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
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
In this paper we propose an absolute error loss EB estimator for parameter of one-side truncation distribution families. Under some conditions we have proved that the convergence rates of its Bayes risk is o, where 0&...In this paper we propose an absolute error loss EB estimator for parameter of one-side truncation distribution families. Under some conditions we have proved that the convergence rates of its Bayes risk is o, where 0<λ,r≤1,Mn≤lnln n (for large n),Mn→∞ as n→∞.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
According to the World Health Organization,about 50 million people worldwide suffer from epilepsy.The detection and treatment of epilepsy face great challenges.Electroencephalogram(EEG)is a significant research object...According to the World Health Organization,about 50 million people worldwide suffer from epilepsy.The detection and treatment of epilepsy face great challenges.Electroencephalogram(EEG)is a significant research object widely used in diagnosis and treatment of epilepsy.In this paper,an adaptive feature learning model for EEG signals is proposed,which combines Huber loss function with adaptive weight penalty term.Firstly,each EEG signal is decomposed by intrinsic time-scale decomposition.Secondly,the statistical index values are calculated from the instantaneous amplitude and frequency of every component and fed into the proposed model.Finally,the discriminative features learned by the proposed model are used to detect seizures.Our main innovation is to consider a highly flexible penalization based on Huber loss function,which can set different weights according to the influence of different features on epilepsy detection.Besides,the new model can be solved by proximal alternating direction multiplier method,which can effectively ensure the convergence of the algorithm.The performance of the proposed method is evaluated on three public EEG datasets provided by the Bonn University,Childrens Hospital Boston-Massachusetts Institute of Technology,and Neurological and Sleep Center at Hauz Khas,New Delhi(New Delhi Epilepsy data).The recognition accuracy on these two datasets is 98%and 99.05%,respectively,indicating the application value of the new model.展开更多
This paper studies the problem of robust H∞ control of piecewise-linear chaotic systems with random data loss. The communication links between the plant and the controller are assumed to be imperfect （that is, data ...This paper studies the problem of robust H∞ control of piecewise-linear chaotic systems with random data loss. The communication links between the plant and the controller are assumed to be imperfect （that is, data loss occurs intermittently, which appears typically in a network environment）. The data loss is modelled as a random process which obeys a Bernoulli distribution. In the face of random data loss, a piecewise controller is designed to robustly stabilize the networked system in the sense of mean square and also achieve a prescribed H∞ disturbance attenuation performance based on a piecewise-quadratic Lyapunov function. The required H∞ controllers can be designed by solving a set of linear matrix inequalities （LMIs）. Chua＇s system is provided to illustrate the usefulness and applicability of the developed theoretical results.展开更多
Accurate prediction of formation pore pressure is essential to predict fluid flow and manage hydrocarbon production in petroleum engineering.Recent deep learning technique has been receiving more interest due to the g...Accurate prediction of formation pore pressure is essential to predict fluid flow and manage hydrocarbon production in petroleum engineering.Recent deep learning technique has been receiving more interest due to the great potential to deal with pore pressure prediction.However,most of the traditional deep learning models are less efficient to address generalization problems.To fill this technical gap,in this work,we developed a new adaptive physics-informed deep learning model with high generalization capability to predict pore pressure values directly from seismic data.Specifically,the new model,named CGP-NN,consists of a novel parametric features extraction approach(1DCPP),a stacked multilayer gated recurrent model(multilayer GRU),and an adaptive physics-informed loss function.Through machine training,the developed model can automatically select the optimal physical model to constrain the results for each pore pressure prediction.The CGP-NN model has the best generalization when the physicsrelated metricλ=0.5.A hybrid approach combining Eaton and Bowers methods is also proposed to build machine-learnable labels for solving the problem of few labels.To validate the developed model and methodology,a case study on a complex reservoir in Tarim Basin was further performed to demonstrate the high accuracy on the pore pressure prediction of new wells along with the strong generalization ability.The adaptive physics-informed deep learning approach presented here has potential application in the prediction of pore pressures coupled with multiple genesis mechanisms using seismic data.展开更多
With the successful application and breakthrough of deep learning technology in image segmentation,there has been continuous development in the field of seismic facies interpretation using convolutional neural network...With the successful application and breakthrough of deep learning technology in image segmentation,there has been continuous development in the field of seismic facies interpretation using convolutional neural networks.These intelligent and automated methods significantly reduce manual labor,particularly in the laborious task of manually labeling seismic facies.However,the extensive demand for training data imposes limitations on their wider application.To overcome this challenge,we adopt the UNet architecture as the foundational network structure for seismic facies classification,which has demonstrated effective segmentation results even with small-sample training data.Additionally,we integrate spatial pyramid pooling and dilated convolution modules into the network architecture to enhance the perception of spatial information across a broader range.The seismic facies classification test on the public data from the F3 block verifies the superior performance of our proposed improved network structure in delineating seismic facies boundaries.Comparative analysis against the traditional UNet model reveals that our method achieves more accurate predictive classification results,as evidenced by various evaluation metrics for image segmentation.Obviously,the classification accuracy reaches an impressive 96%.Furthermore,the results of seismic facies classification in the seismic slice dimension provide further confirmation of the superior performance of our proposed method,which accurately defines the range of different seismic facies.This approach holds significant potential for analyzing geological patterns and extracting valuable depositional information.展开更多
Efficiently solving partial differential equations(PDEs)is a long-standing challenge in mathematics and physics research.In recent years,the rapid development of artificial intelligence technology has brought deep lea...Efficiently solving partial differential equations(PDEs)is a long-standing challenge in mathematics and physics research.In recent years,the rapid development of artificial intelligence technology has brought deep learning-based methods to the forefront of research on numerical methods for partial differential equations.Among them,physics-informed neural networks(PINNs)are a new class of deep learning methods that show great potential in solving PDEs and predicting complex physical phenomena.In the field of nonlinear science,solitary waves and rogue waves have been important research topics.In this paper,we propose an improved PINN that enhances the physical constraints of the neural network model by adding gradient information constraints.In addition,we employ meta-learning optimization to speed up the training process.We apply the improved PINNs to the numerical simulation and prediction of solitary and rogue waves.We evaluate the accuracy of the prediction results by error analysis.The experimental results show that the improved PINNs can make more accurate predictions in less time than that of the original PINNs.展开更多
Infrared small target detection is a common task in infrared image processing.Under limited computa⁃tional resources.Traditional methods for infrared small target detection face a trade-off between the detection rate ...Infrared small target detection is a common task in infrared image processing.Under limited computa⁃tional resources.Traditional methods for infrared small target detection face a trade-off between the detection rate and the accuracy.A fast infrared small target detection method tailored for resource-constrained conditions is pro⁃posed for the YOLOv5s model.This method introduces an additional small target detection head and replaces the original Intersection over Union(IoU)metric with Normalized Wasserstein Distance(NWD),while considering both the detection accuracy and the detection speed of infrared small targets.Experimental results demonstrate that the proposed algorithm achieves a maximum effective detection speed of 95 FPS on a 15 W TPU,while reach⁃ing a maximum effective detection accuracy of 91.9 AP@0.5,effectively improving the efficiency of infrared small target detection under resource-constrained conditions.展开更多
Generative adversarial network(GAN)has achieved great success in many fields such as computer vision,speech processing,and natural language processing,because of its powerful capabilities for generating realistic samp...Generative adversarial network(GAN)has achieved great success in many fields such as computer vision,speech processing,and natural language processing,because of its powerful capabilities for generating realistic samples.In this paper,we introduce GAN into the field of electromagnetic signal classification(ESC).ESC plays an important role in both military and civilian domains.However,in many specific scenarios,we can’t obtain enough labeled data,which cause failure of deep learning methods because they are easy to fall into over-fitting.Fortunately,semi-supervised learning(SSL)can leverage the large amount of unlabeled data to enhance the classification performance of classifiers,especially in scenarios with limited amount of labeled data.We present an SSL framework by incorporating GAN,which can directly process the raw in-phase and quadrature(IQ)signal data.According to the characteristics of the electromagnetic signal,we propose a weighted loss function,leading to an effective classifier to realize the end-to-end classification of the electromagnetic signal.We validate the proposed method on both public RML2016.04c dataset and real-world Aircraft Communications Addressing and Reporting System(ACARS)signal dataset.Extensive experimental results show that the proposed framework obtains a significant increase in classification accuracy compared with the state-of-the-art studies.展开更多
This paper considers a robust kernel regularized classification algorithm with a non-convex loss function which is proposed to alleviate the performance deterioration caused by the outliers.A comparison relationship b...This paper considers a robust kernel regularized classification algorithm with a non-convex loss function which is proposed to alleviate the performance deterioration caused by the outliers.A comparison relationship between the excess misclassification error and the excess generalization error is provided;from this,along with the convex analysis theory,a kind of learning rate is derived.The results show that the performance of the classifier is effected by the outliers,and the extent of impact can be controlled by choosing the homotopy parameters properly.展开更多
Electricity plays a vital role in daily life and economic development.The status of the indicator lights of the power plant needs to be checked regularly to ensure the normal supply of electricity.Aiming at the proble...Electricity plays a vital role in daily life and economic development.The status of the indicator lights of the power plant needs to be checked regularly to ensure the normal supply of electricity.Aiming at the problem of a large amount of data and different sizes of indicator light detection,we propose an improved You Only Look Once vision 5(YOLOv5)power plant indicator light detection algorithm.The algorithm improves the feature extraction ability based on YOLOv5s.First,our algorithm enhances the ability of the network to perceive small objects by combining attention modules for multi-scale feature extraction.Second,we adjust the loss function to ensure the stability of the object frame during the regression process and improve the conver-gence accuracy.Finally,transfer learning is used to augment the dataset to improve the robustness of the algorithm.The experimental results show that the average accuracy of the proposed squeeze-and-excitation YOLOv5s(SE-YOLOv5s)algorithm is increased by 4.39%to 95.31%compared with the YOLOv5s algorithm.The proposed algorithm can better meet the engineering needs of power plant indicator light detection.展开更多
A 3D laser scanning strategy based on cascaded deep neural network is proposed for the scanning system converted from 2D Lidar with a pitching motion device. The strategy is aimed at moving target detection and monito...A 3D laser scanning strategy based on cascaded deep neural network is proposed for the scanning system converted from 2D Lidar with a pitching motion device. The strategy is aimed at moving target detection and monitoring. Combining the device characteristics, the strategy first proposes a cascaded deep neural network, which inputs 2D point cloud, color image and pitching angle. The outputs are target distance and speed classification. And the cross-entropy loss function of network is modified by using focal loss and uniform distribution to improve the recognition accuracy. Then a pitching range and speed model are proposed to determine pitching motion parameters. Finally, the adaptive scanning is realized by integral separate speed PID. The experimental results show that the accuracies of the improved network target detection box, distance and speed classification are 90.17%, 96.87% and 96.97%, respectively. The average speed error of the improved PID is 0.4239°/s, and the average strategy execution time is 0.1521 s.The range and speed model can effectively reduce the collection of useless information and the deformation of the target point cloud. Conclusively, the experimental of overall scanning strategy show that it can improve target point cloud integrity and density while ensuring the capture of target.展开更多
In this paper, we construct the empirical B ay es test (EBT) for the parameter of the truncated-type distribution families. It is found that the proposed test is asymptotically optimal. The convergence rate of the EBT...In this paper, we construct the empirical B ay es test (EBT) for the parameter of the truncated-type distribution families. It is found that the proposed test is asymptotically optimal. The convergence rate of the EBT is given.展开更多
Grating-based X-ray phase-contrast imaging enhances the contrast of imaged objects,particularly soft tissues.However,the radiation dose in computed tomography(CT)is generally excessive owing to the complex collection ...Grating-based X-ray phase-contrast imaging enhances the contrast of imaged objects,particularly soft tissues.However,the radiation dose in computed tomography(CT)is generally excessive owing to the complex collection scheme.Sparse-view CT collection reduces the radiation dose,but with reduced resolution and reconstructed artifacts particularly in analytical reconstruction methods.Recently,deep learning has been employed in sparse-view CT reconstruction and achieved stateof-the-art results.Nevertheless,its low generalization performance and requirement for abundant training datasets have hindered the practical application of deep learning in phase-contrast CT.In this study,a CT model was used to generate a substantial number of simulated training datasets,thereby circumventing the need for experimental datasets.By training a network with simulated training datasets,the proposed method achieves high generalization performance in attenuationbased CT and phase-contrast CT,despite the lack of sufficient experimental datasets.In experiments utilizing only half of the CT data,our proposed method obtained an image quality comparable to that of the filtered back-projection algorithm with full-view projection.The proposed method simultaneously addresses two challenges in phase-contrast three-dimensional imaging,namely the lack of experimental datasets and the high exposure dose,through model-driven deep learning.This method significantly accelerates the practical application of phase-contrast CT.展开更多
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.
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In this paper we propose an absolute error loss EB estimator for parameter of one-side truncation distribution families. Under some conditions we have proved that the convergence rates of its Bayes risk is o, where 0<λ,r≤1,Mn≤lnln n (for large n),Mn→∞ as n→∞.
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Supported by National Natural Science Foundation of China(Grant Nos.11701144,11971149)Henan Province Key and Promotion Special(Science and Technology)Project(Grant No.212102310305).
文摘According to the World Health Organization,about 50 million people worldwide suffer from epilepsy.The detection and treatment of epilepsy face great challenges.Electroencephalogram(EEG)is a significant research object widely used in diagnosis and treatment of epilepsy.In this paper,an adaptive feature learning model for EEG signals is proposed,which combines Huber loss function with adaptive weight penalty term.Firstly,each EEG signal is decomposed by intrinsic time-scale decomposition.Secondly,the statistical index values are calculated from the instantaneous amplitude and frequency of every component and fed into the proposed model.Finally,the discriminative features learned by the proposed model are used to detect seizures.Our main innovation is to consider a highly flexible penalization based on Huber loss function,which can set different weights according to the influence of different features on epilepsy detection.Besides,the new model can be solved by proximal alternating direction multiplier method,which can effectively ensure the convergence of the algorithm.The performance of the proposed method is evaluated on three public EEG datasets provided by the Bonn University,Childrens Hospital Boston-Massachusetts Institute of Technology,and Neurological and Sleep Center at Hauz Khas,New Delhi(New Delhi Epilepsy data).The recognition accuracy on these two datasets is 98%and 99.05%,respectively,indicating the application value of the new model.
基金Project partially supported by the Young Scientists Fund of the National Natural Science Foundation of China(Grant No.60904004)the Key Youth Science and Technology Foundation of University of Electronic Science and Technology of China (Grant No.L08010201JX0720)
文摘This paper studies the problem of robust H∞ control of piecewise-linear chaotic systems with random data loss. The communication links between the plant and the controller are assumed to be imperfect （that is, data loss occurs intermittently, which appears typically in a network environment）. The data loss is modelled as a random process which obeys a Bernoulli distribution. In the face of random data loss, a piecewise controller is designed to robustly stabilize the networked system in the sense of mean square and also achieve a prescribed H∞ disturbance attenuation performance based on a piecewise-quadratic Lyapunov function. The required H∞ controllers can be designed by solving a set of linear matrix inequalities （LMIs）. Chua＇s system is provided to illustrate the usefulness and applicability of the developed theoretical results.
基金funded by the National Natural Science Foundation of China(General Program:No.52074314,No.U19B6003-05)National Key Research and Development Program of China(2019YFA0708303-05)。
文摘Accurate prediction of formation pore pressure is essential to predict fluid flow and manage hydrocarbon production in petroleum engineering.Recent deep learning technique has been receiving more interest due to the great potential to deal with pore pressure prediction.However,most of the traditional deep learning models are less efficient to address generalization problems.To fill this technical gap,in this work,we developed a new adaptive physics-informed deep learning model with high generalization capability to predict pore pressure values directly from seismic data.Specifically,the new model,named CGP-NN,consists of a novel parametric features extraction approach(1DCPP),a stacked multilayer gated recurrent model(multilayer GRU),and an adaptive physics-informed loss function.Through machine training,the developed model can automatically select the optimal physical model to constrain the results for each pore pressure prediction.The CGP-NN model has the best generalization when the physicsrelated metricλ=0.5.A hybrid approach combining Eaton and Bowers methods is also proposed to build machine-learnable labels for solving the problem of few labels.To validate the developed model and methodology,a case study on a complex reservoir in Tarim Basin was further performed to demonstrate the high accuracy on the pore pressure prediction of new wells along with the strong generalization ability.The adaptive physics-informed deep learning approach presented here has potential application in the prediction of pore pressures coupled with multiple genesis mechanisms using seismic data.
基金funded by the Fundamental Research Project of CNPC Geophysical Key Lab(2022DQ0604-4)the Strategic Cooperation Technology Projects of China National Petroleum Corporation and China University of Petroleum-Beijing(ZLZX 202003)。
文摘With the successful application and breakthrough of deep learning technology in image segmentation,there has been continuous development in the field of seismic facies interpretation using convolutional neural networks.These intelligent and automated methods significantly reduce manual labor,particularly in the laborious task of manually labeling seismic facies.However,the extensive demand for training data imposes limitations on their wider application.To overcome this challenge,we adopt the UNet architecture as the foundational network structure for seismic facies classification,which has demonstrated effective segmentation results even with small-sample training data.Additionally,we integrate spatial pyramid pooling and dilated convolution modules into the network architecture to enhance the perception of spatial information across a broader range.The seismic facies classification test on the public data from the F3 block verifies the superior performance of our proposed improved network structure in delineating seismic facies boundaries.Comparative analysis against the traditional UNet model reveals that our method achieves more accurate predictive classification results,as evidenced by various evaluation metrics for image segmentation.Obviously,the classification accuracy reaches an impressive 96%.Furthermore,the results of seismic facies classification in the seismic slice dimension provide further confirmation of the superior performance of our proposed method,which accurately defines the range of different seismic facies.This approach holds significant potential for analyzing geological patterns and extracting valuable depositional information.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.42005003 and 41475094).
文摘Efficiently solving partial differential equations(PDEs)is a long-standing challenge in mathematics and physics research.In recent years,the rapid development of artificial intelligence technology has brought deep learning-based methods to the forefront of research on numerical methods for partial differential equations.Among them,physics-informed neural networks(PINNs)are a new class of deep learning methods that show great potential in solving PDEs and predicting complex physical phenomena.In the field of nonlinear science,solitary waves and rogue waves have been important research topics.In this paper,we propose an improved PINN that enhances the physical constraints of the neural network model by adding gradient information constraints.In addition,we employ meta-learning optimization to speed up the training process.We apply the improved PINNs to the numerical simulation and prediction of solitary and rogue waves.We evaluate the accuracy of the prediction results by error analysis.The experimental results show that the improved PINNs can make more accurate predictions in less time than that of the original PINNs.
文摘Infrared small target detection is a common task in infrared image processing.Under limited computa⁃tional resources.Traditional methods for infrared small target detection face a trade-off between the detection rate and the accuracy.A fast infrared small target detection method tailored for resource-constrained conditions is pro⁃posed for the YOLOv5s model.This method introduces an additional small target detection head and replaces the original Intersection over Union(IoU)metric with Normalized Wasserstein Distance(NWD),while considering both the detection accuracy and the detection speed of infrared small targets.Experimental results demonstrate that the proposed algorithm achieves a maximum effective detection speed of 95 FPS on a 15 W TPU,while reach⁃ing a maximum effective detection accuracy of 91.9 AP@0.5,effectively improving the efficiency of infrared small target detection under resource-constrained conditions.
基金the National Natural Science Foundation of China(Nos.61771380,U19B2015,U1730109).
文摘Generative adversarial network(GAN)has achieved great success in many fields such as computer vision,speech processing,and natural language processing,because of its powerful capabilities for generating realistic samples.In this paper,we introduce GAN into the field of electromagnetic signal classification(ESC).ESC plays an important role in both military and civilian domains.However,in many specific scenarios,we can’t obtain enough labeled data,which cause failure of deep learning methods because they are easy to fall into over-fitting.Fortunately,semi-supervised learning(SSL)can leverage the large amount of unlabeled data to enhance the classification performance of classifiers,especially in scenarios with limited amount of labeled data.We present an SSL framework by incorporating GAN,which can directly process the raw in-phase and quadrature(IQ)signal data.According to the characteristics of the electromagnetic signal,we propose a weighted loss function,leading to an effective classifier to realize the end-to-end classification of the electromagnetic signal.We validate the proposed method on both public RML2016.04c dataset and real-world Aircraft Communications Addressing and Reporting System(ACARS)signal dataset.Extensive experimental results show that the proposed framework obtains a significant increase in classification accuracy compared with the state-of-the-art studies.
基金supported by the NSF(61877039)the NSFC/RGC Joint Research Scheme(12061160462 and N City U 102/20)of China+2 种基金the NSF(LY19F020013)of Zhejiang Provincethe Special Project for Scientific and Technological Cooperation(20212BDH80021)of Jiangxi Provincethe Science and Technology Project in Jiangxi Province Department of Education(GJJ211334)。
文摘This paper considers a robust kernel regularized classification algorithm with a non-convex loss function which is proposed to alleviate the performance deterioration caused by the outliers.A comparison relationship between the excess misclassification error and the excess generalization error is provided;from this,along with the convex analysis theory,a kind of learning rate is derived.The results show that the performance of the classifier is effected by the outliers,and the extent of impact can be controlled by choosing the homotopy parameters properly.
基金supported by the National Natural Science Foun-dation of China(Nos.61702347,62027801)the Natural Sci-ence Foundation of Hebei Province(Nos.F2022210007,F2017210161)+1 种基金the Science and Technology Project of Hebei Education Department(Nos.ZD2022100,QN2017132)the Central Guidance on Local Science and Technology Development Fund(No.226Z0501G)。
文摘Electricity plays a vital role in daily life and economic development.The status of the indicator lights of the power plant needs to be checked regularly to ensure the normal supply of electricity.Aiming at the problem of a large amount of data and different sizes of indicator light detection,we propose an improved You Only Look Once vision 5(YOLOv5)power plant indicator light detection algorithm.The algorithm improves the feature extraction ability based on YOLOv5s.First,our algorithm enhances the ability of the network to perceive small objects by combining attention modules for multi-scale feature extraction.Second,we adjust the loss function to ensure the stability of the object frame during the regression process and improve the conver-gence accuracy.Finally,transfer learning is used to augment the dataset to improve the robustness of the algorithm.The experimental results show that the average accuracy of the proposed squeeze-and-excitation YOLOv5s(SE-YOLOv5s)algorithm is increased by 4.39%to 95.31%compared with the YOLOv5s algorithm.The proposed algorithm can better meet the engineering needs of power plant indicator light detection.
基金funded by National Natural Science Foundation of China(Grant No. 51805146)the Fundamental Research Funds for the Central Universities (Grant No. B200202221)+1 种基金Jiangsu Key R&D Program (Grant Nos. BE2018004-1, BE2018004)College Students’ Innovative Entrepreneurial Training Plan Program (Grant No. 2020102941513)。
文摘A 3D laser scanning strategy based on cascaded deep neural network is proposed for the scanning system converted from 2D Lidar with a pitching motion device. The strategy is aimed at moving target detection and monitoring. Combining the device characteristics, the strategy first proposes a cascaded deep neural network, which inputs 2D point cloud, color image and pitching angle. The outputs are target distance and speed classification. And the cross-entropy loss function of network is modified by using focal loss and uniform distribution to improve the recognition accuracy. Then a pitching range and speed model are proposed to determine pitching motion parameters. Finally, the adaptive scanning is realized by integral separate speed PID. The experimental results show that the accuracies of the improved network target detection box, distance and speed classification are 90.17%, 96.87% and 96.97%, respectively. The average speed error of the improved PID is 0.4239°/s, and the average strategy execution time is 0.1521 s.The range and speed model can effectively reduce the collection of useless information and the deformation of the target point cloud. Conclusively, the experimental of overall scanning strategy show that it can improve target point cloud integrity and density while ensuring the capture of target.
文摘In this paper, we construct the empirical B ay es test (EBT) for the parameter of the truncated-type distribution families. It is found that the proposed test is asymptotically optimal. The convergence rate of the EBT is given.
基金supported by the National Natural Science Foundation of China(Nos.U2032148,U2032157,11775224)USTC Research Funds of the Double First-Class Initiative(No.YD2310002008)the National Key Research and Development Program of China(No.2017YFA0402904),the Youth Innovation Promotion Association,CAS(No.2020457)。
文摘Grating-based X-ray phase-contrast imaging enhances the contrast of imaged objects,particularly soft tissues.However,the radiation dose in computed tomography(CT)is generally excessive owing to the complex collection scheme.Sparse-view CT collection reduces the radiation dose,but with reduced resolution and reconstructed artifacts particularly in analytical reconstruction methods.Recently,deep learning has been employed in sparse-view CT reconstruction and achieved stateof-the-art results.Nevertheless,its low generalization performance and requirement for abundant training datasets have hindered the practical application of deep learning in phase-contrast CT.In this study,a CT model was used to generate a substantial number of simulated training datasets,thereby circumventing the need for experimental datasets.By training a network with simulated training datasets,the proposed method achieves high generalization performance in attenuationbased CT and phase-contrast CT,despite the lack of sufficient experimental datasets.In experiments utilizing only half of the CT data,our proposed method obtained an image quality comparable to that of the filtered back-projection algorithm with full-view projection.The proposed method simultaneously addresses two challenges in phase-contrast three-dimensional imaging,namely the lack of experimental datasets and the high exposure dose,through model-driven deep learning.This method significantly accelerates the practical application of phase-contrast CT.
