CAJ | 학술논문

支持向量机（support vector machine ，SVM ）具有良好的学习性能和泛化能力，因而被广泛应用于恒星光谱分类中。然而实际应用面临的数据规模往往很大，SVM 便暴露出计算量大、分类速度慢等问题。为了解决上述问题，Jayadeva等提出双支持向量机（twin support vector machine ，TWSVM ），将计算时间减少至SVM的1／4。然后上述方法仅关注数据的全局特征，对每类数据的局部特征并未关注。鉴于此，提出基于流形模糊双支持向量机（manifold fuzzy twin support vector machine ，MF-TSVM）的恒星光谱分类方法。利用流形判别分析获得数据的全局特征和局部特征，模糊隶属度函数的引入将各类数据区别对待，尽可能减少噪声点和奇异点对分类结果的影响。与C-SVM ，KNN等传统分类方法在SDSS恒星光谱数据集上的比较实验表明了该方法的有效性。
지지향량궤（support vector machine ，SVM ）구유량호적학습성능화범화능력，인이피엄범응용우항성광보분류중。연이실제응용면림적수거규모왕왕흔대，SVM 편폭로출계산량대、분류속도만등문제。위료해결상술문제，Jayadeva등제출쌍지지향량궤（twin support vector machine ，TWSVM ），장계산시간감소지SVM적1／4。연후상술방법부관주수거적전국특정，대매류수거적국부특정병미관주。감우차，제출기우류형모호쌍지지향량궤（manifold fuzzy twin support vector machine ，MF-TSVM）적항성광보분류방법。이용류형판별분석획득수거적전국특정화국부특정，모호대속도함수적인입장각류수거구별대대，진가능감소조성점화기이점대분류결과적영향。여C-SVM ，KNN등전통분류방법재SDSS항성광보수거집상적비교실험표명료해방법적유효성。
Support vector machine (SVM ) with good leaning ability and generalization is widely used in the star spectra data clas-sification .But when the scale of data becomes larger ,the shortages of SVM appear :the calculation amount is quite large and the classification speed is too slow .In order to solve the above problems ,twin support vector machine (TWSVM ) was proposed by Jayadeva .The advantage of TSVM is that the time cost is reduced to 1/4 of that of SVM .While all the methods mentioned above only focus on the global characteristics and neglect the local characteristics .In view of this ,an automatic classification method of star spectra data based on manifold fuzzy twin support vector machine (MF-TSVM ) is proposed in this paper .In MF-TSVM ,manifold-based discriminant analysis (MDA) is used to obtain the global and local characteristics of the input data and the fuzzy membership is introduced to reduce the influences of noise and singular data on the classification results .Compara-tive experiments with current classification methods ,such as C-SVM and KNN ,on the SDSS star spectra datasets verify the ef-fectiveness of the proposed method .