In recent years,anomaly detection has attracted much attention in industrial production.As traditional anomaly detection methods usually rely on direct comparison of samples,they often ignore the intrinsic relationshi...In recent years,anomaly detection has attracted much attention in industrial production.As traditional anomaly detection methods usually rely on direct comparison of samples,they often ignore the intrinsic relationship between samples,resulting in poor accuracy in recognizing anomalous samples.To address this problem,a knowledge distillation anomaly detection method based on feature reconstruction was proposed in this study.Knowledge distillation was performed after inverting the structure of the teacher-student network to avoid the teacher-student network sharing the same inputs and similar structure.Representability was improved by using feature splicing to unify features at different levels,and the merged features were processed and reconstructed using an improved Transformer.The experimental results show that the proposed method achieves better performance on the MVTec dataset,verifying its effectiveness and feasibility in anomaly detection tasks.This study provides a new idea to improve the accuracy and efficiency of anomaly detection.展开更多
Apostichopus japonicus(Holothuroidea,Echinodermata) is an ecological and economic species in East Asia.Conventional biometric monitoring method includes diving for samples and weighing above water,with highly variable...Apostichopus japonicus(Holothuroidea,Echinodermata) is an ecological and economic species in East Asia.Conventional biometric monitoring method includes diving for samples and weighing above water,with highly variable in weight measurement due to variation in the quantity of water in the respiratory tree and intestinal content of this species.Recently,video survey method has been applied widely in biometric detection on underwater benthos.However,because of the high flexibility of A.japonicus body,video survey method of monitoring is less used in sea cucumber.In this study,we designed a model to evaluate the wet weight of A.japonicus,using machine vision technology combined with a support vector machine(SVM) that can be used infield surveys on the A.japonicus population.Continuous dorsal images of free-moving A.japonicus individuals in seawater were captured,which also allows for the development of images of the core body edge as well as thorn segmentation.Parameters that include body length,body breadth,perimeter and area,were extracted from the core body edge images and used in SVM regression,to predict the weight of A.japonicus and for comparison with a power model.Results indicate that the use of SVM for predicting the weight of 33 A.japonicus individuals is accurate(R^2=0.99) and compatible with the power model(R^2=0.96).The image-based analysis and size-weight regression models in this study may be useful in body weight evaluation of A.japonicus in lab and field study.展开更多
A gamma-ray Computed Tomography （CT）technique based on MATLAB has been developed,and its potential for the application of multiphase flow detection has been demonstrated with simulation results.Aiming to improve the...A gamma-ray Computed Tomography （CT）technique based on MATLAB has been developed,and its potential for the application of multiphase flow detection has been demonstrated with simulation results.Aiming to improve the real time performance,we design a CT system with fixed sources and limited detecors.By dissecting the imaging region with Delaunay triangulation method,the algebraic reconstruction algorithm and simultaneous multiplicative algebraic reconstruction algorithm re implemented respective algebraic reconstruction algorithm are implemented respectively to reconstruct cross-sectional images.The resultant images can be utilized to identify flow regimes or extract characteristic parameters.展开更多
The weight of shelled shrimp is an important parameter for grading process.The weight prediction of shelled shrimp by contour area is not accurate enough because of the ignorance of the shrimp thickness.In this paper,...The weight of shelled shrimp is an important parameter for grading process.The weight prediction of shelled shrimp by contour area is not accurate enough because of the ignorance of the shrimp thickness.In this paper,a multivariate prediction model containing area,perimeter,length,and width was established.A new calibration algorithm for extracting length of shelled shrimp was proposed,which contains binary image thinning,branch recognition and elimination,and length reconstruction,while its width was calculated during the process of length extracting.The model was further validated with another set of images from 30 shelled shrimps.For a comparison purpose,artificial neural network(ANN) was used for the shrimp weight predication.The ANN model resulted in a better prediction accuracy(with the average relative error at 2.67%),but took a tenfold increase in calculation time compared with the weight-area-perimeter(WAP) model(with the average relative error at 3.02%).We thus conclude that the WAP model is a better method for the prediction of the weight of shelled red shrimp.展开更多
Second-order stochastic dominance plays an important role in reliability and various branches of economics such as finance and decision-making under risk, and statistical testing for the stochastic dominance is often ...Second-order stochastic dominance plays an important role in reliability and various branches of economics such as finance and decision-making under risk, and statistical testing for the stochastic dominance is often useful in practice. In this paper, we present a test of stochastic equality under the constraint of second-order stochastic dominance based on the theory of empirical processes. The asymptotic distribution of the test statistic is obtained, and a simple method to compute the critical value is derived. Simulation results and real data examples are presented to illustrate the proposed test method.展开更多
文摘In recent years,anomaly detection has attracted much attention in industrial production.As traditional anomaly detection methods usually rely on direct comparison of samples,they often ignore the intrinsic relationship between samples,resulting in poor accuracy in recognizing anomalous samples.To address this problem,a knowledge distillation anomaly detection method based on feature reconstruction was proposed in this study.Knowledge distillation was performed after inverting the structure of the teacher-student network to avoid the teacher-student network sharing the same inputs and similar structure.Representability was improved by using feature splicing to unify features at different levels,and the merged features were processed and reconstructed using an improved Transformer.The experimental results show that the proposed method achieves better performance on the MVTec dataset,verifying its effectiveness and feasibility in anomaly detection tasks.This study provides a new idea to improve the accuracy and efficiency of anomaly detection.
基金Supported by the National Natural Science Foundation of China(NSFC)-Shandong Joint Fund for Marine Science Research Centers(No.U1406403)the National Key Technology Research and Development Program of China(No.2011BAD13B02)+1 种基金the National Marine Public Welfare Research Project(No.201205023)the Strategic Priority Research Program of Chinese Academy of Sciences(No.XDA11020404)
文摘Apostichopus japonicus(Holothuroidea,Echinodermata) is an ecological and economic species in East Asia.Conventional biometric monitoring method includes diving for samples and weighing above water,with highly variable in weight measurement due to variation in the quantity of water in the respiratory tree and intestinal content of this species.Recently,video survey method has been applied widely in biometric detection on underwater benthos.However,because of the high flexibility of A.japonicus body,video survey method of monitoring is less used in sea cucumber.In this study,we designed a model to evaluate the wet weight of A.japonicus,using machine vision technology combined with a support vector machine(SVM) that can be used infield surveys on the A.japonicus population.Continuous dorsal images of free-moving A.japonicus individuals in seawater were captured,which also allows for the development of images of the core body edge as well as thorn segmentation.Parameters that include body length,body breadth,perimeter and area,were extracted from the core body edge images and used in SVM regression,to predict the weight of A.japonicus and for comparison with a power model.Results indicate that the use of SVM for predicting the weight of 33 A.japonicus individuals is accurate(R^2=0.99) and compatible with the power model(R^2=0.96).The image-based analysis and size-weight regression models in this study may be useful in body weight evaluation of A.japonicus in lab and field study.
基金supported by National Natural Science Foundation of China(No.60820106002,50937005,60532020)
文摘A gamma-ray Computed Tomography （CT）technique based on MATLAB has been developed,and its potential for the application of multiphase flow detection has been demonstrated with simulation results.Aiming to improve the real time performance,we design a CT system with fixed sources and limited detecors.By dissecting the imaging region with Delaunay triangulation method,the algebraic reconstruction algorithm and simultaneous multiplicative algebraic reconstruction algorithm re implemented respective algebraic reconstruction algorithm are implemented respectively to reconstruct cross-sectional images.The resultant images can be utilized to identify flow regimes or extract characteristic parameters.
文摘The weight of shelled shrimp is an important parameter for grading process.The weight prediction of shelled shrimp by contour area is not accurate enough because of the ignorance of the shrimp thickness.In this paper,a multivariate prediction model containing area,perimeter,length,and width was established.A new calibration algorithm for extracting length of shelled shrimp was proposed,which contains binary image thinning,branch recognition and elimination,and length reconstruction,while its width was calculated during the process of length extracting.The model was further validated with another set of images from 30 shelled shrimps.For a comparison purpose,artificial neural network(ANN) was used for the shrimp weight predication.The ANN model resulted in a better prediction accuracy(with the average relative error at 2.67%),but took a tenfold increase in calculation time compared with the weight-area-perimeter(WAP) model(with the average relative error at 3.02%).We thus conclude that the WAP model is a better method for the prediction of the weight of shelled red shrimp.
基金This work is supported by Grants from the Natural Science Foundation of China （11271039） Specialized Research Fund for the Doctoral Program of Higher Education+2 种基金 Research Fund of Weifang University （2011Z24） Funding Project of Science and Technology Research Plan of Weifang City （201301019） The Natural Science Foundation of Shandong （ZR2013FL032）.
文摘Second-order stochastic dominance plays an important role in reliability and various branches of economics such as finance and decision-making under risk, and statistical testing for the stochastic dominance is often useful in practice. In this paper, we present a test of stochastic equality under the constraint of second-order stochastic dominance based on the theory of empirical processes. The asymptotic distribution of the test statistic is obtained, and a simple method to compute the critical value is derived. Simulation results and real data examples are presented to illustrate the proposed test method.
