Surbhi Agrawal

Machine Learning in Astronomy: A Case Study in Quasar-Star Classification

We present the results of various automated classification methods, based on machine learning (ML), of objects from data releases 6 and 7 (DR6 and DR7) of the Sloan Digital Sky Survey (SDSS), primarily distinguishing stars from quasars. We provide a careful scrutiny of approaches available in the literature and have highlighted the pitfalls in those approaches based on the nature of data used for the study. The aim is to investigate the appropriateness of the application of certain ML methods. The manuscript argues convincingly in favor of the efficacy of asymmetric AdaBoost to classify photometric data. The paper presents a critical review of existing study and puts forward an application of asymmetric AdaBoost, as an offspring of that exercise.

An enhancement to CloudSim via distributed data storage

The advent of cloud computing technology has made its presence effectively felt in various application areas such as business, industry, scientific, administrative, astronomy, high-energy physics, information, education etc. Its capability of meeting the various continuously changing demands in all fields makes it increasingly popular. In order to use cloud computing technology, the user has to make him/her familiar with the various facets of the technology through the simulators, which serve as training assets to familiarize the users with the real time scenario. Among the various cloud simulators available, the widely used CloudSim 3.0.3 is considered for analysis. This version of the simulator proposed in the paper uses hard drive storage, with new features in data storage being included to achieve distributed storage resulting in load balancing across the nodes. The method helps achieve reduction in data migration and mitigate data loss in case nodes crash.