Tools
Tools
Kazi, Naumaan Mohammed Saeed (2020) Using Machine Learning Models to Study Human Error Related Factors in Aviation Accidents and Incidents. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration manual)
Download (2MB) | Preview |
Abstract
The importance of Human Factor (HF) is long been recognized in aviation industry, in order to deeply understand and prevent the errors caused by humans was the foremost challenge for the safety board of aviation. The focus of this study is to identify the characteristic of human error causing aviation accidents and incidents, with the presence of these attributes in a large sample of aviation crashes. Archaeological data was collected from 1971 to 2018, which is of 47 years as it was used to identify the presence of HF was thoroughly analyzed in correlation to attributes indicating pilot features, crash conditions, and aircraft features. Models Gaussian Naïve Bayes, Random Forest, Logistic Regression, XGBoost classifier, SVM and Artificial Neural Network (ANN) modeling was performed to evaluate the associations of individual attributes with the probability of HF given a crash. Through this study we found accuracy to give the accurate evaluation for every classifier. In comparison between top three models, SVM with cross validation managed to give highest accuracy of 96%. The result of 93.19% in ANN model was improved using Hyper-Parameter tuning which gave an accuracy of 93.29%. During the evaluation of this study we would demonstrate to yield meaningful information using machine learning models.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software T Technology > TL Motor vehicles. Aeronautics. Astronautics |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Dan English |
| Date Deposited: | 11 Jun 2020 11:15 |
| Last Modified: | 11 Jun 2020 11:15 |
| URI: | https://norma.ncirl.ie/id/eprint/4273 |
Actions (login required)
 |
View Item |