The non-stationary of the motor imagery electroencephalography(MI-EEG)signal is one of the main limitations for the development of motor imagery brain-computer interfaces(MI-BCI).The nonstationary of the MI-EEG signal...The non-stationary of the motor imagery electroencephalography(MI-EEG)signal is one of the main limitations for the development of motor imagery brain-computer interfaces(MI-BCI).The nonstationary of the MI-EEG signal and the changes of the experimental environment make the feature distribution of the testing set and training set deviates,which reduces the classification accuracy of MI-BCI.In this paper,we propose a Kullback–Leibler divergence(KL)-based transfer learning algorithm to solve the problem of feature transfer,the proposed algorithm uses KL to measure the similarity between the training set and the testing set,adds support vector machine(SVM)classification probability to classify and weight the covariance,and discards the poorly performing samples.The results show that the proposed algorithm can significantly improve the classification accuracy of the testing set compared with the traditional algorithms,especially for subjects with medium classification accuracy.Moreover,the algorithm based on transfer learning has the potential to improve the consistency of feature distribution that the traditional algorithms do not have,which is significant for the application of MI-BCI.展开更多
The quick spread of the CoronavirusDisease(COVID-19)infection around the world considered a real danger for global health.The biological structure and symptoms of COVID-19 are similar to other viral chest maladies,whi...The quick spread of the CoronavirusDisease(COVID-19)infection around the world considered a real danger for global health.The biological structure and symptoms of COVID-19 are similar to other viral chest maladies,which makes it challenging and a big issue to improve approaches for efficient identification of COVID-19 disease.In this study,an automatic prediction of COVID-19 identification is proposed to automatically discriminate between healthy and COVID-19 infected subjects in X-ray images using two successful moderns are traditional machine learning methods(e.g.,artificial neural network(ANN),support vector machine(SVM),linear kernel and radial basis function(RBF),k-nearest neighbor(k-NN),Decision Tree(DT),andCN2 rule inducer techniques)and deep learningmodels(e.g.,MobileNets V2,ResNet50,GoogleNet,DarkNet andXception).A largeX-ray dataset has been created and developed,namely the COVID-19 vs.Normal(400 healthy cases,and 400 COVID cases).To the best of our knowledge,it is currently the largest publicly accessible COVID-19 dataset with the largest number of X-ray images of confirmed COVID-19 infection cases.Based on the results obtained from the experiments,it can be concluded that all the models performed well,deep learning models had achieved the optimum accuracy of 98.8%in ResNet50 model.In comparison,in traditional machine learning techniques, the SVM demonstrated the best result for an accuracy of 95% and RBFaccuracy 94% for the prediction of coronavirus disease 2019.展开更多
Rolling bearings are key components of the drivetrain in wind turbines,and their health is critical to wind turbine operation.In practical diagnosis tasks,the vibration signal is usually interspersed with many disturb...Rolling bearings are key components of the drivetrain in wind turbines,and their health is critical to wind turbine operation.In practical diagnosis tasks,the vibration signal is usually interspersed with many disturbing components,and the variation of operating conditions leads to unbalanced data distribution among different conditions.Although intelligent diagnosis methods based on deep learning have been intensively studied,it is still challenging to diagnose rolling bearing faults with small amounts of samples.To address the above issue,we introduce the deep residual joint transfer strategy method for the cross-condition fault diagnosis of rolling bearings.One-dimensional vibration signals are pre-processed by overlapping feature extraction techniques to fully extract fault characteristics.The deep residual network is trained in training tasks with sufficient samples,for fault pattern classification.Subsequently,three transfer strategies are used to explore the generalizability and adaptability of the pre-trained models to the data distribution in target tasks.Among them,the feature transferability between different tasks is explored by model transfer,and it is validated that minimizing data differences of tasks through a dual-stream adaptation structure helps to enhance generalization of the models to the target tasks.In the experiments of rolling bearing faults with unbalanced data conditions,localized faults of motor bearings and planet bearings are successfully identified,and good fault classification results are achieved,which provide guidance for the cross-condition fault diagnosis of rolling bearings with small amounts of training data.展开更多
In some image classification tasks, similarities among different categories are different and the samples are usually misclassified as highly similar categories. To distinguish highly similar categories, more specific...In some image classification tasks, similarities among different categories are different and the samples are usually misclassified as highly similar categories. To distinguish highly similar categories, more specific features are required so that the classifier can improve the classification performance. In this paper, we propose a novel two-level hierarchical feature learning framework based on the deep convolutional neural network(CNN), which is simple and effective. First, the deep feature extractors of different levels are trained using the transfer learning method that fine-tunes the pre-trained deep CNN model toward the new target dataset. Second, the general feature extracted from all the categories and the specific feature extracted from highly similar categories are fused into a feature vector. Then the final feature representation is fed into a linear classifier. Finally, experiments using the Caltech-256, Oxford Flower-102, and Tasmania Coral Point Count(CPC) datasets demonstrate that the expression ability of the deep features resulting from two-level hierarchical feature learning is powerful. Our proposed method effectively increases the classification accuracy in comparison with flat multiple classification methods.展开更多
文摘The non-stationary of the motor imagery electroencephalography(MI-EEG)signal is one of the main limitations for the development of motor imagery brain-computer interfaces(MI-BCI).The nonstationary of the MI-EEG signal and the changes of the experimental environment make the feature distribution of the testing set and training set deviates,which reduces the classification accuracy of MI-BCI.In this paper,we propose a Kullback–Leibler divergence(KL)-based transfer learning algorithm to solve the problem of feature transfer,the proposed algorithm uses KL to measure the similarity between the training set and the testing set,adds support vector machine(SVM)classification probability to classify and weight the covariance,and discards the poorly performing samples.The results show that the proposed algorithm can significantly improve the classification accuracy of the testing set compared with the traditional algorithms,especially for subjects with medium classification accuracy.Moreover,the algorithm based on transfer learning has the potential to improve the consistency of feature distribution that the traditional algorithms do not have,which is significant for the application of MI-BCI.
文摘The quick spread of the CoronavirusDisease(COVID-19)infection around the world considered a real danger for global health.The biological structure and symptoms of COVID-19 are similar to other viral chest maladies,which makes it challenging and a big issue to improve approaches for efficient identification of COVID-19 disease.In this study,an automatic prediction of COVID-19 identification is proposed to automatically discriminate between healthy and COVID-19 infected subjects in X-ray images using two successful moderns are traditional machine learning methods(e.g.,artificial neural network(ANN),support vector machine(SVM),linear kernel and radial basis function(RBF),k-nearest neighbor(k-NN),Decision Tree(DT),andCN2 rule inducer techniques)and deep learningmodels(e.g.,MobileNets V2,ResNet50,GoogleNet,DarkNet andXception).A largeX-ray dataset has been created and developed,namely the COVID-19 vs.Normal(400 healthy cases,and 400 COVID cases).To the best of our knowledge,it is currently the largest publicly accessible COVID-19 dataset with the largest number of X-ray images of confirmed COVID-19 infection cases.Based on the results obtained from the experiments,it can be concluded that all the models performed well,deep learning models had achieved the optimum accuracy of 98.8%in ResNet50 model.In comparison,in traditional machine learning techniques, the SVM demonstrated the best result for an accuracy of 95% and RBFaccuracy 94% for the prediction of coronavirus disease 2019.
基金This work was supported by National Natural Science Foundation of China(52275080).The authors are grateful to the reviewers for their valuable comments and to Bei Wang for her help in polishing the English of this paper.
文摘Rolling bearings are key components of the drivetrain in wind turbines,and their health is critical to wind turbine operation.In practical diagnosis tasks,the vibration signal is usually interspersed with many disturbing components,and the variation of operating conditions leads to unbalanced data distribution among different conditions.Although intelligent diagnosis methods based on deep learning have been intensively studied,it is still challenging to diagnose rolling bearing faults with small amounts of samples.To address the above issue,we introduce the deep residual joint transfer strategy method for the cross-condition fault diagnosis of rolling bearings.One-dimensional vibration signals are pre-processed by overlapping feature extraction techniques to fully extract fault characteristics.The deep residual network is trained in training tasks with sufficient samples,for fault pattern classification.Subsequently,three transfer strategies are used to explore the generalizability and adaptability of the pre-trained models to the data distribution in target tasks.Among them,the feature transferability between different tasks is explored by model transfer,and it is validated that minimizing data differences of tasks through a dual-stream adaptation structure helps to enhance generalization of the models to the target tasks.In the experiments of rolling bearing faults with unbalanced data conditions,localized faults of motor bearings and planet bearings are successfully identified,and good fault classification results are achieved,which provide guidance for the cross-condition fault diagnosis of rolling bearings with small amounts of training data.
基金Project supported by the National Natural Science Foundation of China(No.61379074)the Zhejiang Provincial Natural Science Foundation of China(Nos.LZ12F02003 and LY15F020035)
文摘In some image classification tasks, similarities among different categories are different and the samples are usually misclassified as highly similar categories. To distinguish highly similar categories, more specific features are required so that the classifier can improve the classification performance. In this paper, we propose a novel two-level hierarchical feature learning framework based on the deep convolutional neural network(CNN), which is simple and effective. First, the deep feature extractors of different levels are trained using the transfer learning method that fine-tunes the pre-trained deep CNN model toward the new target dataset. Second, the general feature extracted from all the categories and the specific feature extracted from highly similar categories are fused into a feature vector. Then the final feature representation is fed into a linear classifier. Finally, experiments using the Caltech-256, Oxford Flower-102, and Tasmania Coral Point Count(CPC) datasets demonstrate that the expression ability of the deep features resulting from two-level hierarchical feature learning is powerful. Our proposed method effectively increases the classification accuracy in comparison with flat multiple classification methods.
