Project detail

Expert system for automatic analysis and control of big data storage for manufacturing companies

Duration: 01.10.2017 — 31.12.2020

Funding resources

Ministerstvo průmyslu a obchodu ČR - TRIO

- whole funder (2017-08-24 - 2020-12-31)

On the project

Cílem tohoto projektu je výzkum a vývoj expertního systému, který s využitím technologií prediktivní analytiky bude schopen automaticky analyzovat provoz big data úložišť v reálném čase a navrhovat okamžitý a vhodný způsob zotavení datového skladu z chyby či poruchy za cílem minimalizace finančních ztrát podniku. Navrhované řešení se týká zejména produktů společností Hitachi a Hewlett Packard (jsou v současné době považováni za leadry trhu v oblasti data storage) a předpovídají funkci datových skladů. Vyvinutý nástroj bude možné nasadit na stávající provozované datové sklady a s pomocí umělé inteligence bude možné rozpoznávat netypické chování a předpovídat možnost selhání prvků datového skladu či automaticky navrhovat vhodné řešení pro minimalizaci ztrát na základě vzniklého problému s pomocí prediktivní analytiky.

Description in English
The main objective of this project is the research and development of an expert system which, using predictive analytics technology will be able to automatically analyze big-data storages in the real-time and suggest immediate and suitable way how to recover the warehouse data from error or fault state in order to minimize financial losses of a company. The proposed solution is devoted to product lines of the Hitachi, Hewlett Packard (currently considered the market leader in data storage) and SUN platform. The developed system can be deployed on existing operating data warehouses and by the use of artificial intelligence it will be able to recognize unusual behavior, predict the possible failure of the data warehouse and automatically suggest appropriate solutions to minimize possible losses and propose predictive analytics. (See also Annex, section 1.2)

Keywords
big data; datové sklady; prediktivní analytika; umělá inteligence

Key words in English
big data; data warehouses; predictive analytics; artificial intelligence

Mark

FV20044

Default language

Czech

People responsible

Mašek Jan, Ing., Ph.D. - fellow researcher
Povoda Lukáš, Ing., Ph.D. - fellow researcher
Rajnoha Martin, Ing., Ph.D. - fellow researcher
Uher Václav, Ing., Ph.D. - fellow researcher
Burget Radim, doc. Ing., Ph.D. - principal person responsible

Units

Department of Telecommunications
- (2017-10-01 - 2020-12-31)

Results

MAŠEK, J.; RAJNOHA, M.; BURGET, R.; DUTTA, M. Automatic System for Diseased Artery Transverse Section Detection. In 2018 5th International Conference on Signal Processing and Integrated Networks (SPIN). Dillí, Indie: 2018. p. 322-326. ISBN: 978-1-5386-3045-7.
Detail

RAJNOHA, M.; POVODA, L.; MAŠEK, J.; BURGET, R.; DUTTA, M. Pedestrian Detection from Low Resolution Public Cameras in the Wild. In 2018 5th International Conference on Signal Processing and Integrated Networks (SPIN). New Delhi, India: 2018. p. 291-295. ISBN: 978-1-5386-3045-7.
Detail

RAJNOHA, M.; BURGET, R.; MEKYSKA, J.; ELIÁŠOVÁ, I.; KOŠŤÁLOVÁ, M.; REKTOROVÁ, I. Towards Identification of Hypomimia in Parkinson’s Disease Based on Face Recognition Methods. In 2018 10th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT). Moskva: 2018. p. 182-185. ISBN: 978-1-5386-9361-2.
Detail

RAJNOHA, M.; BURGET, R.; POVODA, L. Image Background Noise Impact on Convolutional Neural Network Training. In 2018 10th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT). Moskva: 2018. p. 168-171. ISBN: 978-1-5386-9361-2.
Detail

MYŠKA, V.;BURGET, R.;POVODA, L.;DUTTA, M. Linguistically independent sentiment analysis using convolutional-recurrent neural networks model. In 2019 42nd International Conference on Telecommunications and Signal Processing (TSP). Budapest, Hungary: IEEE, 2019. p. 212-215. ISBN: 978-1-7281-1864-2.
Detail

MYŠKA,V.; BURGET, R.; BREZANY, P. Graph neural network for website element detection. In 42nd International Conference on Telecommunications and Signal Processing (TSP). Budapest, Hungary: IEEE, 2019. p. 216-219. ISBN: 978-1-7281-1864-2.
Detail

FATIMA, A.; MAUYA, R.; DUTTA, M.; BURGET, R.; MAŠEK, J. Android Malware Detection Using Genetic Algorithm based Optimized Feature Selection and Machine Learning. In 2019 42nd International Conference on Telecommunications and Signal Processing (TSP). 2019. p. 220-223. ISBN: 978-1-7281-1864-2.
Detail

RAJNOHA, M.; MIKULEC, V.; BURGET, R.; DRAŽIL, J. A Perspective of the Noise Removal for Faster Neural Network Training. In 2019 11th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT). Dublin: 2019. p. 1-4. ISBN: 978-1-7281-5763-4.
Detail

IRSHAD, A.; MAUYA, R.; DUTTA, M.; BURGET, R.; UHER, V. Feature Optimization for Run Time Analysis of Malware in Windows Operating System using Machine Learning Approach. In 2019 42nd International Conference on Telecommunications and Signal Processing (TSP). Budapest, Hungary: IEEE, 2019. p. 255-260. ISBN: 978-1-7281-1864-2.
Detail

KOLAŘÍK, M.; BURGET, R.; ŘÍHA, K. Comparing Normalization Methods for Limited Batch Size Segmentation Neural Networks. In 2020 43rd International Conference on Telecommunications and Signal Processing (TSP). 2020. p. 677-680. ISBN: 978-1-7281-6376-5.
Detail

BURGET, R.; MAŠEK, J.; KOLAŘÍK, M.; DRAŽIL, J.; SUŠILA, P.: Expertní systém pro automatickou analýzu a řízení big data úložišť; Expertní systém pro automatickou analýzu a řízení big data úložišť. 3S.cz, s. r. o. Eliášova 25 616 00 BRNO. URL: https://3s.cz/cs/odborna-sekce/detail/id/176-vyuziti-umele-inteligence-pro-rizeni-v-big-data-ulozist. (software)
Detail

Responsibility: Burget Radim, doc. Ing., Ph.D.