Vladimir Ceperic

Learn More
In this paper the use of sparse linear regression algorithms in echo state networks (ESN) is presented for reducing the number of readouts and improving the robustness and generalization properties of ESNs. Three data sets with overall 80 tests are used to validate the use of sparse linear regression algorithms for echo state networks. It is shown that it(More)
This paper presents a generic strategy for short-term load forecasting (STLF) based on the support vector regression machines (SVR). Two important improvements to the SVR based load forecasting method are introduced, i.e., procedure for generation of model inputs and subsequent model input selection using feature selection algorithms. One of the objectives(More)
High frequency/speed designs still predominantly use microstrip lines on relatively cheap FR-4 substrates, despite their relatively poor high frequency performance. One good alternative is to use CBCPW lines (conductor backed coplanar waveguide). Compared to CBCPW, microstrip lines are more susceptible to interference (EMI) and can more easily generate(More)
A black-box method for modeling the time-domain response of integrated circuits (ICs) based on echo state networks is proposed. The number and value of the input and feedback delays required for modeling nonlinear systems with memory are detected automatically, and the training procedure is very fast and robust. The resulting models can be implemented in(More)
This paper describes an implementation of a proportional-integral-derivative (PID) controller with an iterative error compensator for a DC brushless motor to improve the quality of a photocopier. The parameters of the iterative error compensator are determined by using particle swarm optimization algorithm. The proposed controller reduces the effects of(More)
The aim of this study is to develop a new, computationally-efficient, anatomically-realistic 3D bidomain cardiac electrical activity model using widely available software and standard low-cost hardware. The model incorporates whole-heart embedded in a human torso, spontaneous activation of sinoatrial node and specialized conduction system with heterogeneous(More)