Deep learning for inferring cause of data anomalies

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F18%3A00106847" target="_blank" >RIV/00216224:14330/18:00106847 - isvavai.cz</a>

Result on the web

<a href="http://dx.doi.org/10.1088/1742-6596/1085/4/042015" target="_blank" >http://dx.doi.org/10.1088/1742-6596/1085/4/042015</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1088/1742-6596/1085/4/042015" target="_blank" >10.1088/1742-6596/1085/4/042015</a>

Result language

angličtina

Original language name

Deep learning for inferring cause of data anomalies

Original language description

Daily operation of a large-scale experiment is a resource consuming task, particularly from perspectives of routine data quality monitoring. Typically, data comes from different sub-detectors and the global quality of data depends on the combinatorial performance of each of them. In this paper, the problem of identifying channels in which anomalies occurred is considered. We introduce a generic deep learning model and prove that, under reasonable assumptions, the model learns to identify ’channels’ which are affected by an anomaly. Such model could be used for data quality manager cross-check and assistance and identifying good channels in anomalous data samples. The main novelty of the method is that the model does not require ground truth labels for each channel, only global flag is used. This effectively distinguishes the model from classical classification methods. Being applied to CMS data collected in the year 2010, this approach proves its ability to decompose anomaly by separate channels.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2018

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Journal of Physics: Conference Series Volume 1085, Issue 4, 18th International Workshop on Advanced Computing and Analysis Techniques in Physics Research, ACAT 2017

ISBN

—

ISSN

1742-6588

e-ISSN

—

Number of pages

6

Pages from-to

1-6

Publisher name

Institute of Physics Publishing

Place of publication

Seattle

Event location

Seattle

Event date

Jan 1, 2018

Type of event by nationality

CST - Celostátní akce

UT code for WoS article

000467872200081