Avtor/Urednik		Nančovska, Irena; Todorovski, Ljupčo; Jeglič, Anton; Fefer, Dušan
Naslov		Identification and predicion of DC voltage generation system with equation discovery system and neural networks
Tip		članek
Vir		In: Adam SF, Petriu EM, Piuri V, editors. ETIMVITS' 98. Proceedings of the 1998 IEEE international workshop on emerging technologies, intelligent measurement and virtual systems for instrumentation and measurement; 1998 May 15-16; St. Paul. St. Paul: Instrumentation and measurement society,
Leto izdaje		1998
Obseg		str. 20-9
Jezik		eng
Abstrakt		The aim of the paper is to compare the predictive abilities of the novel method for time series prediction that is based on equation discovery with neural networks. Both methods are used for short-term (one-step a head) prediction and have the ability to learn from examples. With purpose to validate the predictive models, they are applied to several data sets. Further, the successful predictive models could be used for voltage correction in a high precision solid-state DC voltage reference source (DCVRS) as a segment in the software controlled voltage reference elements (VRE).
Deskriptorji		NEURAL NETWORKS (COMPUTER) ARTIFICIAL INTELLIGENCE FORECASTING