Distributed Conformal Anomaly Detection. / Nouretdinov, Ilia.

Machine Learning and Applications (ICMLA), 2016 15th IEEE International Conference on. IEEE Computer Society, 2017. p. 1-6.

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

E-pub ahead of print

Standard

Distributed Conformal Anomaly Detection. / Nouretdinov, Ilia.

Machine Learning and Applications (ICMLA), 2016 15th IEEE International Conference on. IEEE Computer Society, 2017. p. 1-6.

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

Harvard

Nouretdinov, I 2017, Distributed Conformal Anomaly Detection. in Machine Learning and Applications (ICMLA), 2016 15th IEEE International Conference on. IEEE Computer Society, pp. 1-6. https://doi.org/10.1109/ICMLA.2016.0049

APA

Nouretdinov, I. (2017). Distributed Conformal Anomaly Detection. In Machine Learning and Applications (ICMLA), 2016 15th IEEE International Conference on (pp. 1-6). IEEE Computer Society. https://doi.org/10.1109/ICMLA.2016.0049

Vancouver

Nouretdinov I. Distributed Conformal Anomaly Detection. In Machine Learning and Applications (ICMLA), 2016 15th IEEE International Conference on. IEEE Computer Society. 2017. p. 1-6 https://doi.org/10.1109/ICMLA.2016.0049

Author

Nouretdinov, Ilia. / Distributed Conformal Anomaly Detection. Machine Learning and Applications (ICMLA), 2016 15th IEEE International Conference on. IEEE Computer Society, 2017. pp. 1-6

BibTeX

@inproceedings{1a6fc568d5c44b7f9e081aff356a2aaf,
title = "Distributed Conformal Anomaly Detection",
abstract = "Conformal approach to anomaly detection was recently developed as a reliable framework of classifying examples into normal and abnormal groups based on a training data set containing only normal examples. Its validity property is that a normal example, generated by the same distribution as the examples from the training set, is classified as anomaly with probability bounded from above by a pre-selected significance level. Parallel processing of big data may require a split of the training set into several sources. We also assume that the collection of data for two or more sources might be done in parallel and the data distribution may differ for these sources. The contribution of this work to conformal anomaly detection is studying the ways of keeping conformal validity when the training set is obtained from heterogeneous (differently distributed) sources.",
keywords = "conformal prediction, anomaly detection, distributed computing, validity",
author = "Ilia Nouretdinov",
year = "2017",
month = feb,
day = "2",
doi = "10.1109/ICMLA.2016.0049",
language = "English",
isbn = "978-1-5090-6168-6",
pages = "1--6",
booktitle = "Machine Learning and Applications (ICMLA), 2016 15th IEEE International Conference on",
publisher = "IEEE Computer Society",
address = "United States",

}

RIS

TY - GEN

T1 - Distributed Conformal Anomaly Detection

AU - Nouretdinov, Ilia

PY - 2017/2/2

Y1 - 2017/2/2

N2 - Conformal approach to anomaly detection was recently developed as a reliable framework of classifying examples into normal and abnormal groups based on a training data set containing only normal examples. Its validity property is that a normal example, generated by the same distribution as the examples from the training set, is classified as anomaly with probability bounded from above by a pre-selected significance level. Parallel processing of big data may require a split of the training set into several sources. We also assume that the collection of data for two or more sources might be done in parallel and the data distribution may differ for these sources. The contribution of this work to conformal anomaly detection is studying the ways of keeping conformal validity when the training set is obtained from heterogeneous (differently distributed) sources.

AB - Conformal approach to anomaly detection was recently developed as a reliable framework of classifying examples into normal and abnormal groups based on a training data set containing only normal examples. Its validity property is that a normal example, generated by the same distribution as the examples from the training set, is classified as anomaly with probability bounded from above by a pre-selected significance level. Parallel processing of big data may require a split of the training set into several sources. We also assume that the collection of data for two or more sources might be done in parallel and the data distribution may differ for these sources. The contribution of this work to conformal anomaly detection is studying the ways of keeping conformal validity when the training set is obtained from heterogeneous (differently distributed) sources.

KW - conformal prediction, anomaly detection, distributed computing, validity

U2 - 10.1109/ICMLA.2016.0049

DO - 10.1109/ICMLA.2016.0049

M3 - Conference contribution

SN - 978-1-5090-6168-6

SP - 1

EP - 6

BT - Machine Learning and Applications (ICMLA), 2016 15th IEEE International Conference on

PB - IEEE Computer Society

ER -