Identification and Classification of Exoplanets using Light Intensity.

Garude, Aaditya Balkrishna (2022) Identification and Classification of Exoplanets using Light Intensity. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (945kB) | Preview

Abstract

The evolution of the astronomy field has been significantly impacted by science and technological innovation. Scientists have confirmed that there are more than a thousand exoplanets. The light curve, which is tiny and has uneven residual scattering, is defined by the brightness of the stars. The department of National Aeronautics and Space Administration (NASA) performed Kepler Mission and collected valuable insights in the form of data known as light curves which indicates brightness of stars. This data is in the form of Time series.Exoplanets were previously identified utilizing the transit methodology, which calls for human participation to analyze the signals associated to exoplanets. Therefore, automating a particular study is a crucial way for managing with huge Data that are generated by the most recent technology. It also helps to reduce human work. So, utilizing light intensity, we have presented a machine learning approach to finding exoplanets. Certain exploratory data analysis were performed to understand the data.The data then went through three Baseline Machine Learning models which gave undesirable results due to imbalance data. To overcome this imbalance nature of the Data SMOTE techniques was introduced which will help to balance the data and the identical Machine Learning models were applied again as a form of experiment two and desired outputs were achieved. To conclude, the results with and without the implementation of SMOTE technique are compared and it shows significant difference in getting better performance in terms of accuracy, confusion matrix, ROC and Area under the curve with the SMOTE technique.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Exoplanets; Flux intensity; Machine Learning; SMOTE
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QB Astronomy Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	24 Jan 2023 15:39
Last Modified:	03 Mar 2023 12:14
URI:	https://norma.ncirl.ie/id/eprint/6122

Actions (login required)

View Item