Abidin 《China Communications》 SCIE EI CSCD 2021年第10期45-76,共32页
Recently,the evolution of Generative Adversarial Networks(GANs)has embarked on a journey of revolutionizing the field of artificial and computational intelligence.To improve the generating ability of GANs,various loss... Recently,the evolution of Generative Adversarial Networks(GANs)has embarked on a journey of revolutionizing the field of artificial and computational intelligence.To improve the generating ability of GANs,various loss functions are introduced to measure the degree of similarity between the samples generated by the generator and the real data samples,and the effectiveness of the loss functions in improving the generating ability of GANs.In this paper,we present a detailed survey for the loss functions used in GANs,and provide a critical analysis on the pros and cons of these loss functions.First,the basic theory of GANs along with the training mechanism are introduced.Then,the most commonly used loss functions in GANs are introduced and analyzed.Third,the experimental analyses and comparison of these loss functions are presented in different GAN architectures.Finally,several suggestions on choosing suitable loss functions for image synthesis tasks are given. 展开更多
关键词 loss functions deep learning machine learning unsupervised learning generative adversarial networks(GANs) image synthesis
暂未订购 下载PDF
The Credibility Models under LINEX Loss Functions 认领 引用 被引量：10
10
作者 WEN Li-min ZHANG Xiankun ZHENG Dan FANG .ling 《Chinese Quarterly Journal of Mathematics》 CSCD 2012年第3期397-402,共6页
LINEX(linear and exponential) loss function is a useful asymmetric loss function. The purpose of using a LINEX loss function in credibility models is to solve the problem of very high premium by suing a symmetric quad... LINEX(linear and exponential) loss function is a useful asymmetric loss function. The purpose of using a LINEX loss function in credibility models is to solve the problem of very high premium by suing a symmetric quadratic loss function in most of classical credibility models. The Bayes premium and the credibility premium are derived under LINEX loss function. The consistency of Bayes premium and credibility premium were also checked. Finally, the simulation was introduced to show the differences between the credibility estimator we derived and the classical one. 展开更多
关键词 LINEX loss function credibility estimator Bayes premium
暂未订购 下载PDF
Application of Weighted Cross-Entropy Loss Function in Intrusion Detection 认领 引用 被引量：3
11
作者 Ziyun Zhou Hong Huang Binhao Fang 《Journal of Computer and Communications》 2021年第11期1-21,共21页
The deep learning model is overfitted and the accuracy of the test set is reduced when the deep learning model is trained in the network intrusion detection parameters, due to the traditional loss function convergence... The deep learning model is overfitted and the accuracy of the test set is reduced when the deep learning model is trained in the network intrusion detection parameters, due to the traditional loss function convergence problem. Firstly, we utilize a network model architecture combining Gelu activation function and deep neural network;Secondly, the cross-entropy loss function is improved to a weighted cross entropy loss function, and at last it is applied to intrusion detection to improve the accuracy of intrusion detection. In order to compare the effect of the experiment, the KDDcup99 data set, which is commonly used in intrusion detection, is selected as the experimental data and use accuracy, precision, recall and F1-score as evaluation parameters. The experimental results show that the model using the weighted cross-entropy loss function combined with the Gelu activation function under the deep neural network architecture improves the evaluation parameters by about 2% compared with the ordinary cross-entropy loss function model. Experiments prove that the weighted cross-entropy loss function can enhance the model’s ability to discriminate samples. 展开更多
关键词 Cross-Entropy Loss Function Visualization Analysis Intrusion Detection KDD Data Set Accuracy
暂未订购 下载PDF
Admissible Linear Estimators of Multivariate Regression Coefcient with Respect to an Inequality Constraint under Balanced Loss Function 认领 引用
12
作者 Jie WU Daojiang HE 《Journal of Mathematical Research with Applications》 CSCD 2013年第6期745-752,共8页
In this paper, the admissibility of multivariate linear regression coefficient with respect to an inequality constraint under balanced loss function is investigated. Necessary and sufficient conditions for admissible ... In this paper, the admissibility of multivariate linear regression coefficient with respect to an inequality constraint under balanced loss function is investigated. Necessary and sufficient conditions for admissible homogeneous and inhomogeneous linear estimators are obtained, respectively. 展开更多
关键词 admissibility inequality constraint balanced loss function homogeneous （inhomogeneous） linear estimator.
暂未订购 下载PDF
The Credibility Estimators under MLINEX Loss Function 认领 引用
13
作者 ZHANG Qiang CUI Qian-qian CHEN Ping 《Chinese Quarterly Journal of Mathematics》 2018年第1期43-50,共8页
In this paper, MLINEX loss function was considered to solve the problem of high premium in credibility models. The Bayes premium and credibility premium were obtained under MLINEX loss function by using a symmetric qu... In this paper, MLINEX loss function was considered to solve the problem of high premium in credibility models. The Bayes premium and credibility premium were obtained under MLINEX loss function by using a symmetric quadratic loss function. A credibility model with multiple contracts was established and the corresponding credibility estimator was derived under MLINEX loss function. For this model the estimations of the structure parameters and a numerical example were also given. 展开更多
关键词 MLINEX loss function Bayes premium Credibility estimator Multiple contracts
暂未订购 下载PDF
Remote Sensing Plateau Forest Segmentation with Boundary Preserving Double Loss Function Collaborative Learning 认领 引用
14
作者 Ying Ma Jiaqi Zhang +3 位作者 Pengyu Liu Zhihao Wei Lingfei Zhang Xiaowei Jia 《Journal of New Media》 2022年第4期165-177,共13页
Plateau forest plays an important role in the high-altitude ecosystem,and contributes to the global carbon cycle.Plateau forest monitoring request in-suit data from field investigation.With recent development of the r... Plateau forest plays an important role in the high-altitude ecosystem,and contributes to the global carbon cycle.Plateau forest monitoring request in-suit data from field investigation.With recent development of the remote sensing technic,large-scale satellite data become available for surface monitoring.Due to the various information contained in the remote sensing data,obtain accurate plateau forest segmentation from the remote sensing imagery still remain challenges.Recent developed deep learning(DL)models such as deep convolutional neural network(CNN)has been widely used in image processing tasks,and shows possibility for remote sensing segmentation.However,due to the unique characteristics and growing environment of the plateau forest,generate feature with high robustness needs to design structures with high robustness.Aiming at the problem that the existing deep learning segmentation methods are difficult to generate the accurate boundary of the plateau forest within the satellite imagery,we propose a method of using boundary feature maps for collaborative learning.There are three improvements in this article.First,design a multi input model for plateau forest segmentation,including the boundary feature map as an additional input label to increase the amount of information at the input.Second,we apply a strong boundary search algorithm to obtain boundary value,and propose a boundary value loss function.Third,improve the Unet segmentation network and combine dense block to improve the feature reuse ability and reduces the image information loss of the model during training.We then demonstrate the utility of our method by detecting plateau forest regions from ZY-3 satellite regarding to Sanjiangyuan nature reserve.The experimental results show that the proposed method can utilize multiple feature information comprehensively which is beneficial to extracting information from boundary,and the detection accuracy is generally higher than several state-of-art algorithms.As a result of this investigation,the study will contribute in several ways to our understanding of DL for region detection and will provide a basis for further researches. 展开更多
关键词 Remote sensing forest segmentation boundary preserving double loss function
暂未订购 下载PDF
Survey on the Loss Function of Deep Learning in Face Recognition 认领 引用
15
作者 Jun Wang Suncheng Feng +1 位作者 Yong Cheng Najla Al-Nabhan 《Journal of Information Hiding and Privacy Protection》 2021年第1期29-45,共17页
With the continuous development of face recognition network,the selection of loss function plays an increasingly important role in improving accuracy.The loss function of face recognition network needs to minimize the... With the continuous development of face recognition network,the selection of loss function plays an increasingly important role in improving accuracy.The loss function of face recognition network needs to minimize the intra-class distance while expanding the inter-class distance.So far,one of our mainstream loss function optimization methods is to add penalty terms,such as orthogonal loss,to further constrain the original loss function.The other is to optimize using the loss based on angular/cosine margin.The last is Triplet loss and a new type of joint optimization based on HST Loss and ACT Loss.In this paper,based on the three methods with good practical performance and the joint optimization method,various loss functions are thoroughly reviewed. 展开更多
关键词 Loss function face recognition orthogonality loss ArcFace the joint loss
暂未订购 下载PDF
Enhancing fault detection using CHRRA-Unet and focal loss functions for imbalanced data:A case study in Luoping county,Yunnan,China 认领 引用
16
作者 Gong Cheng Syed Hussain +6 位作者 Yingdong Yang Li Sun Asad Atta Cheng Huang Guangqiang Li Mohammad Naseer Lingyi Liao 《Artificial Intelligence in Geosciences》 EI CSCD 2026年第1期16-29,共14页
Recent advancements in remote sensing technology have made it easier to detect surface faults.Deep learning,especially convolutional models,offers new potential for automatic fault detection from remote sensing imager... Recent advancements in remote sensing technology have made it easier to detect surface faults.Deep learning,especially convolutional models,offers new potential for automatic fault detection from remote sensing imagery.However,these models often struggle with segmentation accuracy due to their limitations in handling spatial hierarchies and short-range dependencies.They process data in local contexts,which is insufficient for tasks requiring an understanding of global structures,like fault detection.This leads to inaccurate boundary divisions and incomplete fault trace detections.To address these issues,the Convolution Holographic Reduced Representations-Based Unet(CHRRA-Unet)is introduced.This U-shaped network combines convolution and a novel attention-based transformer for remote sensing image segmentation.By extracting both local and global features,the CHRRA-Unet significantly improves the detection of geological faults in remote sensing images.By incorporating a convolutional module(CM)and holographic reduced representation attention(HRRA),local and global feature extraction is improved.To minimize computational complexity,the traditional Multi-Layer Per-ceptron(MLP)is replaced with the Local Perception Module(LPM).The Multi-Feature Conversion Module(MFCM)ensures an effective combination of feature maps during encoding and decoding,enhancing the net-work’s ability to accurately detect fault traces.Extensive experiments show that CHRRA-Unet achieves a high accuracy rate of 97.20%in remote sensing image segmentation,outperforming existing models and providing superior fault detection capabilities over current methods. 展开更多
关键词 Fault detection Imbalance datasets Focal loss function CHRRA-Unet Hrrformer models Remote sensing data
On Loss Functionals for Physics-Informed Neural Networks for Steady-State Convection-Dominated Convection-Diffusion Problems 认领 引用
17
作者 Derk Frerichs-Mihov Linus Henning Volker John 《Communications on Applied Mathematics and Computation》 EI CSCD 2026年第1期287-308,共22页
Solutions of convection-dominated convection-diffusion problems usually possess layers,which are regions where the solution has a steep gradient.It is well known that many classical numerical discretization techniques... Solutions of convection-dominated convection-diffusion problems usually possess layers,which are regions where the solution has a steep gradient.It is well known that many classical numerical discretization techniques face difficulties when approximating the solution to these problems.In recent years,physics-informed neural networks(PINNs)for approximating the solution to(initial-)boundary value problems((I)BVPs)received a lot of interest.This paper studies various loss functionals for PINNs that are especially designed for convectiondominated convection-diffusion problems and that are novel in the context of PINNs.They are numerically compared to the vanilla and an hp-variational loss functional from the literature based on two steady-state benchmark problems whose solutions possess different types of layers.We observe that the best novel loss functionals reduce the L2(Ω)error by 17.3%for the first and 5.5%for the second problem compared to the methods from the literature. 展开更多
关键词 Steady-state convection-diffusion problems Convection-dominated regime Physics-informed neural networks(PINNs) Loss functionals
Loss-of-function mutations in the fruit softening gene POLYGALACTURONASE1 doubled fruit firmness in strawberry 认领 引用
18
作者 Nicolás P.Jiménez Marta Bjornson +7 位作者 Randi A.Famula Dominique D.A.Pincot Michael A.Hardigan Mary A.Madera Cindy M.Lopez Ramirez Glenn S.Cole Mitchell J.Feldmann Steven J.Knapp 《Horticulture Research》 SCIE CSCD 2025年第2期215-235,共21页
Wildtype fruit of cultivated strawberry(Fragaria×ananassa)are typically soft and highly perishable when fully ripe.The development of firm-fruited cultivars by phenotypic selection has greatly increased shelf-lif... Wildtype fruit of cultivated strawberry(Fragaria×ananassa)are typically soft and highly perishable when fully ripe.The development of firm-fruited cultivars by phenotypic selection has greatly increased shelf-life,decreased postharvest perishability,and driven the expansion of strawberry production worldwide.Hypotheses for the firm-fruited phenotype include mutations affecting the expression of genes encoding polygalacturonases(PGs)that soften fruit by degrading cell wall pectins.Here we show that loss-of-function mutations in the fruit softening gene POLYGALACTURONASE1(FaPG1;PG1-6A1)double fruit firmness in strawberry.PG1-6A1 was one of three tandem duplicated PG genes found to be in linkage disequilibrium(LD)with a quantitative trait locus(QTL)affecting fruit firmness on chromosome 6A.PG1-6A1 was strongly expressed in soft-fruited(wildtype)homozygotes and weakly expressed in firm-fruited(mutant)homozygotes.Genome-wide association,quantitative trait transcript,DNA sequence,and expression-QTL analyses identified genetic variants in LD with PG1-6A1 that were positively correlated with fruit firmness and negatively correlated with PG1-6A1 expression.An Enhancer/Suppressor-mutator(En/Spm)transposable element insertion was discovered upstream of PG1-6A1 in mutant homozygotes that we hypothesize transcriptionally downregulates the expression of PG1-6A1.The PG1-6A1 locus was incompletely dominant and explained 26–76%of the genetic variance for fruit firmness among phenotypically diverse individuals.Additional loci are hypothesized to underlie the missing heritability.Highly accurate codominant genotyping assays were developed for modifying fruit firmness by marker-assisted selection of the En/Spm insertion and single nucleotide polymorphisms associated with the PG1-6A1 locus. 展开更多
关键词 quantitative trait locus strawberry loss function mutations fruit firmness soften fruit polygalacturonase transposable element insertion phenotypic selection
暂未订购 下载PDF
YOLOv5-RF:a deep learning method for tailings pond identification in high-resolution remote sensing images based on improved loss function 认领 引用 被引量：1
19
作者 Weiming Zhang Wenliang Jiang +5 位作者 Qiang Li Yi Luo Heng Zhang Qisong Jiao Yongsheng Li Hongbo Jiang 《Big Earth Data》 EI CSCD 2025年第1期100-126,共27页
Tailings ponds are critical facilities in the mining industry,and accurate monitoring and management of these ponds are of paramount importance.However,conventional object detection methodologies,including recent adva... Tailings ponds are critical facilities in the mining industry,and accurate monitoring and management of these ponds are of paramount importance.However,conventional object detection methodologies,including recent advancements,often face significant challenges in addressing the complexities inherent to tailings pond environments.This is particularly due to deficiencies in their loss function design,which can result in protracted convergence times and suboptimal performance when detecting smaller targets.In this study,we introduce an innovative loss function termed the Rapid Intersection over Union(RIoU)loss function,which incorporates a focal weight and is integrated into the YOLOv5 object detection framework to develop the YOLOv5-RF model.This approach aims to enhance both convergence speed and improve convergence accuracy in the tailings pond identification process by comprehensively addressing the specific challenges posed by complex environmental conditions,thereby enhancing the precision and robustness of tailings pond target detection.It integrates the concepts of the central triangle and the aspect ratio of the circumscribed rectangle,assigning specific weights and penalty terms to optimize the model’s performance in object detection tasks.We validated the efficacy of YOLOv5-RF through simulation experiments and high-resolution remote sensing images of tailings ponds.The experimental results indicate that RIoU facilitates faster convergence rates.Specifically,YOLOv5-RF achieves accuracy and recall rates that are 2%and 2.1%higher than those of YOLOv5,respectively.Furthermore,it completes 120 iterations in 1.08 hours less time compared to its predecessor model while exhibiting an inference time that is 11.7 ms shorter than that for YOLOv5.These findings suggest that our model significantly enhances processing speed without compromising accuracy levels.This research offers novel technical approaches as well as theoretical support for monitoring tailings ponds using computer vision and remote sensing technologies. 展开更多
关键词 Object detection YOLOv5 loss function tailings ponds remote sensing identification
3D holographic metasurface design by deep learning with partitioned loss function 认领 引用 被引量：1
20
作者 YUNXIN GUO YI YANG +4 位作者 FAN HUANG JIANQIANG GU CHUNMEI OUYANG QUAN XU XUEQIAN ZHANG 《Photonics Research》 SCIE EI CAS CSCD 2025年第12期3383-3398,共16页
Deep learning has significantly accelerated the automation of metasurface design and reduced its dependence on empirical approaches.However,it still has not fully demonstrated its capabilities in the most challenging ... Deep learning has significantly accelerated the automation of metasurface design and reduced its dependence on empirical approaches.However,it still has not fully demonstrated its capabilities in the most challenging light field manipulation:3D holography.In this paper,we present a framework that integrates a fully connected forward prediction network with a 3D convolutional inverse design network to design terahertz 3D holographic metasurfaces. 展开更多
关键词 light field manipulation d holographyin deep learning d holographic metasurface partitioned loss function d convolutional inverse design network empirical approacheshoweverit terahertz d holographic metasurfaces forward prediction network
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 235 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈