New tool for visualization of time series and anomalies in streaming data

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F16%3A00236681" target="_blank" >RIV/68407700:21230/16:00236681 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.researchgate.net/publication/291774971_NEW_TOOL_FOR_VISUALIZATION_OF_TIME-SERIES_AND_ANOMALIES_IN_STREAMING_DATA_-_short_version" target="_blank" >https://www.researchgate.net/publication/291774971_NEW_TOOL_FOR_VISUALIZATION_OF_TIME-SERIES_AND_ANOMALIES_IN_STREAMING_DATA_-_short_version</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.11118/actaun201664041353" target="_blank" >10.11118/actaun201664041353</a>

Jazyk výsledku

angličtina

Název v původním jazyce

New tool for visualization of time series and anomalies in streaming data

Popis výsledku v původním jazyce

Presented is a new visualization module which is available as an open source solution and features some novel combination of capabilities. The focus is on its lightweight, interactive & intuitive use and ease of deployment – including a setup for a live monitoring system with anomaly detection and highlighting abilities. This study describes the design and development process of our new tool for visualization of time-series data with focus on anomaly detection and streaming data. We frame the examples and motivation from our research activities, which include design and evaluation of neural network models, systems for continuous monitoring and anomaly detection (for example in IT or medical domains), and from usage in signal analysis applications. The most important aspects of the proposed visualization tool are ease of availability, interactive graph support, live monitoring and a possibility to highlight anomalies. The software is published at https://github.com/nupic-community/nupic.visualizations (OTAHAL, M., FOHL, J., 2015); there is also available an extended version of the article with more details and figures (OTAHAL, M., STEPANKOVA, O., 2015).

Název v anglickém jazyce

New tool for visualization of time series and anomalies in streaming data

Popis výsledku anglicky

Presented is a new visualization module which is available as an open source solution and features some novel combination of capabilities. The focus is on its lightweight, interactive & intuitive use and ease of deployment – including a setup for a live monitoring system with anomaly detection and highlighting abilities. This study describes the design and development process of our new tool for visualization of time-series data with focus on anomaly detection and streaming data. We frame the examples and motivation from our research activities, which include design and evaluation of neural network models, systems for continuous monitoring and anomaly detection (for example in IT or medical domains), and from usage in signal analysis applications. The most important aspects of the proposed visualization tool are ease of availability, interactive graph support, live monitoring and a possibility to highlight anomalies. The software is published at https://github.com/nupic-community/nupic.visualizations (OTAHAL, M., FOHL, J., 2015); there is also available an extended version of the article with more details and figures (OTAHAL, M., STEPANKOVA, O., 2015).

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

JC - Počítačový hardware a software

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2016

Kód důvěrnosti údajů

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

Název periodika

Acta Universitatis Agriculturae et Silviculturae Mendelianae Brunensis

ISSN

1211-8516

e-ISSN

—

Svazek periodika

2016

Číslo periodika v rámci svazku

64

Stát vydavatele periodika

CZ - Česká republika

Počet stran výsledku

12

Strana od-do

1353-1364

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-84990891747