Siniša Ilić
Siniša Ilić has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Petar Spalevic
University of Pristina
2 shared publications - Alempije Veljovic
Faculty of Technical Sciences, Čačak
1 shared publication Biljana Prica
Faculty of technical sciences in Kosovska Mitrovica%SR33-01.08
1 shared publication- Dejan Lazovic
Faculty of Technical Sciences, Kosovska Mitrovica
1 shared publication Dragana Radosavljević
Faculty of Technical Sciences, University of Priština at Kosovska Mitrovica, Kneza Miloša 7, 38220 Kosovska Mitrovica, Serbia
1 shared publicationDragiša Miljković
Faculty of Technical Sciences, Knjaza Miloša 7, 38220 Kosovska Mitrovica
1 shared publication
Latest Publications
- Open Access
- 1 October 2025
- Published by IOP Publishing in IOP Conference Series: Materials Science and Engineering
- Vol. 1339 (1)
Using the data mining algorithms for sorting series in a Non-Parametric Stochastic Generation of Streamflow Series
Obtaining the prediction of natural flows of rivers enable planning of optimal operation rules for water allocation in the coming years. There are various models for prediction of a time-series of flow values for a large number of years based on observed data for significantly less time period. In this paper is presented a new method for calculation of a final step in one of the non-parametric models (Marković et al. algorithm) that in significantly less time (around 1 minute compared to 20 hours) sorts the data in simulated time series by using predictive data mining algorithms.
- 1 October 2025
- Published by IOP Publishing in IOP Conference Series: Materials Science and Engineering
- Vol. 1339 (1)
Open AccessUsing the data mining algorithms for sorting series in a Non-Parametric Stochastic Generation of Streamflow Series
Obtaining the prediction of natural flows of rivers enable planning of optimal operation rules for water allocation in the coming years. There are various models for prediction of a time-series of flow values for a large number of years based on observed data for significantly less time period. In this paper is presented a new method for calculation of a final step in one of the non-parametric models (Marković et al. algorithm) that in significantly less time (around 1 minute compared to 20 hours) sorts the data in simulated time series by using predictive data mining algorithms.
- 5 February 2022
- Published by University of Slavonski Brod in Tehnicki vjesnik - Technical Gazette
- Vol. 29 (1) , 346-353
A Comparison of Query Execution Speeds for Large Amounts of Data Using Various DBMS Engines Executing on Selected RAM and CPU Configurations
In modern economies, most important business decisions are based on detailed analysis of available data. In order to obtain a rapid response from analytical tools, data should be pre-aggregated over dimensions that are of most interest to each busine...
- 5 February 2022
- Published by University of Slavonski Brod in Tehnicki vjesnik - Technical Gazette
- Vol. 29 (1) , 346-353
A Comparison of Query Execution Speeds for Large Amounts of Data Using Various DBMS Engines Executing on Selected RAM and CPU Configurations
In modern economies, most important business decisions are based on detailed analysis of available data. In order to obtain a rapid response from analytical tools, data should be pre-aggregated over dimensions that are of most interest to each busine...
- Open Access
- 1 January 2013
- Published by National Library of Serbia in Serbian Journal of Electrical Engineering
- Vol. 10 (2) , 247-260
Comparison of different methods for extracting bone cross-sectional geometric properties from CT images
Analysis of the geometric properties of bone cross-sections is often used to determine skeletal performance and the ability of the body to resist different external forces. This analysis is dependent on obtaining adequate bone cross-sectional images. CT images can be used for this purpose by performing some pre-processing of images in order to achieve sufficient accuracy. In this paper we have used experiments to show that relatively good accuracy of bone cross sectional areas and moments of inertia can be achieved by simple threshold level filtering of CT images.
- 1 January 2013
- Published by National Library of Serbia in Serbian Journal of Electrical Engineering
- Vol. 10 (2) , 247-260
Open AccessComparison of different methods for extracting bone cross-sectional geometric properties from CT images
Analysis of the geometric properties of bone cross-sections is often used to determine skeletal performance and the ability of the body to resist different external forces. This analysis is dependent on obtaining adequate bone cross-sectional images. CT images can be used for this purpose by performing some pre-processing of images in order to achieve sufficient accuracy. In this paper we have used experiments to show that relatively good accuracy of bone cross sectional areas and moments of inertia can be achieved by simple threshold level filtering of CT images.
- 7 May 2012
- Published by Oxford University Press (OUP) in The Computer Journal
- Vol. 56 (7) , 827-842
Using Wavelet Packets for Selectivity Estimation
The selectivity estimation (estimating the number of records that satisfy query conditions) is an important task for query optimization in modern database management systems (DBMS). For this reason, many DBMS maintain histograms to approximate the frequency distribution of values in the attributes of relations. In this paper, we present wavelet packets as an alternative method to the standard wavelet decomposition for building histograms of the distribution of data stored in relations to the database. This method is tested by approximating the cumulative data distribution of one attribute and the joint distributions of two attributes in a relation using various error measures. Experiments performed on synthetically generated data distributions show that our histograms offer improvements in accuracy over standard wavelet decomposition methods.
- 7 May 2012
- Published by Oxford University Press (OUP) in The Computer Journal
- Vol. 56 (7) , 827-842
Using Wavelet Packets for Selectivity Estimation
The selectivity estimation (estimating the number of records that satisfy query conditions) is an important task for query optimization in modern database management systems (DBMS). For this reason, many DBMS maintain histograms to approximate the frequency distribution of values in the attributes of relations. In this paper, we present wavelet packets as an alternative method to the standard wavelet decomposition for building histograms of the distribution of data stored in relations to the database. This method is tested by approximating the cumulative data distribution of one attribute and the joint distributions of two attributes in a relation using various error measures. Experiments performed on synthetically generated data distributions show that our histograms offer improvements in accuracy over standard wavelet decomposition methods.
- Open Access
- 1 January 2010
- Published by National Library of Serbia in Facta universitatis - series: Electronics and Energetics
- Vol. 23 (3) , 379-393
Recognition of vowels in continuous speech by using formants
Speech consists of acoustic pressure waves created by the voluntary movements of anatomical structures in the human speech production system. These waveforms are broadly classified into voiced and unvoiced speech. Voiced sounds (vowels for example), produce quasi-periodic pulses of air which are acoustically filtered as they propagate through the vocal tract. The main distinction between vowels and consonants is that vowels resonate in the throat. Formants are exactly the resonant frequencies of a vocal tract when pronouncing a vowel. In this paper we attempt to carry out Vowel Recognition through Formant Analysis in Serbian language, wherein we detect which of the five Serbian vowels is spoken by the Speaker. Here we describe a standard approach for classification of vowels in continuous speech based on three formants: F1, F2 and F3. We have investigated the correlations between formants in each vowel and developed the algorithm to reduce the overlap of different vowels in F1-F2 and F2-F3 planes.
- 1 January 2010
- Published by National Library of Serbia in Facta universitatis - series: Electronics and Energetics
- Vol. 23 (3) , 379-393
Open AccessRecognition of vowels in continuous speech by using formants
Speech consists of acoustic pressure waves created by the voluntary movements of anatomical structures in the human speech production system. These waveforms are broadly classified into voiced and unvoiced speech. Voiced sounds (vowels for example), produce quasi-periodic pulses of air which are acoustically filtered as they propagate through the vocal tract. The main distinction between vowels and consonants is that vowels resonate in the throat. Formants are exactly the resonant frequencies of a vocal tract when pronouncing a vowel. In this paper we attempt to carry out Vowel Recognition through Formant Analysis in Serbian language, wherein we detect which of the five Serbian vowels is spoken by the Speaker. Here we describe a standard approach for classification of vowels in continuous speech based on three formants: F1, F2 and F3. We have investigated the correlations between formants in each vowel and developed the algorithm to reduce the overlap of different vowels in F1-F2 and F2-F3 planes.