Stellar Spectral Classification with Minimum Within-Class and Maximum Between-Class Scatter Support Vector Machine

Support Vector Machine (SVM) is one of the important stellar spectral classification methods, and it is widely used in practice. But its classification efficiencies cannot be greatly improved because it does not take the class distribution into consideration. In view of this, a modified SVM named Minimum within-class and Maximum between-class scatter Support Vector Machine (MMSVM) is constructed to deal with the above problem. MMSVM merges the advantages of Fisher’s Discriminant Analysis (FDA) and SVM, and the comparative experiments on the Sloan Digital Sky Survey (SDSS) show that MMSVM performs better than SVM.     

Stellar Spectral Classification with Locality Preserving Projections and Support Vector Machine

With the help of computer tools and algorithms, automatic stellar spectral classification has become an area of current interest. The process of stellar spectral classification mainly includes two steps: dimension reduction and classification. As a popular dimensionality reduction technique, Principal Component Analysis (PCA) is widely used in stellar spectra classification. Another dimensionality reduction technique, Locality Preserving Projections (LPP) has not been widely used in astronomy. The advantage of LPP is that it can preserve the local structure of the data after dimensionality reduction. In view of this, we investigate how to apply LPP+SVM in classifying the stellar spectral subclasses. In the comparative experiment, the performance of LPP is compared with PCA. The stellar spectral classification process is composed of the following steps. Firstly, PCA and LPP are respectively applied to reduce the dimension of spectra data. Then, Support Vector Machine (SVM) is used to classify the 4 subclasses of K-type and 3 subclasses of F-type spectra from Sloan Digital Sky Survey (SDSS). Lastly, the performance of LPP+SVM is compared with that of PCA+SVM in stellar spectral classification, and we found that LPP does better than PCA.     

Classification of stellar spectra with SVM based on within-class scatter and between-class scatter

Support Vector Machine (SVM) is a popular data mining technique, and it has been widely applied in astronomical tasks, especially in stellar spectra classification. Since SVM doesn’t take the data distribution into consideration, and therefore, its classification efficiencies can’t be greatly improved. Meanwhile, SVM ignores the internal information of the training dataset, such as the within-class structure and between-class structure. In view of this, we propose a new classification algorithm-SVM based on Within-Class Scatter and Between-Class Scatter (WBS-SVM) in this paper. WBS-SVM tries to find an optimal hyperplane to separate two classes. The difference is that it incorporates minimum within-class scatter and maximum between-class scatter in Linear Discriminant Analysis (LDA) into SVM. These two scatters represent the distributions of the training dataset, and the optimization of WBS-SVM ensures the samples in the same class are as close as possible and the samples in different classes are as far as possible. Experiments on the K-, F-, G-type stellar spectra from Sloan Digital Sky Survey (SDSS), Data Release 8 show that our proposed WBS-SVM can greatly improve the classification accuracies.     

基于NPSVM模型的超新星识别方法

巡天观测与高能物理、黑洞天文等领域均有密切的联系.基于星系-超新星二分类问题,研究光谱数据预处理,结合余弦相似度改善PCA(Principal Component Analysis)光谱分解特征提取方法,用SDSS(the Sloan Digital Sky Survey)、WISeREP(the Weizmann Interactive Supernova data REPository)组成的5620条光谱数据集训练支持向量机,可以得到0.498%泛化误差的识别模型和新样本分类概率.使用Neyman-Pearson决策方法建立NPSVM(Neyman-Pearson Support Vector Machine)模型可进一步降低超新星的漏判率.     

Research on Star/Galaxy Classification Based on Stacking Ensemble Learning

Machine learning has achieved great success in many areas today, but the forecast effect of machine learning often depends on the specific problem. An ensemble learning forecasts results by combining multiple base classifiers. Therefore, its ability to adapt to various scenarios is strong, and the classification accuracy is high. In response to the low classification accuracy of the darkest source magnitude set of stars/galaxies in the Sloan Digital Sky Survey (SDSS), a star/galaxy classification algorithm based on the stacking ensemble learning is proposed in this paper. The complete photometric data set is obtained from the SDSS Data Release (DR) 7, and divided into the bright source magnitude set, dark source magnitude set, and darkest source magnitude set according to the stellar magnitude. Firstly, the 10-fold nested cross-validation method is used for the darkest source magnitude set, then the Support Vector Machine (SVM), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost) algorithms are used to establish the base-classifier model; the Gradient Boosting Decision Tree (GBDT) is used as the meta-classifier model. Finally, based on the classification accuracy of galaxies and other indicators, the classification results are analyzed and compared with the results obtained by the Function Tree (FT), SVM, RF, GBDT, Stacked Denoising Autoencoders (SDAE), Deep Belief Nets (DBN), and Deep Perception Decision Tree (DPDT) models. The experimental results show that the stacking ensemble learning model has improved the classification accuracy of galaxies in the darkest source magnitude set by nearly 10% compared to the function tree algorithm. Compared with other traditional machine learning algorithm, stronger lifting algorithm, and deep learning algorithm, the stacking ensemble learning model also has different degrees of improvement.     

Classification of Stellar Spectra with Fuzzy Minimum Within-Class Support Vector Machine

Classification is one of the important tasks in astronomy, especially in spectra analysis. Support Vector Machine (SVM) is a typical classification method, which is widely used in spectra classification. Although it performs well in practice, its classification accuracies can not be greatly improved because of two limitations. One is it does not take the distribution of the classes into consideration. The other is it is sensitive to noise. In order to solve the above problems, inspired by the maximization of the Fisher’s Discriminant Analysis (FDA) and the SVM separability constraints, fuzzy minimum within-class support vector machine (FMWSVM) is proposed in this paper. In FMWSVM, the distribution of the classes is reflected by the within-class scatter in FDA and the fuzzy membership function is introduced to decrease the influence of the noise. The comparative experiments with SVM on the SDSS datasets verify the effectiveness of the proposed classifier FMWSVM.     

基于Stacking集成学习的恒星/星系分类研究

机器学习在当今诸多领域已经取得了巨大的成功,但是机器学习的预测效果往往依赖于具体问题.集成学习通过综合多个基分类器来预测结果,因此,其适应各种场景的能力较强,分类准确率较高.基于斯隆数字巡天(Sloan Digital Sky Survey,SDSS)计划恒星/星系中最暗源星等集分类正确率低的问题,提出一种基于Stacking集成学习的恒星/星系分类算法.从SDSS-DR7(SDSS Data Release 7)中获取完整的测光数据集,并根据星等值划分为亮源星等集、暗源星等集和最暗源星等集.仅针对分类较为复杂且困难的最暗源星等集展开分类研究.首先,对最暗源星等集使用10折嵌套交叉验证,然后使用支持向量机(Support Vector Machine,SVM)、随机森林(Random Forest,RF)、XGBoost(eXtreme Gradient Boosting)等算法建立基分类器模型;使用梯度提升树(Gradient Boosting Decision Tree,GBDT)作为元分类器模型.最后,使用基于星系的分类正确率等指标,与功能树(Function Tree,FT)、SVM、RF、GBDT、XGBoost、堆叠降噪自编码(Stacked Denoising AutoEncoders,SDAE)、深度置信网络(Deep Belief Network,DBN)、深度感知决策树(Deep Perception Decision Tree,DPDT)等模型进行分类结果对比分析.实验结果表明,Stacking集成学习模型在最暗源星等集分类中要比FT算法的星系分类正确率提高了将近10%.同其他传统的机器学习算法、较强的提升算法、深度学习算法相比,Stacking集成学习模型也有较大的提升.     

Spectral classification of stars based on LAMOST spectra

In this work, we select spectra of stars with high signal-to-noise ratio from LAMOST data and map their MK classes to the spectral features. The equivalent widths of prominent spectral lines, which play a similar role as multi-color photometry, form a clean stellar locus well ordered by MK classes. The advantage of the stellar locus in line indices is that it gives a natural and continuous classification of stars consistent with either broadly used MK classes or stellar astrophysical parameters. We also employ an SVM-based classification algorithm to assign MK classes to LAMOST stellar spectra. We find that the completenesses of the classifications are up to 90% for A and G type stars, but they are down to about 50% for OB and K type stars. About 40% of the OB and K type stars are mis-classified as A and G type stars,respectively. This is likely due to the difference in the spectral features between late B type and early A type stars or between late G and early K type stars being very weak. The relatively poor performance of the automatic MK classification with SVM suggests that the direct use of line indices to classify stars is likely a more preferable choice.     

Contour detection in Cassini ISS images based on Hierarchical Extreme Learning Machine and Dense Conditional Random Field

In Cassini ISS(Imaging Science Subsystem) images, contour detection is often performed on disk-resolved objects to accurately locate their center. Thus, contour detection is a key problem. Traditional edge detection methods, such as Canny and Roberts, often extract the contour with too much interior details and noise. Although the deep convolutional neural network has been applied successfully in many image tasks, such as classification and object detection, it needs more time and computer resources. In this paper,a contour detection algorithm based on H-ELM(Hierarchical Extreme Learning Machine) and Dense CRF(Dense Conditional Random Field) is proposed for Cassini ISS images. The experimental results show that this algorithm's performance is better than both traditional machine learning methods, such as Support Vector Machine, Extreme Learning Machine and even deep Convolutional Neural Network. The extracted contour is closer to the actual contour. Moreover, it can be trained and tested quickly on the general configuration of PC, and thus can be applied to contour detection for Cassini ISS images.     

Automatic Detection and Classification of Coronal Mass Ejections

We present an automatic algorithm to detect, characterize, and classify coronal mass ejections (CMEs) in Large Angle Spectrometric Coronagraph (LASCO) C2 and C3 images. The algorithm includes three steps: (1) production running difference images of LASCO C2 and C3; (2) characterization of properties of CMEs such as intensity, height, angular width of span, and speed, and (3) classification of strong, median, and weak CMEs on the basis of CME characterization. In this work, image enhancement, segmentation, and morphological methods are used to detect and characterize CME regions. In addition, Support Vector Machine (SVM) classifiers are incorporated with the CME properties to distinguish strong CMEs from other weak CMEs. The real-time CME detection and classification results are recorded in a database to be available to the public. Comparing the two available CME catalogs, SOHO/LASCO and CACTus CME catalogs, we have achieved accurate and fast detection of strong CMEs and most of weak CMEs.     

On the use of logistic regression for stellar classification

We are totally immersed in the Big Data era and reliable algorithms and methods for data classification are instrumental for astronomical research. Random Forest and Support Vector Machines algorithms have become popular over the last few years and they are widely used for different stellar classification problems. In this article, we explore an alternative supervised classification method scarcely exploited in astronomy, Logistic Regression, that has been applied successfully in other scientific areas, particularly biostatistics. We have applied this method in order to derive membership probabilities for potential T Tauri star candidates from ultraviolet-infrared colour-colour diagrams.     

基于胶囊网络的恒星光谱分类研究

大型巡天项目的快速发展,产生大量的恒星光谱数据,也使得实现恒星光谱数据的自动分类成为一项具有挑战性的工作.提出一种新的基于胶囊网络的恒星光谱分类方法,首先利用1维卷积网络和短时傅里叶变换将来源于LAMOST(Large Sky Area Multi-Object Fiber Spectroscopy Telescope)Data Release 5(DR5)的F5、G5、K5型1维恒星光谱转化成2维傅里叶谱图像,再通过胶囊网络对2维谱图像进行自动分类.由于胶囊网络具有保留图像中实体之间的分层位姿关系和无需池化层的优点,实验结果表明:胶囊网络具有较好的分类性能,对于F5、G5、K5型恒星光谱的分类,准确率优于其他分类方法.     

Automatic Short-Term Solar Flare Prediction Using Machine Learning and Sunspot Associations

In this paper, a machine-learning-based system that could provide automated short-term solar flare prediction is presented. This system accepts two sets of inputs: McIntosh classification of sunspot groups and solar cycle data. In order to establish a correlation between solar flares and sunspot groups, the system explores the publicly available solar catalogues from the National Geophysical Data Center to associate sunspots with their corresponding flares based on their timing and NOAA numbers. The McIntosh classification for every relevant sunspot is extracted and converted to a numerical format that is suitable for machine learning algorithms. Using this system we aim to predict whether a certain sunspot class at a certain time is likely to produce a significant flare within six hours time and if so whether this flare is going to be an X or M flare. Machine learning algorithms such as Cascade-Correlation Neural Networks (CCNNs), Support Vector Machines (SVMs) and Radial Basis Function Networks (RBFN) are optimised and then compared to determine the learning algorithm that would provide the best prediction performance. It is concluded that SVMs provide the best performance for predicting whether a McIntosh classified sunspot group is going to flare or not but CCNNs are more capable of predicting the class of the flare to erupt. A hybrid system that combines a SVM and a CCNN is suggested for future use.     

Stellar Spectral Classification Based on Capsule Network

The rapid development of large-scale sky survey project has produced a large amount of stellar spectral data, which make the automatic classification of stellar spectral data a challenging task. In this paper, we have proposed a stellar spectral classification method based on a capsule network. At first, by using the one-dimensional convolutional network and short-time Fourier transform (STFT), the one-dimensional spectra of the F5, G5, and K5 types selected from the LAMOST Data Release 5 (DR5) are converted into the two-dimensional Fourier spectrum images. Then, the two-dimensional Fourier spectrum images are classified automatically by the capsule network. Because the capsule network can preserve the hierarchical pose relationships among the entities in the image, and it does not need any pooling layers, the experimental results show that the capsule network has a better classification performance, for the classifications of the F5, G5, and K5-type stellar spectra, its classification accuracy is superior to other classification methods.     

Automatic Detection of Limb Prominences in 304 Å EUV Images

A new algorithm for automatic detection of prominences on the solar limb in 304 Å EUV images is presented, and results of its application to SOHO/EIT data discussed. The detection is based on the method of moments combined with a classifier analysis aimed at discriminating between limb prominences, active regions, and the quiet corona. This classifier analysis is based on a Support Vector Machine (SVM). Using a set of 12 moments of the radial intensity profiles, the algorithm performs well in discriminating between the above three categories of limb structures, with a misclassification rate of 7%. Pixels detected as belonging to a prominence are then used as the starting point to reconstruct the whole prominence by morphological image-processing techniques. It is planned that a catalogue of limb prominences identified in SOHO and STEREO data using this method will be made publicly available to the scientific community.     

Generation and performance of automated jarosite mineral detectors for visible/near-infrared spectrometers at Mars

We have developed two automated detectors that can recognize the sulfate mineral jarosite in unknown visible to near-infrared spectra (350-2500 nm). The two detectors are optimized for use within the terrestrial and martian atmospheres. The detectors are built from Support Vector Machines trained using a generative model to create linear mixtures of library mineral spectra. Both detectors performed with an average ∼90% accuracy on laboratory spectra of single minerals and the laboratory and field spectra of rocks collected in a hydrothermal environment. This type of algorithm will contribute to the efficiency of onboard data analysis of landed and orbital visible/near-infrared spectrometers at Mars.     

基于深度学习的LAMOST星系星族参数测量

星系的光谱包含其内部恒星的年龄和金属丰度等信息, 从观测光谱数据中测量这些信息对于深入了解星系的形成和演化至关重要. LAMOST (Large Sky Area Multi-Object Fiber Spectroscopic Telescope)巡天发布了大量的星系光谱, 这些高维光谱与它们的物理参数之间存在着高度的非线性关系. 而深度学习适合于处理多维、海量的非线性数据, 因此基于深度学习技术构建了一个8个卷积层$+$4个池化层$+$1个全连接层的卷积神经网络, 对LAMOST Data Release 7 (DR7)星系的年龄和金属丰度进行自动估计. 实验结果表明, 使用卷积神经网络通过星系光谱预测的星族参数与传统方法基本一致, 误差在0.18dex以内, 并且随着光谱信噪比的增大, 预测误差越来越小. 实验还对比了卷积神经网络与随机森林回归模型、深度神经网络的参数测量结果, 结果表明卷积神经网络的结果优于其他两种回归模型.     

A multi-layered backpropagation artificial neural network algorithm for UV spectral classification

In this paper we present an application of an artificial neural network model based on a multi-layered backpropagation algorithm for spectral classification of UV data from the International Ultraviolet Explorer (IUE) low dispersion spectra reference atlas. The model used is similar to that of von Hippel et al. (1994), and is found to reduce the classification error as compared to the recently reported results on the same data set (Gulati et al. 1994b). The improved version of the network is much simpler in structure and the training time is reduced by a factor of almost 20. Such networks will prove very useful in efficient classification of large databases Subject headings: neural networks, stellar spectra, classification     

MK标准星的CCD光谱及光谱分类判据向黄红区的扩展

本文提供了１２５颗ＭＫ标准星的ＣＣＤ光谱,光谱型从Ｏ到Ｍ,光度级从Ｖ到Ⅰ,构成较完整的二元分类框架,光谱覆盖范围由传统蓝紫区延伸到黄红区．初步考察和归纳了黄红区适于恒星分类的主要光谱特征和判据．这些结果对于采用相似分辨率的恒星光谱分类工作是非常有用的．     

基于卷积神经网络的恒星光谱型和光度型的分类模型

恒星光谱分类是天文学中一个重要的研究问题.对于已经采集到的海量高维恒星光谱数据的分类,采用模式匹配方法对光谱型分类较为成功,但其缺点在于标准恒星模版之间的差异性在匹配实际观测数据中不能体现出来,尤其是当需要进行光谱型和光度型的二元分类时模版匹配法往往会失败.而采用谱线特征测量的光度型分类强烈地依赖谱线拟合的准确性.为了解决二元分类的问题,介绍了一种基于卷积神经网络的恒星光谱型和光度型分类模型(Classification model of Stellar Spectral type and Luminosity type based on Convolution Neural Network, CSSL CNN).这一模型使用卷积神经网络来提取光谱的特征,通过注意力模块学习到了重要的光谱特征,借助池化操作降低了光谱的维度并压缩了模型参数的数量,使用全连接层来学习特征并对恒星光谱进行分类.实验中使用了大天区面积多目标光纤光谱天文望远镜(Large Sky Area Multi-Object Fiber Spectroscopy Telescope, LAMOST)公开数据集Data Release 5 (DR5,用了其中71282条恒星光谱数据,每条光谱包含了3000多维的特征)对该模型的性能进行验证与评估.实验结果表明,基于卷积神经网络的模型在恒星的光谱型分类上准确率达到92.04%,而基于深度神经网络的模型(Celestial bodies Spectral Classification Model, CSC Model)只有87.54%的准确率; CSSL CNN在恒星的光谱型和光度型二元分类上准确率达到83.91%,而模式匹配方法MKCLASS仅有38.38%的准确率且效率较低.