Pulsar Search using Supervised Machine Learning: An Application of Astronomy
Identification of pulsars in radio astronomy is a tough task because the radio telescopes detecting most of the radiations are noise. Selecting proper radiations emitted by pulsars is a cognitively demanding process. In this paper, the Support Vector Machine-based classifier is implemented to identify pulsar stars from noise by classifying pulsar candidates from non-pulsar candidates. The support vector machine concept is explained with the classification of data. The algorithm is implemented using four statistics values of the two input features. The statistics are mean, standard deviation, excess kurtosis, and skewness. The input features are integrated profile and DM-SNR curve. The two class Support Vector Machine algorithm is trained using 17,897 observations. Average predicting accuracy obtained is 97.54%.