Airline Crash Prediction Using Machine Learning
Abstracting useful information from a big data has always been a challenging task. Data mining is a powerful technology with great potential to extract knowledge based information from such data. Prediction can be done with past and related records in different fields. Risk and safety have always been an important consideration in the field of aircraft. Prediction of accident in aircraft will save life and cost. This paper proposes an accident prediction system with huge collection of past records by applying effective predictive data mining techniques like Decision Tree (DT) and Naive Bayes which have a greater capacity to handle huge and noisy data that are used to predict accidents with more accuracy. The methods used, prove to handle noisy, unrelated and missing data. The prediction results are tabulated and ranges between 80% to 90%.
This work focus on using data mining techniques in the process of accident prediction with aircraft accident details as training data set. Data from National Transportation Safety Board (NTSB), which records all the aircraft accidents, is used as training dataset for the proposed system. Various attributes which caused the accidents are analyzed. Collectively a set of ten attributes with one year of accident records are used as the training set.Huge Collection of past accident records of all types are available in different formats and found to be erroneous. Fields and records which support the aircraft accident prediction are filtered.
On the normalized data, Naive Bayes is applied to predict the future possibility of accident occurrence.Naive Bayes implements mapping of inputs into a high dimensional space using a set of nonlinear basis functions.For cross validation or to measure the accuracy level of Naive Bayes, further techniques are implemented to predict accidents. DT which can handle nonlinear data in a more effective way is implemented and tested.