Ample Feature Selection Algorithm for Efficient Prediction of Main Causes of Aviation Accident using Tree based Classifiers
S Sasikala1, E A Neeba2, A. Suresh3, Pethuru Raj4, M Hemanth Chakravarthy5

1S.Sasikala, Professor, Department of Computer Science and Engineering, Paavai Engineering College, Namakkal (Tamil Nadu), India.
2E.A Neeba, Assistant Professor, Department of Information Technology,Rajagiri School of Engineering & Technology, Rajagiri Valley, Kakkanad, Kochi (Kerala), India.
3A.Suresh, Professor & Head, Department of Computer Science and Engineering, Nehru Institute of Engineering and Technology, T.M. Palayam, Coimbatore (Tamil Nadu), India.
4Pethuru Raj, Chief Architect and Vice President, Site Reliability Engineering SRE Division Reliance Jio Infocomm. Ltd. RJIL, SARGOD Imperial, Residency Road, Bangalore (Karnataka), India.
5M.Hemanth Chakravarthy, Application Development Team Lead, Accenture Technology, Perungalathur, Chennai (Tamil Nadu), India.
Manuscript received on 07 March 2019 | Revised Manuscript received on 20 March 2019 | Manuscript published on 30 March 2019 | PP: 941-946 | Volume-8 Issue-5, March 2019 | Retrieval Number: E2874038519/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Safety and Happy Journey have always been imperative believe in aviation. Aviation industry has to accumulate huge quantity of experience and data for every year. These data repository includes the data reports including the flight operations, pilot activity report, maintenance report and other supporting reports. Even though these documents are carefully verified for the safest airline journey, it is necessary to provide a precaution checklist with the primary and secondary factor causing the aviation accidents. This paper focus on releasing a Aviation checklist for pre-checking both primary and secondary factors before operating the flight with the help of data mining techniques. The proposed novel feature selection algorithm is compared with traditional feature selection algorithms and its accuracy is evaluated through the Tree based conventional classifiers like J48 (C4.5), Naïve Bayes Tree (NBT), Random Tree (RT), and REP Tree. The research will be justified with real data reports which are collected between the years 1919-2014. This aircraft dataset is provided with 1379 Instances (reports) and 231 attributes (causes). With the classification techniques of data mining, the causes for the aviation accidents are classified as class attribute. The obtained classification accuracy demonstrates that the proposed method could contribute to the successful detection of Aviation Accident Factors and could be applied as pre-check list for the safety journey.
Keyword: Oscillating Search, Feature Selection, Tree Based Classifiers, Correlation Based Feature Selection Aviation Accident Hazards, Improved Oscillated Correlation Based Feature Selection.
Scope of the Article: Regression and Prediction