Validity and efficiency of conformal anomaly detection on big distributed data. / Nouretdinov, Ilia.

In: Advances in Science, Technology and Engineering Systems Journal, Vol. 2, No. 3, 2017, p. 254-267.

Research output: Contribution to journalArticlepeer-review

Published

Standard

Validity and efficiency of conformal anomaly detection on big distributed data. / Nouretdinov, Ilia.

In: Advances in Science, Technology and Engineering Systems Journal, Vol. 2, No. 3, 2017, p. 254-267.

Research output: Contribution to journalArticlepeer-review

Harvard

Nouretdinov, I 2017, 'Validity and efficiency of conformal anomaly detection on big distributed data', Advances in Science, Technology and Engineering Systems Journal, vol. 2, no. 3, pp. 254-267. https://doi.org/10.25046/aj020335

APA

Nouretdinov, I. (2017). Validity and efficiency of conformal anomaly detection on big distributed data. Advances in Science, Technology and Engineering Systems Journal, 2(3), 254-267. https://doi.org/10.25046/aj020335

Vancouver

Nouretdinov I. Validity and efficiency of conformal anomaly detection on big distributed data. Advances in Science, Technology and Engineering Systems Journal. 2017;2(3):254-267. https://doi.org/10.25046/aj020335

Author

Nouretdinov, Ilia. / Validity and efficiency of conformal anomaly detection on big distributed data. In: Advances in Science, Technology and Engineering Systems Journal. 2017 ; Vol. 2, No. 3. pp. 254-267.

BibTeX

@article{943c75b522224010ad2ded406580ee1b,
title = "Validity and efficiency of conformal anomaly detection on big distributed data",
abstract = "Conformal Prediction is a recently developed framework for reliable confident predictions. In this work we discuss its possible application to big data coming from different, possibly heterogeneous data sources. On example of anomaly detection problem, we study the question of saving validity of Conformal Prediction in this case. We show that the straight forward averaging approach is invalid, while its easy alternative of maximizing is not very efficient because of its conservativeness. We propose the third compromised approach that is valid, but much less conservative. It is supported by both theoretical justification and experimental results in the area of energy engineering.",
author = "Ilia Nouretdinov",
year = "2017",
doi = "10.25046/aj020335",
language = "English",
volume = "2",
pages = "254--267",
journal = "Advances in Science, Technology and Engineering Systems Journal",
number = "3",

}

RIS

TY - JOUR

T1 - Validity and efficiency of conformal anomaly detection on big distributed data

AU - Nouretdinov, Ilia

PY - 2017

Y1 - 2017

N2 - Conformal Prediction is a recently developed framework for reliable confident predictions. In this work we discuss its possible application to big data coming from different, possibly heterogeneous data sources. On example of anomaly detection problem, we study the question of saving validity of Conformal Prediction in this case. We show that the straight forward averaging approach is invalid, while its easy alternative of maximizing is not very efficient because of its conservativeness. We propose the third compromised approach that is valid, but much less conservative. It is supported by both theoretical justification and experimental results in the area of energy engineering.

AB - Conformal Prediction is a recently developed framework for reliable confident predictions. In this work we discuss its possible application to big data coming from different, possibly heterogeneous data sources. On example of anomaly detection problem, we study the question of saving validity of Conformal Prediction in this case. We show that the straight forward averaging approach is invalid, while its easy alternative of maximizing is not very efficient because of its conservativeness. We propose the third compromised approach that is valid, but much less conservative. It is supported by both theoretical justification and experimental results in the area of energy engineering.

U2 - 10.25046/aj020335

DO - 10.25046/aj020335

M3 - Article

VL - 2

SP - 254

EP - 267

JO - Advances in Science, Technology and Engineering Systems Journal

JF - Advances in Science, Technology and Engineering Systems Journal

IS - 3

ER -