NASA’s Aviation Safety Reporting System (ASRS) database is the world's largest repository of voluntary, confidential safety information provided by aviation's frontline personnel, including pilots, air traffic controllers, mechanics, flight attendants, dispatchers, and other members of the aviation community and the public. The database contains close to 2 million narratives, many of which describe everyday situations in which people saved the day. In these situations, people’s resilient behavior solved a problem, dealt with a malfunction, and maintained a safe operation despite a serious perturbation. To be able to extract lessons of such resilience from this large database, the use of machine learning algorithms is being explored. In this report, we describe a comparison between two such algorithms: Perilog and Word2Vec. An identical search using both programs was done on a database containing approximately 470,000 ASRS reports submitted between 1988 and 2022. The comparison reveals some of the strength and weaknesses of each algorithm as well as the challenges inherent in using such algorithms to extract lessons of resilience from the ASRS database.


    Zugriff

    Zugriff über TIB

    Verfügbarkeit in meiner Bibliothek prüfen


    Exportieren, teilen und zitieren



    Titel :

    Extracting Lessons of Resilience Using Machine Mining of the ASRS Database


    Beteiligte:
    Immanuel Barshi (Autor:in) / Bryan Matthews (Autor:in) / Jolene Feldman (Autor:in)

    Kongress:

    22nd International Symposium on Aviation Psychology (ISAP) ; 2023 ; Rochester, NY, US


    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Keine Angabe


    Sprache :

    Englisch




    Extracting lessons of resilience using machine mining of the ASRS database

    Barshi, Immanuel / Matthews, Bryan / Feldman, Jolene | TIBKAT | 2023

    Freier Zugriff

    Classification and Beyond: Exploring the ASRS Database

    Kraft, R. / Buntine, W. | British Library Conference Proceedings | 1994




    Ground Operations and ASRS

    L. Connell / D. Wichner / A. M. Jakey | NTIS | 2013