Zoran Stajic

Learn More
Providing accurate load forecast to electric utility corporations is essential in order to reduce their operational costs and increase profits. Hence, training set selection is an important preprocessing step which has to be considered in practice in order to increase the accuracy of load forecasts. The usage of mutual information (MI) has been recently(More)
This paper presents a model for short-term load forecasting using least square support vector machines. Available data are analyzed and appropriate features are selected for the model. Last 24 hours load demands are used for features in combination with day in week and hour in day. It is shown that temperature is not always a very good feature for the(More)
In the deregulated energy market, the accuracy of load forecasting has a significant effect on the planning and operational decision making of utility companies. Electric load is a random non-stationary process influenced by a number of factors which make it difficult to model. To achieve better forecasting accuracy, a wide variety of models have been(More)
Training set instance selection is an important preprocessing step in many machine learning problems, including time series prediction, and has to be considered in practice in order to increase the quality of the predictions and possibly reduce training time. Recently, the usage of mutual information (MI) has been proposed in regression tasks, mostly for(More)
CONFLICT OF INTEREST NONE DECLARED. INTRODUCTION P-wave abnormalities on the resting electrocardiogram have been associated with cardiovascular or pulmonary disease. So far, "Gothic" P wave and verticalization of the frontal plane axis is related to lung disease, particularly obstructive lung disease. AIM We tested if inverted P wave in AVl as a lone(More)
INTRODUCTION Coronary procedures cannot be completed in 5-15% of cases through initially used radial artery approach due to frequent radial artery anomalies and vasospasm. In these cases, the ulnar artery approach could be the safe and effective alternative wrist approach. CASE REPORT A 60-year-old patient with stable angina pectoris, hypertension,(More)
This prospective, first-in-man, open-label multicenter study sought to assess the pharmacokinetics of sirolimus after Ultimaster drug-eluting stent implantation (coated with sirolimus and bioabsorbable co-polymer) in patients with de novo coronary artery disease (the TCD-10023 PK study). The primary endpoint was sirolimus concentration in peripheral whole(More)
A novel method for solving nonlinear algebraic equations describing behaviour of self-excited induction generator, based on the MATLAB Optimization Toolbox routines, is presented in the paper. Using this approach, critical rotor speed and excitation capacitance requirements under different loading conditions have been considered. Accuracy of prediction has(More)
— Risk became the crucial decision making criteria in evaluation of some control actions in power systems, but very often, these decisions are made in a highly uncertain environment. In this paper, a new graphical tool for risk assessment and decision making under uncertainty – hybrid influence diagram with fuzzy probability values and fuzzy random(More)
The paper discusses power and especially voltage quality issues in the smart grid environment. New demands that are facing the distribution network, by introducing the concept of intelligent networks (Smart Grids), are presented. Some examples of non-compliance of laws and practices in Serbia are presented as well, as the illustration of lack of strategic(More)