Galaxy morphology classifications based on machine learning are a typical technique to handle enormous amounts of astronomical observation data,but the key challenge is how to provide enough training data for the mach...Galaxy morphology classifications based on machine learning are a typical technique to handle enormous amounts of astronomical observation data,but the key challenge is how to provide enough training data for the machine learning models.Therefore this article proposes an image data augmentation method that combines few-shot learning and generative adversarial networks.The Galaxy10 DECaLs data set is selected for the experiments with consistency,variance,and augmentation effects being evaluated.Three popular networks,including AlexNet,VGG,and ResNet,are used as examples to study the effectiveness of different augmentation methods on galaxy morphology classifications.Experiment results show that the proposed method can generate galaxy images and can be used for expanding the classification model’s training set.According to comparative studies,the best enhancement effect on model performance is obtained by generating a data set that is 0.5–1 time larger than the original data set.Meanwhile,different augmentation strategies have considerably varied effects on different types of galaxies.FSL-GAN achieved the best classification performance on the ResNet network for In-between Round Smooth Galaxies and Unbarred Loose Spiral Galaxies,with F1 Scores of 89.54%and 63.18%,respectively.Experimental comparison reveals that various data augmentation techniques have varied effects on different categories of galaxy morphology and machine learning models.Finally,the best augmentation strategies for each galaxy category are suggested.展开更多
Machine learning has become a crucial technique for classifying the morphology of galaxies as a result of the meteoric development of galactic data.Unfortunately,traditional supervised learning has significant learnin...Machine learning has become a crucial technique for classifying the morphology of galaxies as a result of the meteoric development of galactic data.Unfortunately,traditional supervised learning has significant learning costs since it needs a lot of labeled data to be effective.FixMatch,a semi-supervised learning algorithm that serves as a good method,is now a key tool for using large amounts of unlabeled data.Nevertheless,the performance degrades significantly when dealing with large,imbalanced data sets since FixMatch relies on a fixed threshold to filter pseudo-labels.Therefore,this study proposes a dynamic threshold alignment algorithm based on the FixMatch model.First,the class with the highest amount has its reliable pseudo-label ratio determined,and the remaining classes'reliable pseudo-label ratios are approximated in accordance.Second,based on the predicted reliable pseudo-label ratio for each category,it dynamically calculates the threshold for choosing pseudo-labels.By employing this dynamic threshold,the accuracy bias of each category is decreased and the learning of classes with less samples is improved.Experimental results show that in galaxy morphology classification tasks,compared with supervised learning,the proposed algorithm significantly improves performance.When the amount of labeled data is 100,the accuracy and F1-score are improved by 12.8%and 12.6%,respectively.Compared with popular semisupervised algorithms such as FixMatch and MixMatch,the proposed algorithm has better classification performance,greatly reducing the accuracy bias of each category.When the amount of labeled data is 1000,the accuracy of cigar-shaped smooth galaxies with the smallest sample is improved by 37.94%compared to FixMatch.展开更多
With the construction of large telescopes and the explosive growth of observed galaxy data,we are facing the problem to improve the data processing efficiency while ensuring the accuracy of galaxy morphology classific...With the construction of large telescopes and the explosive growth of observed galaxy data,we are facing the problem to improve the data processing efficiency while ensuring the accuracy of galaxy morphology classification.Therefore,this work designed a lightweight deep learning framework,Efficient Net-G3,for galaxy morphology classification.The proposed framework is based on Efficient Net which integrates the Efficient Neural Architecture Search algorithm.Its performance is assessed with the data set from the Galaxy Zoo Challenge Project on Kaggle.Compared with several typical neural networks and deep learning frameworks in galaxy morphology classification,the proposed Efficient Net-G3 model improved the classification accuracy from 95.8% to 96.63% with F1-Score values of 97.1%.Typically,this model uses the least number of parameters,which is about one tenth that of DenseNet161 and one fifth that of ResNet-26,but its accuracy is about one percent higher than them.The proposed Efficient Net-G3 can act as an important reference for fast morphological classification for massive galaxy data in terms of efficiency and accuracy.展开更多
基金supported by China Manned Space Program through its Space Application System,the National Natural Science Foundation of China(NSFC,grant Nos.11973022 and U1811464)the Natural Science Foundation of Guangdong Province(No.2020A1515010710)。
文摘Galaxy morphology classifications based on machine learning are a typical technique to handle enormous amounts of astronomical observation data,but the key challenge is how to provide enough training data for the machine learning models.Therefore this article proposes an image data augmentation method that combines few-shot learning and generative adversarial networks.The Galaxy10 DECaLs data set is selected for the experiments with consistency,variance,and augmentation effects being evaluated.Three popular networks,including AlexNet,VGG,and ResNet,are used as examples to study the effectiveness of different augmentation methods on galaxy morphology classifications.Experiment results show that the proposed method can generate galaxy images and can be used for expanding the classification model’s training set.According to comparative studies,the best enhancement effect on model performance is obtained by generating a data set that is 0.5–1 time larger than the original data set.Meanwhile,different augmentation strategies have considerably varied effects on different types of galaxies.FSL-GAN achieved the best classification performance on the ResNet network for In-between Round Smooth Galaxies and Unbarred Loose Spiral Galaxies,with F1 Scores of 89.54%and 63.18%,respectively.Experimental comparison reveals that various data augmentation techniques have varied effects on different categories of galaxy morphology and machine learning models.Finally,the best augmentation strategies for each galaxy category are suggested.
基金supported by China Manned Space Program through its Space Application Systemthe National Natural Science Foundation of China(NSFC,grant Nos.11973022 and U1811464)the Natural Science Foundation of Guangdong Province(No.2020A1515010710)。
文摘Machine learning has become a crucial technique for classifying the morphology of galaxies as a result of the meteoric development of galactic data.Unfortunately,traditional supervised learning has significant learning costs since it needs a lot of labeled data to be effective.FixMatch,a semi-supervised learning algorithm that serves as a good method,is now a key tool for using large amounts of unlabeled data.Nevertheless,the performance degrades significantly when dealing with large,imbalanced data sets since FixMatch relies on a fixed threshold to filter pseudo-labels.Therefore,this study proposes a dynamic threshold alignment algorithm based on the FixMatch model.First,the class with the highest amount has its reliable pseudo-label ratio determined,and the remaining classes'reliable pseudo-label ratios are approximated in accordance.Second,based on the predicted reliable pseudo-label ratio for each category,it dynamically calculates the threshold for choosing pseudo-labels.By employing this dynamic threshold,the accuracy bias of each category is decreased and the learning of classes with less samples is improved.Experimental results show that in galaxy morphology classification tasks,compared with supervised learning,the proposed algorithm significantly improves performance.When the amount of labeled data is 100,the accuracy and F1-score are improved by 12.8%and 12.6%,respectively.Compared with popular semisupervised algorithms such as FixMatch and MixMatch,the proposed algorithm has better classification performance,greatly reducing the accuracy bias of each category.When the amount of labeled data is 1000,the accuracy of cigar-shaped smooth galaxies with the smallest sample is improved by 37.94%compared to FixMatch.
基金supported by the National Natural Science Foundation of China(NSFC,Grant Nos.11973022 and U1811464)the Natural Science Foundation of Guangdong Province(No.2020A1515010710)。
文摘With the construction of large telescopes and the explosive growth of observed galaxy data,we are facing the problem to improve the data processing efficiency while ensuring the accuracy of galaxy morphology classification.Therefore,this work designed a lightweight deep learning framework,Efficient Net-G3,for galaxy morphology classification.The proposed framework is based on Efficient Net which integrates the Efficient Neural Architecture Search algorithm.Its performance is assessed with the data set from the Galaxy Zoo Challenge Project on Kaggle.Compared with several typical neural networks and deep learning frameworks in galaxy morphology classification,the proposed Efficient Net-G3 model improved the classification accuracy from 95.8% to 96.63% with F1-Score values of 97.1%.Typically,this model uses the least number of parameters,which is about one tenth that of DenseNet161 and one fifth that of ResNet-26,but its accuracy is about one percent higher than them.The proposed Efficient Net-G3 can act as an important reference for fast morphological classification for massive galaxy data in terms of efficiency and accuracy.
