scispace - formally typeset
M

Milan Gocic

Researcher at University of Niš

Publications -  62
Citations -  2530

Milan Gocic is an academic researcher from University of Niš. The author has contributed to research in topics: Evapotranspiration & Adaptive neuro fuzzy inference system. The author has an hindex of 20, co-authored 56 publications receiving 1843 citations.

Papers
More filters
Journal ArticleDOI

Analysis of changes in meteorological variables using Mann-Kendall and Sen's slope estimator statistical tests in Serbia

TL;DR: In this article, the authors analyzed the annual and seasonal trends of seven meteorological variables for twelve weather stations in Serbia during 1980-2010 and used the nonparametric Mann-Kendall and Sen's methods to determine whether there was a positive or negative trend in weather data with their statistical significance.
Journal ArticleDOI

Analysis of precipitation and drought data in Serbia over the period 1980–2010

TL;DR: In this paper, the authors used linear regression, Mann-Kendall and Spearman's Rho tests at the 5% significance level to analyze precipitation and standardised precipitation index (SPI) trends.
Journal ArticleDOI

Soft computing approaches for forecasting reference evapotranspiration

TL;DR: SVM-Wavelet model was found to perform better than the GP, SVM-FFA and ANN models and have higher correlation coefficient as compared to ANN and GP computational methods.
Journal ArticleDOI

Spatiotemporal characteristics of drought in Serbia

TL;DR: In this paper, the authors evaluated the spatiotemporal characteristics of drought in Serbia based on monthly precipitation data from 29 synoptic stations for the period of 1948-2012, using the Standardized Precipitation Index (SPI) and Smode principal component analysis (PCA) to capture the drought patterns.
Journal ArticleDOI

Extreme learning machine based prediction of daily dew point temperature

TL;DR: The study results convincingly advocate that ELM can be employed as an efficient method to predict daily dew point temperature with much higher precision than the SVM and ANN techniques.