Pregled bibliografske jedinice broj: 548148
Detection of Suspicious Patterns of Energy Consumption Using Neural Network Trained by Generated Samples
Detection of Suspicious Patterns of Energy Consumption Using Neural Network Trained by Generated Samples // Proceedings of the ITI 2011 33rd International Conference on Information Technology Interfaces / Vesna Luzar-Stiffler, Iva Jarec, Zoran Bekic (ur.).
Zagreb: Sveučilišni računski centar Sveučilišta u Zagrebu (Srce), 2011. str. 551-556 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 548148 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Detection of Suspicious Patterns of Energy Consumption Using Neural Network Trained by Generated Samples
Autori
Markoč, Zrinka ; Hlupić, Nikica ; Basch, Danko
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of the ITI 2011 33rd International Conference on Information Technology Interfaces
/ Vesna Luzar-Stiffler, Iva Jarec, Zoran Bekic - Zagreb : Sveučilišni računski centar Sveučilišta u Zagrebu (Srce), 2011, 551-556
ISBN
978-953-7138-21-9
Skup
ITI 2011 33rd International Conference on Information Technology Interfaces
Mjesto i datum
Cavtat, Hrvatska, 27.06.2011. - 30.06.2011
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
non-technical loss; classification; neural network; sampling
Sažetak
In this paper two different methods for non-technical losses (NTL) detection are analyzed and new approach is proposed, based on the noticed drawbacks. It is shown that NTL can be successfully detected by a neural network trained by “artificial”, i.e., generated samples. This approach eliminates the need for many hard-to-obtain real life samples and the network can easily be trained to detect some new, nontypical occurrences in the system. This makes the proposed solution suitable for large companies that supply many different consumers who possibly change their consumption habits.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
POVEZANOST RADA
Projekti:
036-0361959-1979 - Oblikovanje i implementacija programskih jezika specijalne namjene (Basch, Danko, MZO ) ( CroRIS)
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb