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
Behavior recognition of Hu sheep contributes to their intensive and intelligent farming.Due to the generally high density of Hu sheep farming,severe occlusion occurs among different behaviors and even among sheep perf...Behavior recognition of Hu sheep contributes to their intensive and intelligent farming.Due to the generally high density of Hu sheep farming,severe occlusion occurs among different behaviors and even among sheep performing the same behavior,leading to missing and false detection issues in existing behavior recognition methods.A high-low frequency aggregated attention and negative sample comprehensive score loss and comprehensive score soft non-maximum suppression-YOLO(HLNC-YOLO)was proposed for identifying the behavior of Hu sheep,addressing the issues of missed and erroneous detections caused by occlusion between Hu sheep in intensive farming.Firstly,images of four typical behaviors-standing,lying,eating,and drinking-were collected from the sheep farm to construct the Hu sheep behavior dataset(HSBD).Next,to solve the occlusion issues,during the training phase,the C2F-HLAtt module was integrated,which combined high-low frequency aggregation attention,into the YOLO v8 Backbone to perceive occluded objects and introduce an auxiliary reversible branch to retain more effective features.Using comprehensive score regression loss(CSLoss)to reduce the scores of suboptimal boxes and enhance the comprehensive scores of occluded object boxes.Finally,the soft comprehensive score non-maximal suppression(Soft-CS-NMS)algorithm filtered prediction boxes during the inferencing.Testing on the HSBD,HLNC-YOLO achieved a mean average precision(mAP@50)of 87.8%,with a memory footprint of 17.4 MB.This represented an improvement of 7.1,2.2,4.6,and 11 percentage points over YOLO v8,YOLO v9,YOLO v10,and Faster R-CNN,respectively.Research indicated that the HLNC-YOLO accurately identified the behavior of Hu sheep in intensive farming and possessed generalization capabilities,providing technical support for smart farming.展开更多
With the rapid development of digital culture,a large number of cultural texts are presented in the form of digital and network.These texts have significant characteristics such as sparsity,real-time and non-standard ...With the rapid development of digital culture,a large number of cultural texts are presented in the form of digital and network.These texts have significant characteristics such as sparsity,real-time and non-standard expression,which bring serious challenges to traditional classification methods.In order to cope with the above problems,this paper proposes a new ASSC(ALBERT,SVD,Self-Attention and Cross-Entropy)-TextRCNN digital cultural text classification model.Based on the framework of TextRCNN,the Albert pre-training language model is introduced to improve the depth and accuracy of semantic embedding.Combined with the dual attention mechanism,the model’s ability to capture and model potential key information in short texts is strengthened.The Singular Value Decomposition(SVD)was used to replace the traditional Max pooling operation,which effectively reduced the feature loss rate and retained more key semantic information.The cross-entropy loss function was used to optimize the prediction results,making the model more robust in class distribution learning.The experimental results indicate that,in the digital cultural text classification task,as compared to the baseline model,the proposed ASSC-TextRCNN method achieves an 11.85%relative improvement in accuracy and an 11.97%relative increase in the F1 score.Meanwhile,the relative error rate decreases by 53.18%.This achievement not only validates the effectiveness and advanced nature of the proposed approach but also offers a novel technical route and methodological underpinnings for the intelligent analysis and dissemination of digital cultural texts.It holds great significance for promoting the in-depth exploration and value realization of digital culture.展开更多
To address the challenges of small target detection and significant scale variations in unmanned aerial vehicle(UAV)aerial imagery,which often lead to missed and false detections,we propose Multi-scale Feature Fusion ...To address the challenges of small target detection and significant scale variations in unmanned aerial vehicle(UAV)aerial imagery,which often lead to missed and false detections,we propose Multi-scale Feature Fusion YOLO(MFF-YOLO),an enhanced algorithm based on YOLOv8s.Our approach introduces a Multi-scale Feature Fusion Strategy(MFFS),comprising the Multiple Features C2f(MFC)module and the Scale Sequence Feature Fusion(SSFF)module,to improve feature integration across different network levels.This enables more effective capture of fine-grained details and sequential multi-scale features.Furthermore,we incorporate Inner-CIoU,an improved loss function that uses auxiliary bounding boxes to enhance the regression quality of small object boxes.To ensure practicality for UAV deployment,we apply the Layer-adaptive Magnitude-based pruning(LAMP)method to significantly reduce model size and computational cost.Experiments on the VisDrone2019 dataset show that MFF-YOLO achieves a 5.7% increase in mean average precision(mAP)over the baseline,while reducing parameters by 8.5 million and computation by 17.5%.The results demonstrate that our method effectively improves detection performance in UAV aerial scenarios.展开更多
Predicting Antarctic sea ice is of substantial academic and practical significance.However,current prediction models,including deep learning(DL)-based models,show notable bias in the marginal ice zone.In this study,we...Predicting Antarctic sea ice is of substantial academic and practical significance.However,current prediction models,including deep learning(DL)-based models,show notable bias in the marginal ice zone.In this study,we developed a pure data-driven DL model for predicting the Antarctic austral summer monthly-to-seasonal sea ice concentration(SIC)by incorporating a novel hybrid sea ice edge constraint loss function(HybridLoss).The model is referred to as ASICNet.Independent testing based on the last five years(2019–23)demonstrates that ASICNet with HybridLoss achieves significantly higher skill metrics than without,with a reduced mean absolute error of 0.021 from 0.022,a reduced integrated ice edge error of 1.714×10^(6)from 1.794×10^(6)km^(2),but an increased pattern correlation coefficient of 0.40 from 0.38,although both ASICNet versions outperform dynamical and statistical models.Furthermore,enhanced heat maps were developed to interpret the predictability sources of sea ice within DL-based models,and the results suggest that the predictability of Antarctic sea ice is attributable to factors like the Antarctic Dipole(ADP),Amundsen Sea Low(ASL),and Southern Ocean sea surface temperature(SST),as revealed in previous studies.Thus,ASICNet is an efficient tool for austral summer Antarctic SIC prediction.展开更多
Ufmylation is an ubiquitin-like post-translational modification characterized by the covalent binding of mature UFM1 to target proteins.Although the consequences of ufmylation on target proteins are not fully understo...Ufmylation is an ubiquitin-like post-translational modification characterized by the covalent binding of mature UFM1 to target proteins.Although the consequences of ufmylation on target proteins are not fully understood,its importance is evident from the disorders resulting from its dysfunction.Numerous case reports have established a link between biallelic loss-of-function and/or hypomorphic variants in ufmylation-related genes and a spectrum of pediatric neurodevelopmental disorders.展开更多
Remote sensing image super-resolution technology is pivotal for enhancing image quality in critical applications including environmental monitoring,urban planning,and disaster assessment.However,traditional methods ex...Remote sensing image super-resolution technology is pivotal for enhancing image quality in critical applications including environmental monitoring,urban planning,and disaster assessment.However,traditional methods exhibit deficiencies in detail recovery and noise suppression,particularly when processing complex landscapes(e.g.,forests,farmlands),leading to artifacts and spectral distortions that limit practical utility.To address this,we propose an enhanced Super-Resolution Generative Adversarial Network(SRGAN)framework featuring three key innovations:(1)Replacement of L1/L2 loss with a robust Charbonnier loss to suppress noise while preserving edge details via adaptive gradient balancing;(2)A multi-loss joint optimization strategy dynamically weighting Charbonnier loss(β=0.5),Visual Geometry Group(VGG)perceptual loss(α=1),and adversarial loss(γ=0.1)to synergize pixel-level accuracy and perceptual quality;(3)A multi-scale residual network(MSRN)capturing cross-scale texture features(e.g.,forest canopies,mountain contours).Validated on Sentinel-2(10 m)and SPOT-6/7(2.5 m)datasets covering 904 km2 in Motuo County,Xizang,our method outperforms the SRGAN baseline(SR4RS)with Peak Signal-to-Noise Ratio(PSNR)gains of 0.29 dB and Structural Similarity Index(SSIM)improvements of 3.08%on forest imagery.Visual comparisons confirm enhanced texture continuity despite marginal Learned Perceptual Image Patch Similarity(LPIPS)increases.The method significantly improves noise robustness and edge retention in complex geomorphology,demonstrating 18%faster response in forest fire early warning and providing high-resolution support for agricultural/urban monitoring.Future work will integrate spectral constraints and lightweight architectures.展开更多
With the efficient and intelligent development of computer-based big data processing,applying machine learning methods to the processing and interpretation of logging data in the field of geophysical well logging has ...With the efficient and intelligent development of computer-based big data processing,applying machine learning methods to the processing and interpretation of logging data in the field of geophysical well logging has broad potential for improving production efficiency.Currently,the Jiyuan Oilfield in the Ordos Basin relies mainly on manual reprocessing and interpretation of old well logging data to identify different fluid types in low-contrast reservoirs,guiding subsequent production work.This study uses well logging data from the Chang 1 reservoir,partitioning the dataset based on individual wells for model training and testing.A deep learning model for intelligent reservoir fluid identification was constructed by incorporating the focal loss function.Comparative validations with five other models,including logistic regression(LR),naive Bayes(NB),gradient boosting decision trees(GBDT),random forest(RF),and support vector machine(SVM),show that this model demonstrates superior identification performance and significantly improves the accuracy of identifying oil-bearing fluids.Mutual information analysis reveals the model's differential dependency on various logging parameters for reservoir fluid identification.This model provides important references and a basis for conducting regional studies and revisiting old wells,demonstrating practical value that can be widely applied.展开更多
The aging process is an inexorable fact throughout our lives and is considered a major factor in develo ping neurological dysfunctions associated with cognitive,emotional,and motor impairments.Aging-associated neurode...The aging process is an inexorable fact throughout our lives and is considered a major factor in develo ping neurological dysfunctions associated with cognitive,emotional,and motor impairments.Aging-associated neurodegenerative diseases are characterized by the progressive loss of neuronal structure and function.展开更多
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
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
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
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 m...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
The effective energy loss functions for Al have been derived from differential i nverse inelastic mean free path based on the extended Landau approach. It has be en revealed that the effective energy loss function is ...The effective energy loss functions for Al have been derived from differential i nverse inelastic mean free path based on the extended Landau approach. It has be en revealed that the effective energy loss function is very close in value to th e theoretical surface energy loss function in the lower energy loss region but g radually approaches the theoretical bulk energy loss function in the higher ener gy loss region. Moreover, the intensity corresponding to surface excitation in e ffective energy loss functions decreases with the increase of primary electron e nergy. These facts show that the present effective energy loss function describe s not only surface excitation but also bulk excitation. At last, REELS spectra s imulated by Monte Carlo method based on use of the effective energy loss functio ns has reproduced the experimental REELS spectra with considerable success.展开更多
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
We present a fitting calculation of energy-loss function for 26 bulk materials, including 18 pure elements （Ag, A1, Au, C, Co, Cs, Cu, Er, Fe, Ge, Mg, Mo, Nb, Ni, Pd, Pt, Si, Te） and 8 compounds （AgCl, Al2O3, AlAs,...We present a fitting calculation of energy-loss function for 26 bulk materials, including 18 pure elements （Ag, A1, Au, C, Co, Cs, Cu, Er, Fe, Ge, Mg, Mo, Nb, Ni, Pd, Pt, Si, Te） and 8 compounds （AgCl, Al2O3, AlAs, CdS, SiO2, ZnS, ZnSe, ZnTe） for application to surface electron spectroscopy analysis. The experimental energy-loss function, which is derived from measured optical data, is fitted into a finite sum of formula based on the Drude-Lindhard dielectric model. By checking the oscillator strength-sum and perfect- screening-sum rules, we have validated the high accuracy of the fitting results. Further-more, based on the fitted parameters, the simulated reflection electron energy-loss spec- troscopy （REELS） spectrum shows a good agreement with experiment. The calculated fitting parameters of energy loss function are stored in an open and online database at http：//micro.ustc.edu.cn/ELF/ELF.html.展开更多
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
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
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
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
基金Supported by the National Defense Basic Scientific Research Program of China.
文摘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.
文摘Behavior recognition of Hu sheep contributes to their intensive and intelligent farming.Due to the generally high density of Hu sheep farming,severe occlusion occurs among different behaviors and even among sheep performing the same behavior,leading to missing and false detection issues in existing behavior recognition methods.A high-low frequency aggregated attention and negative sample comprehensive score loss and comprehensive score soft non-maximum suppression-YOLO(HLNC-YOLO)was proposed for identifying the behavior of Hu sheep,addressing the issues of missed and erroneous detections caused by occlusion between Hu sheep in intensive farming.Firstly,images of four typical behaviors-standing,lying,eating,and drinking-were collected from the sheep farm to construct the Hu sheep behavior dataset(HSBD).Next,to solve the occlusion issues,during the training phase,the C2F-HLAtt module was integrated,which combined high-low frequency aggregation attention,into the YOLO v8 Backbone to perceive occluded objects and introduce an auxiliary reversible branch to retain more effective features.Using comprehensive score regression loss(CSLoss)to reduce the scores of suboptimal boxes and enhance the comprehensive scores of occluded object boxes.Finally,the soft comprehensive score non-maximal suppression(Soft-CS-NMS)algorithm filtered prediction boxes during the inferencing.Testing on the HSBD,HLNC-YOLO achieved a mean average precision(mAP@50)of 87.8%,with a memory footprint of 17.4 MB.This represented an improvement of 7.1,2.2,4.6,and 11 percentage points over YOLO v8,YOLO v9,YOLO v10,and Faster R-CNN,respectively.Research indicated that the HLNC-YOLO accurately identified the behavior of Hu sheep in intensive farming and possessed generalization capabilities,providing technical support for smart farming.
基金funded by China National Innovation and Entrepreneurship Project Fund Innovation Training Program(202410451009).
文摘With the rapid development of digital culture,a large number of cultural texts are presented in the form of digital and network.These texts have significant characteristics such as sparsity,real-time and non-standard expression,which bring serious challenges to traditional classification methods.In order to cope with the above problems,this paper proposes a new ASSC(ALBERT,SVD,Self-Attention and Cross-Entropy)-TextRCNN digital cultural text classification model.Based on the framework of TextRCNN,the Albert pre-training language model is introduced to improve the depth and accuracy of semantic embedding.Combined with the dual attention mechanism,the model’s ability to capture and model potential key information in short texts is strengthened.The Singular Value Decomposition(SVD)was used to replace the traditional Max pooling operation,which effectively reduced the feature loss rate and retained more key semantic information.The cross-entropy loss function was used to optimize the prediction results,making the model more robust in class distribution learning.The experimental results indicate that,in the digital cultural text classification task,as compared to the baseline model,the proposed ASSC-TextRCNN method achieves an 11.85%relative improvement in accuracy and an 11.97%relative increase in the F1 score.Meanwhile,the relative error rate decreases by 53.18%.This achievement not only validates the effectiveness and advanced nature of the proposed approach but also offers a novel technical route and methodological underpinnings for the intelligent analysis and dissemination of digital cultural texts.It holds great significance for promoting the in-depth exploration and value realization of digital culture.
基金supported by the National Natural Science Foundation of China(No.61976028).
文摘To address the challenges of small target detection and significant scale variations in unmanned aerial vehicle(UAV)aerial imagery,which often lead to missed and false detections,we propose Multi-scale Feature Fusion YOLO(MFF-YOLO),an enhanced algorithm based on YOLOv8s.Our approach introduces a Multi-scale Feature Fusion Strategy(MFFS),comprising the Multiple Features C2f(MFC)module and the Scale Sequence Feature Fusion(SSFF)module,to improve feature integration across different network levels.This enables more effective capture of fine-grained details and sequential multi-scale features.Furthermore,we incorporate Inner-CIoU,an improved loss function that uses auxiliary bounding boxes to enhance the regression quality of small object boxes.To ensure practicality for UAV deployment,we apply the Layer-adaptive Magnitude-based pruning(LAMP)method to significantly reduce model size and computational cost.Experiments on the VisDrone2019 dataset show that MFF-YOLO achieves a 5.7% increase in mean average precision(mAP)over the baseline,while reducing parameters by 8.5 million and computation by 17.5%.The results demonstrate that our method effectively improves detection performance in UAV aerial scenarios.
基金jointly supported by the National Natural Science Foundation of China(Grant No.42376250)the Strategic Priority Research Program of the Chinese Academy of Sciences(Grant No.XDA19070402).
文摘Predicting Antarctic sea ice is of substantial academic and practical significance.However,current prediction models,including deep learning(DL)-based models,show notable bias in the marginal ice zone.In this study,we developed a pure data-driven DL model for predicting the Antarctic austral summer monthly-to-seasonal sea ice concentration(SIC)by incorporating a novel hybrid sea ice edge constraint loss function(HybridLoss).The model is referred to as ASICNet.Independent testing based on the last five years(2019–23)demonstrates that ASICNet with HybridLoss achieves significantly higher skill metrics than without,with a reduced mean absolute error of 0.021 from 0.022,a reduced integrated ice edge error of 1.714×10^(6)from 1.794×10^(6)km^(2),but an increased pattern correlation coefficient of 0.40 from 0.38,although both ASICNet versions outperform dynamical and statistical models.Furthermore,enhanced heat maps were developed to interpret the predictability sources of sea ice within DL-based models,and the results suggest that the predictability of Antarctic sea ice is attributable to factors like the Antarctic Dipole(ADP),Amundsen Sea Low(ASL),and Southern Ocean sea surface temperature(SST),as revealed in previous studies.Thus,ASICNet is an efficient tool for austral summer Antarctic SIC prediction.
文摘Ufmylation is an ubiquitin-like post-translational modification characterized by the covalent binding of mature UFM1 to target proteins.Although the consequences of ufmylation on target proteins are not fully understood,its importance is evident from the disorders resulting from its dysfunction.Numerous case reports have established a link between biallelic loss-of-function and/or hypomorphic variants in ufmylation-related genes and a spectrum of pediatric neurodevelopmental disorders.
基金This study was supported by:Inner Mongolia Academy of Forestry Sciences Open Research Project(Grant No.KF2024MS03)The Project to Improve the Scientific Research Capacity of the Inner Mongolia Academy of Forestry Sciences(Grant No.2024NLTS04)The Innovation and Entrepreneurship Training Program for Undergraduates of Beijing Forestry University(Grant No.X202410022268).
文摘Remote sensing image super-resolution technology is pivotal for enhancing image quality in critical applications including environmental monitoring,urban planning,and disaster assessment.However,traditional methods exhibit deficiencies in detail recovery and noise suppression,particularly when processing complex landscapes(e.g.,forests,farmlands),leading to artifacts and spectral distortions that limit practical utility.To address this,we propose an enhanced Super-Resolution Generative Adversarial Network(SRGAN)framework featuring three key innovations:(1)Replacement of L1/L2 loss with a robust Charbonnier loss to suppress noise while preserving edge details via adaptive gradient balancing;(2)A multi-loss joint optimization strategy dynamically weighting Charbonnier loss(β=0.5),Visual Geometry Group(VGG)perceptual loss(α=1),and adversarial loss(γ=0.1)to synergize pixel-level accuracy and perceptual quality;(3)A multi-scale residual network(MSRN)capturing cross-scale texture features(e.g.,forest canopies,mountain contours).Validated on Sentinel-2(10 m)and SPOT-6/7(2.5 m)datasets covering 904 km2 in Motuo County,Xizang,our method outperforms the SRGAN baseline(SR4RS)with Peak Signal-to-Noise Ratio(PSNR)gains of 0.29 dB and Structural Similarity Index(SSIM)improvements of 3.08%on forest imagery.Visual comparisons confirm enhanced texture continuity despite marginal Learned Perceptual Image Patch Similarity(LPIPS)increases.The method significantly improves noise robustness and edge retention in complex geomorphology,demonstrating 18%faster response in forest fire early warning and providing high-resolution support for agricultural/urban monitoring.Future work will integrate spectral constraints and lightweight architectures.
基金supported by a project of the Shaanxi Youth Science and Technology Star(2021KJXX-87)public welfare geological survey projects of Shaanxi Institute of Geologic Survey(20180301,201918 and 202103)。
文摘With the efficient and intelligent development of computer-based big data processing,applying machine learning methods to the processing and interpretation of logging data in the field of geophysical well logging has broad potential for improving production efficiency.Currently,the Jiyuan Oilfield in the Ordos Basin relies mainly on manual reprocessing and interpretation of old well logging data to identify different fluid types in low-contrast reservoirs,guiding subsequent production work.This study uses well logging data from the Chang 1 reservoir,partitioning the dataset based on individual wells for model training and testing.A deep learning model for intelligent reservoir fluid identification was constructed by incorporating the focal loss function.Comparative validations with five other models,including logistic regression(LR),naive Bayes(NB),gradient boosting decision trees(GBDT),random forest(RF),and support vector machine(SVM),show that this model demonstrates superior identification performance and significantly improves the accuracy of identifying oil-bearing fluids.Mutual information analysis reveals the model's differential dependency on various logging parameters for reservoir fluid identification.This model provides important references and a basis for conducting regional studies and revisiting old wells,demonstrating practical value that can be widely applied.
文摘The aging process is an inexorable fact throughout our lives and is considered a major factor in develo ping neurological dysfunctions associated with cognitive,emotional,and motor impairments.Aging-associated neurodegenerative diseases are characterized by the progressive loss of neuronal structure and function.
基金Supported by the NNSF of China(71001046)Supported by the NSF of Jiangxi Province(20114BAB211004)
文摘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.
文摘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.
文摘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.
基金supported by Defense Industrial Technology Development Program of China (Grant No. A2520110003)
文摘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.
基金This work was supported by the National Natural Science Foundation of China(No.10025420,No.20075026,No.60306006 and No.90206009)the post-doctoral fellowship provided by a Grant-in-Aid for Creative Scientific Research of Japanese govermment(No.13GS0022).The authors would also like to thank Dr.H.Yoshikawa,National Institute for Materials Science of Japan,and Dr.T.Nagatomi,Osaka University,for their helpful comments.
文摘The effective energy loss functions for Al have been derived from differential i nverse inelastic mean free path based on the extended Landau approach. It has be en revealed that the effective energy loss function is very close in value to th e theoretical surface energy loss function in the lower energy loss region but g radually approaches the theoretical bulk energy loss function in the higher ener gy loss region. Moreover, the intensity corresponding to surface excitation in e ffective energy loss functions decreases with the increase of primary electron e nergy. These facts show that the present effective energy loss function describe s not only surface excitation but also bulk excitation. At last, REELS spectra s imulated by Monte Carlo method based on use of the effective energy loss functio ns has reproduced the experimental REELS spectra with considerable success.
基金This is a Plenary Report on the International Symposium on Approximation Theory and Remote SensingApplications held in Kunming, China in April 2006Supported in part by NSF of China under grants 10571010 , 10171007 and Startup Grant for Doctoral Researchof Beijing University of Technology
文摘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.
文摘We present a fitting calculation of energy-loss function for 26 bulk materials, including 18 pure elements （Ag, A1, Au, C, Co, Cs, Cu, Er, Fe, Ge, Mg, Mo, Nb, Ni, Pd, Pt, Si, Te） and 8 compounds （AgCl, Al2O3, AlAs, CdS, SiO2, ZnS, ZnSe, ZnTe） for application to surface electron spectroscopy analysis. The experimental energy-loss function, which is derived from measured optical data, is fitted into a finite sum of formula based on the Drude-Lindhard dielectric model. By checking the oscillator strength-sum and perfect- screening-sum rules, we have validated the high accuracy of the fitting results. Further-more, based on the fitted parameters, the simulated reflection electron energy-loss spec- troscopy （REELS） spectrum shows a good agreement with experiment. The calculated fitting parameters of energy loss function are stored in an open and online database at http：//micro.ustc.edu.cn/ELF/ELF.html.
基金Jilin Science and Technology Development Plan Project(No.20200403075SF)Doctoral Research Start-Up Fund of Northeast Electric Power University(No.BSJXM-2018202).
文摘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.
基金Supported by the National Natural Science Foundation of China (Grant No.11201005)the Natural Science Foundation of Anhui Province (Grant Nos.1308085QA13+2 种基金1208085MA11)the Key Project of Natural Science Foundation of Universities in Anhui Province (Grant No.KJ2012A135)the Key Project of Distinguished Young Talents of Universities in Anhui Province (Grant No.2012SQRL028ZD)
文摘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.
基金Supported by the National Natural Science Foundation of China（11271189） Supported by the Scientific Research Innovation Project of Jiangsu Province（KYZZ116_0175）
文摘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.
基金This work was supported in part by the National Natural Science Foundation of China(Grant No.41875184)Innovation Team of“Six Talent Peaks”In Jiangsu Province(Grant No.TD-XYDXX-004).
文摘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.
