Predicting Airline Crash due to Birds Strike Using Machine Learning

Abstract

The objective of this proposed work is to predict whether the airline crash has occurred due to a bird strike or not by using data mining techniques. Risk and safety are not always guaranteed within the field of aircraft. Bird strikes are dangerous for aircraft due to the relative speed of the plane with reference to the bird. The characteristics of aircraft damage from bird strikes, which is critical enough to make a high risk to continue a safe flight, differs in step with the dimensions of aircraft. Data from the National Transportation Safety Board (NTSB), which records all the aircraft accidents, are used as a training data set for the proposed system. Machine learning is the most effective technology to harnessing the useful information and knowledge from big data. The proposed work intended at building a prediction model using machine learning techniques such as decision trees and Bayesian classifications, which can be very useful in the aviation safety system and is utilized to conjecture the air crafts mishaps ahead of time so that there is an extension to the reduction in aircraft crash rate. The prediction results are range between 80% to 90%. The proposed aircraft crash prediction model is also assessed by using synthetic data sets.