Anomaly detection in flight recorder data: A dynamic data-driven approach

Santanu Das, Soumalya Sarkar, Asok Ray, Ashok Srivastava, Donald L. Simon

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    12 Citations (Scopus)

    Abstract

    This paper presents a method of feature extraction in the context of aviation data analysis. The underlying algorithm utilizes a feature extraction algorithm called symbolic dynamic filtering (SDF) that was recently published. In SDF, time-series data are partitioned for generating symbol sequences that, in turn, construct probabilistic finite state automata (PFSA) to serve as features for pattern classification. The SDF-based algorithm of feature extraction, which enjoys both flexibility of implementation and computational efficiency, is directly applicable to detection, classification, and prediction of anomalies and faults. The results of analysis with real-world flight recorder data show that the SDF-based features can be derived at a desired level of abstraction from the information embedded in the time-series data. The performance of the proposed SDF-based feature extraction is compared with that of standard temporal feature extraction for anomaly detection. Our study on flight recorder data shows that SDF-based features can enable discovering unique anomalous flights and improve the performance of the detection algorithm. We also theoretically show that under certain conditions it may be possible to achive a better or comparable time complexity with SDF based features.

    Original languageEnglish (US)
    Title of host publication2013 American Control Conference, ACC 2013
    Pages2668-2673
    Number of pages6
    StatePublished - Sep 11 2013
    Event2013 1st American Control Conference, ACC 2013 - Washington, DC, United States
    Duration: Jun 17 2013Jun 19 2013

    Other

    Other2013 1st American Control Conference, ACC 2013
    CountryUnited States
    CityWashington, DC
    Period6/17/136/19/13

    Fingerprint

    Feature extraction
    Time series
    Finite automata
    Computational efficiency
    Aviation
    Pattern recognition

    All Science Journal Classification (ASJC) codes

    • Electrical and Electronic Engineering

    Cite this

    Das, S., Sarkar, S., Ray, A., Srivastava, A., & Simon, D. L. (2013). Anomaly detection in flight recorder data: A dynamic data-driven approach. In 2013 American Control Conference, ACC 2013 (pp. 2668-2673). [6580237]
    Das, Santanu ; Sarkar, Soumalya ; Ray, Asok ; Srivastava, Ashok ; Simon, Donald L. / Anomaly detection in flight recorder data : A dynamic data-driven approach. 2013 American Control Conference, ACC 2013. 2013. pp. 2668-2673
    @inproceedings{ff01bf0c9eef4b31bf7a67edc5a5b125,
    title = "Anomaly detection in flight recorder data: A dynamic data-driven approach",
    abstract = "This paper presents a method of feature extraction in the context of aviation data analysis. The underlying algorithm utilizes a feature extraction algorithm called symbolic dynamic filtering (SDF) that was recently published. In SDF, time-series data are partitioned for generating symbol sequences that, in turn, construct probabilistic finite state automata (PFSA) to serve as features for pattern classification. The SDF-based algorithm of feature extraction, which enjoys both flexibility of implementation and computational efficiency, is directly applicable to detection, classification, and prediction of anomalies and faults. The results of analysis with real-world flight recorder data show that the SDF-based features can be derived at a desired level of abstraction from the information embedded in the time-series data. The performance of the proposed SDF-based feature extraction is compared with that of standard temporal feature extraction for anomaly detection. Our study on flight recorder data shows that SDF-based features can enable discovering unique anomalous flights and improve the performance of the detection algorithm. We also theoretically show that under certain conditions it may be possible to achive a better or comparable time complexity with SDF based features.",
    author = "Santanu Das and Soumalya Sarkar and Asok Ray and Ashok Srivastava and Simon, {Donald L.}",
    year = "2013",
    month = "9",
    day = "11",
    language = "English (US)",
    isbn = "9781479901777",
    pages = "2668--2673",
    booktitle = "2013 American Control Conference, ACC 2013",

    }

    Das, S, Sarkar, S, Ray, A, Srivastava, A & Simon, DL 2013, Anomaly detection in flight recorder data: A dynamic data-driven approach. in 2013 American Control Conference, ACC 2013., 6580237, pp. 2668-2673, 2013 1st American Control Conference, ACC 2013, Washington, DC, United States, 6/17/13.

    Anomaly detection in flight recorder data : A dynamic data-driven approach. / Das, Santanu; Sarkar, Soumalya; Ray, Asok; Srivastava, Ashok; Simon, Donald L.

    2013 American Control Conference, ACC 2013. 2013. p. 2668-2673 6580237.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    TY - GEN

    T1 - Anomaly detection in flight recorder data

    T2 - A dynamic data-driven approach

    AU - Das, Santanu

    AU - Sarkar, Soumalya

    AU - Ray, Asok

    AU - Srivastava, Ashok

    AU - Simon, Donald L.

    PY - 2013/9/11

    Y1 - 2013/9/11

    N2 - This paper presents a method of feature extraction in the context of aviation data analysis. The underlying algorithm utilizes a feature extraction algorithm called symbolic dynamic filtering (SDF) that was recently published. In SDF, time-series data are partitioned for generating symbol sequences that, in turn, construct probabilistic finite state automata (PFSA) to serve as features for pattern classification. The SDF-based algorithm of feature extraction, which enjoys both flexibility of implementation and computational efficiency, is directly applicable to detection, classification, and prediction of anomalies and faults. The results of analysis with real-world flight recorder data show that the SDF-based features can be derived at a desired level of abstraction from the information embedded in the time-series data. The performance of the proposed SDF-based feature extraction is compared with that of standard temporal feature extraction for anomaly detection. Our study on flight recorder data shows that SDF-based features can enable discovering unique anomalous flights and improve the performance of the detection algorithm. We also theoretically show that under certain conditions it may be possible to achive a better or comparable time complexity with SDF based features.

    AB - This paper presents a method of feature extraction in the context of aviation data analysis. The underlying algorithm utilizes a feature extraction algorithm called symbolic dynamic filtering (SDF) that was recently published. In SDF, time-series data are partitioned for generating symbol sequences that, in turn, construct probabilistic finite state automata (PFSA) to serve as features for pattern classification. The SDF-based algorithm of feature extraction, which enjoys both flexibility of implementation and computational efficiency, is directly applicable to detection, classification, and prediction of anomalies and faults. The results of analysis with real-world flight recorder data show that the SDF-based features can be derived at a desired level of abstraction from the information embedded in the time-series data. The performance of the proposed SDF-based feature extraction is compared with that of standard temporal feature extraction for anomaly detection. Our study on flight recorder data shows that SDF-based features can enable discovering unique anomalous flights and improve the performance of the detection algorithm. We also theoretically show that under certain conditions it may be possible to achive a better or comparable time complexity with SDF based features.

    UR - http://www.scopus.com/inward/record.url?scp=84883533871&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84883533871&partnerID=8YFLogxK

    M3 - Conference contribution

    AN - SCOPUS:84883533871

    SN - 9781479901777

    SP - 2668

    EP - 2673

    BT - 2013 American Control Conference, ACC 2013

    ER -

    Das S, Sarkar S, Ray A, Srivastava A, Simon DL. Anomaly detection in flight recorder data: A dynamic data-driven approach. In 2013 American Control Conference, ACC 2013. 2013. p. 2668-2673. 6580237