Abstract:
Airplanes are considered as the fastest and most preferred mode of travel all around the world. However, air travel always comes with the risk of accidents and plane cras...Show MoreMetadata
Abstract:
Airplanes are considered as the fastest and most preferred mode of travel all around the world. However, air travel always comes with the risk of accidents and plane crashes. The severity of these hazards spans over a range from moderate to even fatal depending on a number of parameters. This paper proposes a methodology to predict airplane crash severity using several machine learning algorithms. Out of the many factors that have an impact on the crash, nine of them having a major correlation are taken into consideration. The prediction categories are made based on the number of fatalities and the amount of damage caused to the aircraft. Algorithms such as Support Vector Machine, Random Forest, Gradient Boosting Classifier, K Nearest Neighbors Classifier, Logistic Regression and an Artificial Neural Network are applied along with ensemble techniques and the results are compared to provide a realistic and reliable prediction.
Published in: 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT)
Date of Conference: 06-08 July 2021
Date Added to IEEE Xplore: 03 November 2021
ISBN Information: