doi: 10.18178/ijfcc.2017.6.1.482
Using Associative Petri Net with Over-Sampling Techniques to Construct an Aviation Incident Prediction Model
Hsiu-Sen Chiang
1
,
Tsung-Che Hsieh
1
,
Chia-Chen Chen
2
,
Neil Y. Yen
3
,
Mu-Yen Chen
1
- 1 National Taichung University of Science and Technology, Taichung, 40444 Taiwan
- 2 National Chung Hsing University, Taichung, 402 Taiwan
- 3 University of Aizu, Aizu-Wakamatsu, Fukushima Pref. 965-8580 Japan
Abstract
Most current research applying data miningtechniques to aviation safety focus on the acquisition andselection of data attribute fields, while the selection and analysisof classification algorithms has been largely overlooked. Thisstudy seeks to address this gap as a means of identifying keyfactors which result in aviation fatalities. The study data istaken from the Accident/Incident Data System (AIDS) flightaccident database, which comprises an imbalanced dataset. TheSynthetic Minority Oversampling Technique (SMOTE) is usedto minimize the impact of data imbalance on classificationresults for categories with small datasets. Feature attributeselection was implemented through information gain (IG). Thisstudy also develops an Associative Petri Net (APN) model forcomparison against five other classification methods: which areNaive Bayes, BayesNet, Support Vector Machine (SVM),Decision Tree (C4.5), and Radial Basis Function Network(RBFN). IG is used to identify 10 important factors: Event City,Event State, Flight Phase, Aircraft Model, Aircraft Series,Operator, Primary Flight Type, Flight Conduct Code, FlightPlan Filed Code, and Nbr of Engines. Results show that ourproposed APN model had the highest overall accuracy rate,F-measure score, G-mean score among all algorithms. APN isbased on the Apriori algorithm to provide a rule-based concept.Thus using the APN algorithm to build the model could producean expert system for flight accident prediction.
Keywords
- Aviation safety
- attribute selection
- imbalanced dataset
- SMOTE
- associative petri net
How to Cite
Hsiu-Sen Chiang, Tsung-Che Hsieh, Chia-Chen Chen, Neil Y. Yen, and Mu-Yen Chen, "Using Associative Petri Net with Over-Sampling Techniques to Construct an Aviation Incident Prediction Model," International Journal of Future Computer and Communication, vol. 6, no. 1, pp. 21-26, 2017. https://doi.org/ 10.18178/ijfcc.2017.6.1.482
Copyright & License
Copyright © 2017 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).