PREDICTING A PULSAR STAR - A Classic Class Imbalance Problem
In this project, I have implemented traditional Machine Learning Classifiers (Logistic Regression, Decision Trees, Support Vector Machines and Random Forest) as well as Deep Learning models (Artificial Neural Network and Convolutional Neural Network) to classify Pulsar Stars. Pulsars are a rare type of Neutron star that produce radio emission detectable here on Earth. They are of considerable scientific interest as probes of space-time, the inter-stellar medium, and states of matter . The dataset is available at https://archive.ics.uci.edu/ml/datasets/HTRU2. Here the legitimate pulsar examples are a minority positive class with only 1639 real pulsar examples out of 17898 examples. The goal of this project is to evaluate the performance of the models mentioned above to see which model does the best job in classifying the real pulsars. The traditional ML classifiers performed significantly better in classifying the real pulsars. Among the traditional ML classifiers, Random Forest had the best performance.