1 Clustering NTSB Accidents Data Lishuai Li, Rafael Palacios, R. John Hansman JUP Quarterly Meeting Jan. 2010.

Slides:



Advertisements
Similar presentations
AVIATION SAFETY QUALITY ASSURANCE PROGRAMME
Advertisements

1 Northeast Corridor Cost Benefit Assessment Status Mark Kipperman SAIC July 14, 2003.
Evaluating Controller Complexity Metrics: Preliminary Steps Towards an Abstraction Based Analysis Jonathan HistonProfessor R.J. Hansman JUP Quarterly Review.
Weather and General Aviation Accidents: A Statistical Perspective Jody James National Weather Service, Lubbock, TX Warning Coordination Meteorologist FAA.
Weather Technology In the Cockpit (WTIC) Research and Initial Findings FAA Center of Excellence for General Aviation (PEGASAS) Dr. Seth Young PEGASAS Site.
LifeFlow Case Study: Comparing Traffic Agencies' Performance from Traffic Incident Logs This case study was conducted by John Alexis Guerra Gómez and Krist.
Weather related Aviation Crashes & Deaths in 2004 by Type of Operation Crashes Deaths Crashes Deaths Scheduled Airlines 1 13Scheduled Airlines 1 13 Air.
Boeing Field 1.
Clustering Evaluation April 29, Today Cluster Evaluation – Internal We don’t know anything about the desired labels – External We have some information.
Airport Approach Simulation
Boeing Field. Downbursts can be Divided into Two Main Types MACROBURST: A large downburst with its outburst winds extending greater than 2.5 miles horizontal.
What is Cluster Analysis?
Risk Assessment using Flight Data Analysis
Air Safety and Terrorism Thomas Songer Mita Lovalekar.
Multivariate Analysis Techniques
1 Pilot Knowledge Survey By Bob Jackson, MIC, ZSE CWSU And Accident Study Weather ??
Data Driven Safety. X-15 Simulator X-15 Simulator Use Time honored criteria to predict aircraft behavior failed to uncover serious threats Pilot.
Gerard van Es 58th annual Business Aviation Safety Seminar
Safety By Design Flight Certification AE 6362 Airbus Derivative Team Project Dr. Daniel P. Schrage Course Instructor.
EATS Prague Engine Failure Training Pl. 1 Engine Failure Training Francis Fagegaltier Engine Failure Training Francis Fagegaltier.
Unsupervised Learning. CS583, Bing Liu, UIC 2 Supervised learning vs. unsupervised learning Supervised learning: discover patterns in the data that relate.
Office of Aviation Safety Emergency Medical Services (EMS) Aviation Operations Jeff Guzzetti Deputy Director for Regional Operations.
Slide 1Lesson 14: Fundamentals of the CAP Flying Safety Program Fundamentals of the CAP Flying Safety Program.
1 1 Slide Introduction to Data Mining and Business Intelligence.
Welcome.
Knowledge Discovery and Data Mining Evgueni Smirnov.
AVAT11001: Course Outline 1.Aircraft and Terminology 2.Radio Communications 3.Structure, Propulsion, Fuel Systems 4.Electrical, Hydraulic Systems and Instruments.
Heli-Expo 2013 Safety Challenge The Reality of Aeronautical Knowledge: The Analysis of Accident Reports Against What Aircrews are Supposed to Know.
Knowledge Discovery and Data Mining Evgueni Smirnov.
INTERACTIVE ANALYSIS OF COMPUTER CRIMES PRESENTED FOR CS-689 ON 10/12/2000 BY NAGAKALYANA ESKALA.
ASCI 517 – Advanced Meteorology Jose I. Jourdain Embry Riddle Aeronautical University July 18 th, 2011.
November 29, Hypothesis The hypothesis of this GIS Project is that airplane accidents happen within 25 NM of an airport. General Aviation and.
Research Project #5 Develop Common Data on Accident Circumstances.
Research Project #6 Develop Better Data on Accident Precursors or Leading Indicators.
Safety Recommendation A “Revise 14 CFR Part 91, 135, and 121 to require that all occupants be restrained during takeoff, landing, and turbulent conditions,
Transportation Safety Board of Canada Bureau de la sécurité des transports du Canada Lessons Learned from TSB Investigations of Helicopter Accidents ( )
Major transport accidents in Norway: assessing long-term frequency and priorities for prevention TRB paper Rune Elvik.
Runway Incursion Causal Categories OPERATIONAL ERROR (OE) - A human error caused by a tower controller. There are over 8000 tower controllers in the U.S.
Clustering Clustering is a technique for finding similarity groups in data, called clusters. I.e., it groups data instances that are similar to (near)
Lecture 7: Why Aircraft Needs to be Pressurized
1 Pattern Recognition: Statistical and Neural Lonnie C. Ludeman Lecture 30 Nov 11, 2005 Nanjing University of Science & Technology.
Commercial Aviation Safety Team (CAST) Potential Risk Reduction In Asia Potential Risk Reduction In Asia 3 rd Steering Committee Meeting COSCAP-NA, Sanya,
© Tan,Steinbach, Kumar Introduction to Data Mining 8/05/ Data Mining: Exploring Data Lecture Notes for Chapter 3 Introduction to Data Mining by Tan,
Compiled By: Raj Gaurang Tiwari Assistant Professor SRMGPC, Lucknow Unsupervised Learning.
Commercial Aviation Safety Team (CAST) Update Kyle L. Olsen COSCAP-South East Asia, Macau October, 2008.
30 SECOND RULE Clear your mind of all distractions. Focus on your flight. Remember at least one thing you learned at the safety seminar.
International Civil Aviation Organization ADREP/ECCAIRS End-user course Module N° 4 Preliminary Data Entry at the BEA Mexico City November, 2010.
1. Number of Fatal Accidents GA & Air Taxi CY GA ONLY GA Plus TAXI.
1 © The MITRE Corporation This is the copyright work of The MITRE Corporation and was produced for the U.S. Government under Contract Number DTFA01-01-C
Data Mining – Introduction (contd…) Compiled By: Umair Yaqub Lecturer Govt. Murray College Sialkot.
FINDINGS AND INVESTIGATIONS EXPERIMENTAL AIRCRAFT ACCIDENTS.
Presented to: By: Date: Federal Aviation Administration Southern Region FAASTeam National FAASTeam Projects Area-2 FAASTeam Reps and Lead Reps Mark L.
Abstract Analysis Mohammad Danial bin Mohammad Suhaimi (ME092584) Muhammad Khairil bin Amiruddin (ME092594)
Making Aviation Safer: Results of the National Aviation Weather Program’s 10-Year Goal to Reduce Weather-Related Accidents by 80 Percent 25th IIPS, AMS.
FAA Flight Standards AFS-220/430 FPAW 2017 Summer
Le Jiang (IMSG) and Frank Brody (NWS) (August 2, 2016)
Graphic showing EGPWS Activation
EMBRY-RIDDLE AERONAUTICAL UNIVERSITY College of Aviation
AVIATION SAFETY QUALITY ASSURANCE PROGRAMME
Human factors Forensic investigation
FAA and EASA Sport Aviation Accident Data Richard T Garrison FAI CIMP USA Paris France 2013.
The Business Aviation Perspective
Global Safety Situation
Air Carrier Continuing Analysis and Surveillance System (CASS)
Commercial aircraft operation engine realibility & safety
Data Mining: Exploring Data
Aviation Accidents in Alaska
Objectives of Safety Investigations Current Investigation Process
Turbulence Accidents and NTSB Research Update
Runway Excursions.
Presentation transcript:

1 Clustering NTSB Accidents Data Lishuai Li, Rafael Palacios, R. John Hansman JUP Quarterly Meeting Jan. 2010

2 Introduction  Aviation safety has been improved significantly over the past 50 years.  It is difficult to improve safety by making up for problems occurred in individual accident for the current systems.  Each accident is often induced by various anomalies. To identify patterns, correlations, and trends in large amounts of aviation accidents data can help us to understand problems and to prevent future incidents. Boeing, Statistical Summary of Commercial Jet Airplane Accidents, July 2009 Data Source: National Transportation Safety Board

3 Methodology  Research Method: Use data-mining techniques to identify patterns in accidents data Identify accidents with similar characteristics Incorporate findings with narratives to find causalities  Data: Subset of NTSB accident database system (ADMS2000) Event Type: Accident only, excluding incident FAR Part: Part 91 (General Aviation); Part 121 (Air Carriers) Aircraft Type: Airplanes only Year: from 2000 to 2005 Other database will be considered in future work  Data-mining tools: Clustering (e.g. k-means): use a distance function to search for partitioning of records such that the intra-cluster distance is minimal and the inter-cluster distance is maximum Other data-mining techniques will be considered and used in future study

4 Clustering Method  K-means clustering is a partitioning method.  Data can be partitioned into k mutually exclusive clusters.  K-means clustering finds a partition in which objects within each cluster are as close to each other as possible, and as far from objects in other clusters as possible. Each data point represents an accident. The attributes of that accident determine where the data point is. K-means clustering can be used to find accidents with similar attributes.

5 Preliminary Results of Clustering NTSB Accidents Data  For this preliminary study, we want to test if k-means clustering can be used to identify accidents with similar attributes specified.  Apply k-means clustering method to the subset of NTSB data (Part 91 & Part 121 Accidents from 2000 to 2005)  Accidents attributes used in clustering: Flight Plan Type, Injury Level, Visibility, Phase of Flight Location, Day of The Year

6 Phase of Flight & Visibility Characteristics for Part 91 Accidents ( )  General characteristics of accidents regarding individual variable are commonly known Accidents are more likely to happen in very low visibility conditions High rate of accidents during taking-offs and landings All events with visibility >10 are put into the same grouped as the ones with visibility =0

7 Phase of Flight & Visibility Characteristics by Flight Plan Type Phase of Flight Distribution of Part 91 Accidents ( ) VFR vs. IFR Visibility Distribution of Part 91 Accidents ( ) VFR vs. IFR

8 Phase of Flight & Visibility Characteristics by Injury Level Phase of Flight Distribution of Part 91 Accidents ( ) Non-Fatal vs. Fatal Visibility Distribution of Part 91 Accidents ( ) Non-Fatal vs. Fatal

9 Clustering by Flight Plan Type, Injury Level, Flight Phase, and Visibility  Combine all the information in 4 dimensions to cluster similar accidents  Accidents are clearly separated into 4 categories by Flight Plan Type and Visibility.  IFR accidents and Fatal accidents are more evenly spread over Phase of Flight and Visibility.  VFR/Non-Fatal accidents are concentrated in 3 regions: low visibility, or high visibility in initial phases and landings.

10 Accidents Characteristics by Clusters Fatal VFR/Other Non-Fatal VFR/Other Non-Fatal IFR Fatal IFR Phase of FlightVisibility Phase of FlightVisibility Phase of FlightVisibility Phase of FlightVisibility

11 Locations and Day of The Year of Part 91 Accidents ( ) Total number of accidents included: 6819 Location DistributionTime Distribution

12 Clustering Part 91 Accidents by Location & Day of The Year  Accidents are automatically classified by location and time of the year.  The two variables, location and day of the year, are not enough to create clusters with potential safety implications.

13 Locations and Day of The Year of Part 121 Accidents ( ) Total number of accidents included: 157 Location DistributionTime Distribution

14 Clustering Part 121 Accidents by Location & Day of the Year  Accidents sharing similar locations and time information are clustered together (12 clusters)

15 Accidents in Cluster 2  Cluster 2 includes 5 Caribbean accidents Accidents on 4/22/2002, 2/25/2003, 4/6/2003 4/24/2003 were caused by turbulence Accident on 2/8/2003 was caused by passenger stair handrail collapsing

16 Summary & Future Work  Data-mining method can combine multiple-dimensional information at the same time.  Accidents can be partitioned by clustering methods with specified attributes.  Future Work: Develop a systemic approach to include important variables in clustering method Explore other data-mining techniques to review safety data in a new way Investigate other possible safety data sources, e.g. accidents, ATC operation errors Identify patterns in accidents, or various anomalies, which can reveal subtle causalities underlying in the large amount of data

17 Thank You ! Questions?

18 Backup Slides