917 International Journal of Scientific Management and Development *Correspondent Author: Camelia Arbabzadeh (camelia.arbabzadeh@gmail.com) Manuscript No: IJSMD-KINA-2014-506 International Journal of Scientific Management and Development ISSN:2345-3974 Vol.3 (2), 917-922 February (2015) Research Paper Applying data mining to extract damage level of bird strike on helicopters Camelia Arbabzadeh *1 , Abbas Toloie Eshlaghy 2 1Department of Information Technology Management, Science and Research Branch, Islamic Azad University, Tehran, Iran. 2Department of Industrial Management, Science and Research Branch, Islamic Azad University, Tehran, Iran. Available online at: www.IJSMD.Com Received 20 th November 2014, Revised 20 th December 2014, Accepted 28 th December 2014 Abstract Underestanding the risk factors of damage will be helpful to mitigate damage of bird strike. Planning for preventing bird strike evidence need to risk factors and relation of these factors to level of damage. Hence, the goal of this paper is extracting the risk factors by consideration of damage level imposed on helicopters. The data source of the current research is the Federal Aviation Administration Wildlife Strike Database which was gathered for about twenty years. In this paper, we used four kind of decision tree algorithms included C5.0, CART, C&R TREE, and QUEST to extract damage level of bird strike (D, S, M, and N that demonstrate of destroyed, substantial, minor, and not defined) on helicopters. The results demonstrated that bird size, helicopters type, phase of flight, speed, and type of engine are the most important risk factors causing damage to helicopters, respectively. Finally the research concludes with some suggestions to reduce damage of bird strike on helicopters. Keywords: Bird Strike; Data mining; Decision tree. Introduction A bird strike, sometimes called birdstrike, bird ingestion (if bird swallowed by engine of aircraft), bird hit, or BASH (for Bird Aircraft Strike Hazard) is a collision between an airborne animal (usually a bird or bat) and a human-made vehicle, especially aircraft (wikipedia). Bird strike has become a major threat to air safety globally. Over the years, collision between birds/wildlife and aircrafts has resulted in the death of hundreds of people (USMAN.2012). The cost of bird strikes estimate of US$ 1.2 billion per year that this cost is with concerned of damage and delays (Allan ET AL.2000). ICAO recommended to register the data of airport bird/wildlife strike and organizing a programme for control and preventing this kind of events.This organization also introduce roles and responsibilities within a bird/Wildlife strike control programme (Airport Services Manual). Hence, quantify important parameters that lead us to assess level of damage that probably will occur in the result of bird strike is necessary. On January 15, 2009, the plane struck with geese, lost engine power and landed in Hudson river after 3 minutes into the flight. These bird strike events have major effect on safety in aviation industry. Many researches try to find effective methods and make suggestions to put an end to these kind of events but applying data mining methods on bird strike is rarely occurred. With the rapid growth in air travel, considering risk and safety is important in aviation (Nazeri.2002). Aviation industry is one of the fields that data mining methods have been applied (Gürbüz et al.2011). Data mining is finding relationships to summarize the data in ways that exploit effective data that is useful to the data owner. The relationships and summaries derived through a data mining exercise are often referred to as models or patterns (Gürbüz et al.2011) (Hand et al.2001). knowledge discovery in databases (KDD) is another popular name of data mining that is automated extraction of patterns and can show knowledge implicitly that existed in massive information repositories likes data warehouses or databases (Gürbüz et al.2011) (Jiawei et al.2001). Literature Survey Both (2010) for a given period of time a risk assessment matrix constructed which is included bird species according to frequency of bird strikes are involved and the percentage of strike resulting in damage. The matrix is appropriate tool for manage and monitoring the bird strike hazards (Both et al.2003). Allan (2006) introduces the well-known probability-severity risk assessment matrix for bird strike risk assessment that the bird strikes per bird species over a given 5 year period is considered a measure of strike probability for a given airport. Damage is a measure of likely severity that is the proportion of strikes with each 4Pspecies (Allan et al.2006). This risk assessment matrix is used as auditing tool for the bird strike prevention activities of airfields (Searing.2005). It is a simple tool which shows for which bird species further action is needed. The risk assessment matrix always need to support with a reporting system that furnish reliable information about occurred bird strikes (Both et al.2003) (Linnel,1999). Risk is defined as the product of the severity and probability of wildlife strikes during a predefined period (Allan.2001). Wildlife risk in and around airport is a concerning subject in airports, need to find a threat to measure risk of bird strike in airports. To provide a way posed by each wildlife species, wildlife hazard management experts have suggested to utilize of wildlife risk hazard assessments. In considering that risk is defined as the result of the severity and probability of wildlife strikes during a period of time (Allan.2001). Dolbeer et al (2000) described that birds with bigger size had more probability to provide damages more severely than others in bird strike accidents. Measure of the severity is using the size of birds and the probability is the frequency of bird strike occurrence (Dolbeer at al.2000). Tan et al (2010) for measuring an aerodrome’s wildlife safety performance show a basic framework on the practical application of wildlife risk hazard assessments. The case study is Changi Airport and in this research try to help airports in better