SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Search the digital library catalog Help

Query: search in
search in
search in
search in
* old and bologna study programme

Options:
  Reset


1 - 10 / 11
First pagePrevious page12Next pageLast page
1.
2.
Review of sustainability terms and their definitions
Peter Glavič, Rebeka Kovačič Lukman, 2007, original scientific article

Abstract: Terminology in the field of sustainable development is becoming increasingly important because the number of terms continues to increase along with the rapid increase in awareness of the importance of sustainability. Various definitions of terms are used by different authors and organizations, for example, green chemistry, cleaner production, pollution prevention, etc. The importance of this topic has stimulated research into the problems of clarifying ambiguity and classifying terms used in the sustainability field. This paper provides results of the literature survey and summarizes the definitions of the terms, focusing on the environmental engineering field. In some cases, it proposes an improved definition. A hierarchical classification of the terms and their relationships has been based on a layer format that is presented graphically.
Keywords: chemical process design, sustainability, environmental protection, cleaner production, terminology, definitions, classification
Published: 31.05.2012; Views: 1206; Downloads: 29
URL Link to full text

3.
Developing a question answering system for the slovene language
Ines Čeh, Milan Ojsteršek, 2009, original scientific article

Abstract: In todayćs world the majority of information is sought after on the internet. A common method is the use of search engines. However since the result of a query to the search engine is a ranked list of results, this is not the final step. It is up to the user to review the results and determine which of the results provides the information needed. Often this process is time consuming and does not provide the sought after information. Besides the number of returned results the limiting factor is often the lack of ability of the usersto form the correct query. The solution for this can be found in the formof question answering systems, where the user proposes a question in the natural language, similarly as talking to another person. The answer is the exact answer instead of a list of possible results. This paper presents the design of a question answering system in natural slovene language. The system searches for the answers for our target domain (Faculty of Electrical Engineering and Computer Science) with the use of a local database, databases of the facultyćs information system, MS Excel files and through web service calls. We have developed two separate applications: one for users and the other for the administrators of the system. With the help of the latter application the administrators supervise the functioning and use of entire system. The former application is actually the system that answers the questions.
Keywords: question answering, Slovenian language, question classification, machine learning, question templates, personalization
Published: 31.05.2012; Views: 1206; Downloads: 18
URL Link to full text

4.
An algorithm for protecting knowledge discovery data
Boštjan Brumen, Izidor Golob, Tatjana Welzer-Družovec, Ivan Rozman, Marjan Družovec, Hannu Jaakkola, 2003, original scientific article

Abstract: In the paper, we present an algorithm that can be applied to protect data before a data mining process takes place. The data mining, a part of the knowledge discovery process, is mainly about building models from data. We address the following question: can we protect the data and still allow the data modelling process to take place? We consider the case where the distributions of original data values are preserved while the values themselves change, so that the resulting model is equivalent to the one built with original data. The presented formal approach is especially useful when the knowledge discovery process is outsourced. The application of the algorithm is demonstrated through an example.
Keywords: data protection algorithm, classification algorithm, disclosure control, data mining, knowledge discovery, data security
Published: 01.06.2012; Views: 1098; Downloads: 21
URL Link to full text

5.
Primerjava napovedne vrednosti rezultatov lestvic RISC (Revised Injury Severity Classification) in TRISS (Trauma and Injury Severity Score) na slovenskem vzorcu hudo poškodovanih
Drago Brilej, 2014, dissertation

Abstract: IZHODIŠČA: Temeljni pogoj za zagotavljanje kakovosti zdravljenja je spremljanje rezultatov. Za objektivno oceno potrebujemo ustrezne podatke. Glavni namen registrov poškodovanih je pridobivanje podatkov o celotni verigi oskrbe od mesta nesreče do zaključka hospitalizacije. Zaradi razpršenosti poškodovancev po številnih bolnišnicah v Sloveniji je v Projektu razvoja mreže travmatološke dejavnosti predvidena uvedba nacionalnega registra poškodovancev. Za primerjavo rezultatov zdravljenja poškodovancev z mednarodnimi standardi se največ uporablja metodologija TRISS. Razvili so jo z multivariantno analizo skupine poškodovancev (MTOS), ki se pomembno razlikuje od slovenskega vzorca hudo poškodovanih. Zaradi te razlike se je porodil dvom o uporabnosti metodologije TRISS. Z vključitvijo slovenskih poškodovancev v nemški TR DGU pa smo prevzeli metodo RISC za primerjavo rezultatov zdravljenja z drugimi ustanovami. Nova metoda še ni bila ovrednotena na skupini, ki se razlikuje od poškodbenega vzorca v TR DGU. Namen naloge je preveriti uporabnost metode RISC na slovenskem vzorcu hudo poškodovanih in jo primerjati z metodo TRISS. METODE: Od vstopa v TR DGU v letu 2006 smo v SB Celje prospektivno zajeli podatke o kohortni skupini 376 hudo poškodovanih in jih vnesli v TR DGU. Primerjali smo dejavnike tveganja med poškodovanci v SB Celje in TR DGU ter izračunali vrednosti TRISS in RISC za vsakega poškodovanca. S statistiko M smo primerjali porazdelitev izračunanih verjetnosti preživetja med SB Celje, MTOS in TR DGU. Za ugotavljanje ustreznosti točkovnih lestvic (TRISS, RISC in RISC II) smo uporabili statistične metode diskriminacije (aROC), natančnosti (razlika v preživetju) in kalibracije (statistika H-L). REZULTATI: Povprečna starost poškodovancev je bila 47 let, 83 % je bilo moških, 95 % topih poškodb. Povprečna ISS vrednost je bila 26,4 (90 % ≥ 16). V bolnišnici je umrlo 17,5 % poškodovancev. Standardizirana umrljivost je pokazala za 1,9 % manjšo umrljivost, kot je predvidena s statističnimi modeli. Ugotovili smo pomembno odstopanje v dejavnikih tveganja med poškodovanci v SB Celje in TR DGU, kar lahko razložimo z drugačnimi vključitvenimi merili. Potrdili smo, da je slovenski vzorec hudo poškodovanih drugačen, in da je treba preveriti učinkovitost metode RISC. Primerjali smo preživetje med skupinami in ugotovili slabo ujemanje skupine poškodovancev v SB Celje z MTOS (M = 0,50) ter dobro ujemanje s TR DGU (M = 0,88). V dveh časovnih obdobjih (2006–07 in 2011–12) se porazdelitev v SB Celje ni pomembno spremenila (M = 0,90). Potrdili smo pomembno razliko med skupino MTOS in SB Celje, ki vpliva na uporabnost metode TRISS. Kljub razlikam v dejavnikih tveganja pa smo potrdili dobro ujemanje rezultatov med skupinama SB Celje in TR DGU, kar upravičuje uporabo metode RISC na slovenskem vzorcu hudo poškodovanih. Najboljšo diskriminacijo sta pokazali lestvici RISC in RISCII (aROC 0,91 in 0,90). Najbolj natančna je bila lestvica RISC (razlika v umrljivosti 1,9 %), ki je prav tako imela najboljšo in skoraj popolno kalibracijo (H-L 0,53). ZAKLJUČKI: Metoda RISC je pokazala boljšo diskriminacijo in kalibracijo, bila je bolj natančna kot metodologija TRISS za slovenski vzorec hudo poškodovanih. Primerjava podatkov v SB Celje v letih 2006-7 z leti 2011-2 je pokazala nekaj razlik. Predvsem je opazno izboljšanje na področju kazalnikov kakovosti oskrbe (krajši predbolnišnični čas, krajši čas na urgentnem oddelku). Toda te razlike niso vplivale na uporabnost metode RISC. Prestala je test sprememb v strukturi in obravnavi poškodovancev skozi čas. Metoda TRISS kljub novim koeficientom ni primerna za uporabo na slovenskem vzorcu hudo poškodovanih. Posodobljena RISC II je dobra metoda, a nič boljša od že uveljavljene RISC.
Keywords: hudo poškodovani, vrednotenje, Trauma and Injury Severity Score (TRISS), Revised Injury Severity Classification (RISC), register
Published: 26.01.2015; Views: 969; Downloads: 190
.pdf Full text (6,40 MB)

6.
Characterization of Slovenian wines using multidimensional data analysis from simple enological descriptors
Adriána Bednárová, Roman Kranvogl, Darinka Brodnjak-Vončina, Tjaša Jug, Ernest Beinrohr, 2013, original scientific article

Abstract: Determination of the product's origin is one of the primary requirements when certifying a wine's authenticity. Significant research has described the possibilities of predicting a wine's origin using efficient methods of wine components' analyses connected with multivariate data analysis. The main goal of this study was to examine the discrimination ability of simple enological descriptors for the classification of Slovenian red and white wine samples according to their varieties and geographical origins. Another task was to investigate the inter-relations available among descriptors such as relative density, content of total acids, non-volatile acids and volatile acids, ash, reducing sugars, sugar-free extract, $SO_2$, ethanol, pH, and an important additional variable - the sensorial quality of the wine, using correlation analysis, principal component analysis (PCA), and cluster analysis (CLU). 739 red and white wine samples were scanned on a Wine Scan FT 120, from wave numbers 926 $cm^{–1}$ to 5012 $cm^{–1}$. The applied methods of linear discriminant analysis (LDA), general discriminant analysis (GDA), and artificial neural networks (ANN), demonstrated their power for authentication purposes.
Keywords: wine authentication, enological descriptors, classification techniques, ANN
Published: 10.07.2015; Views: 822; Downloads: 10
.pdf Full text (261,13 KB)
This document has many files! More...

7.
Chemometric characterisation of the quality of ground waters from different wells in Slovenia
Ernest Vončina, Darinka Brodnjak-Vončina, Nataša Sovič, Marjana Novič, 2007, original scientific article

Abstract: The quality of ground water as a source of drinking water in Slovenia is regularly monitored. One of the monitoring programmes is performed on 5 wells for drinking water supply, 3 industrial wells and 2 ground water monitoring wells. Two hundred and fourteen samples of ground waters were analysed in the time 2003-2004. Samples were gathered from ten different sampling sites and physical chemical measurements were performed. The following 13 physical chemical parameters were regularly controlled: temperature, pH, conductivity, nitrate, AOX (adsorbable organic halogens), metals such as chromium, pesticides (desethyl atrazine, atrazine and 2,6-dichlorobenzamide), highly-volatile halogenated hydrocarbons (trichlorometane, 1,1,2,2-tetrachloroethene and 1,1,2-trichloroethene). For handling the results different chemometrics methods were employed, such as basic statistical methods for the determination of mean and median values, standard deviations, minimal and maximal values of measured parameters and their mutual correlation coefficients, cluster analysis (CA), the principal component analysis (PCA), the clustering method based on Kohonen neural network, and linear discriminant analysis (LDA). The study gives the opportunity to follow the quality of ground waters at different sampling sites within the defined time period. Monitoring of general pollution of ground waters and following measuring can be used to search the pollution source, to plan prevention measures and to protect from pollution, as well.
Keywords: ground waters, water quality, principal component analysis, classification, Kohonen neural networks
Published: 21.12.2015; Views: 826; Downloads: 38
.pdf Full text (390,30 KB)
This document has many files! More...

8.
Comprehensible predictive modeling using regularized logistic regression and comorbidity based features
Gregor Štiglic, Petra Povalej Bržan, Nino Fijačko, Fei Wang, Alexandros Kalousis, Boris Delibašić, Zoran Obradović, 2015, original scientific article

Abstract: Different studies have demonstrated the importance of comorbidities to better understand the origin and evolution of medical complications. This study focuses on improvement of the predictive model interpretability based on simple logical features representing comorbidities. We use group lasso based feature interaction discovery followed by a post-processing step, where simple logic terms are added. In the final step, we reduce the feature set by applying lasso logistic regression to obtain a compact set of non-zero coefficients that represent a more comprehensible predictive model. The effectiveness of the proposed approach was demonstrated on a pediatric hospital discharge dataset that was used to build a readmission risk estimation model. The evaluation of the proposed method demonstrates a reduction of the initial set of features in a regression model by 72%, with a slight improvement in the Area Under the ROC Curve metric from 0.763 (95% CI: 0.755%0.771) to 0.769 (95% CI: 0.761%0.777). Additionally, our results show improvement in comprehensibility of the final predictive model using simple comorbidity based terms for logistic regression.
Keywords: predictive models, logistic regression, readmission classification, comorbidities
Published: 19.06.2017; Views: 219; Downloads: 76
.pdf Full text (1,13 MB)
This document has many files! More...

9.
Coopetition effect determinants
Joanna Cygler, Katarzyna Dębkowska, 2015, original scientific article

Abstract: Background and Goal: The article is aimed at conducting an empirical analysis of the value and significance of coopetitors’ attributes thanks to which coopetition, which is a combination of cooperation and competition between competitors, generates a substantial corporate profit. Four major competitors’ attributes have been analysed: its size, geographical scope, market and technological position. The research also includes the Porter’s value chain. Design/ Methodology/Approach: The survey has been conducted on a sample of 235 high- tech companies operating in Poland and involved in coopetition. The sample is representative. The data have been collected at interviews with company top executives or owners. The research applies the method of classification trees, which, thanks to diagrams, sequentially divides the examined data space into classes (spaces) of similar properties. The assessment of the effect of coopetition, including its variants, made by the examined company served as a dependent qualitative variable. Four coopetitor’s attributes and their variants were assumed as explanatory variables (predictors) affecting the assessment of cooperation. Results: The results of research indicated the necessity for an accurate competitor’s profile selection. The significance of each of the four attributes may be different depending on the undertaken areas of cooperation with a competitor. The value of all the attributes of competitors is also diverse depending on the area of cooperation. A selected competitor’s profile with regard to the four analysed attributes may become a stimulant to generate benefits in one area, while in another area it may become an inhibitor. Conclusions: So far, the selection of a coopetition partner has been treated universally, without scrutinizing on some specific needs in relation to the area of cooperation. The selection of an appropriate coopetitor’s profile will allow for the cost reduction in search of appropriate candidates for cooperation and in relations management.
Keywords: coopetition, effects, competitor’s attributes, classification trees
Published: 29.11.2017; Views: 132; Downloads: 42
.pdf Full text (1,04 MB)
This document has many files! More...

10.
Macroeconomic determinants of the non-performing placements and off-balance sheet liabilities of Croatian banks
Manuel Benazić, Dajana Radin, 2015, original scientific article

Abstract: Background and Purpose: The non-performing placements and off-balance sheet liabilities are often considered key factors that lead to banking crises. Economic and financial crises increase the level of the non-performing placements and off-balance sheet liabilities which can cause significant losses for banks. Effective management and regulatory/ supervisory institutions such central banks should be able to recognize and quantify these effects. Therefore, the purpose of this study is to empirically determine the existence and the quantitative impact of main Croatian macroeconomic variables on the non-performing placements and off-balance sheet liabilities of Croatian banks in the long and short-run. Methodology: For this purpose the bounds testing (ARDL) approach for cointegration is applied. The ARDL model is performed in two steps. The first step starts with conducting the bounds test for cointegration. In the second step, when cointegration is found, the long-run relationship and the associated error correction model are estimated. Results: The results indicate the existence of stable cointegration relationship between the variables i.e. in the longrun, an increase in real GDP reduces the level of the non-performing placements and off-balance sheet liabilities of Croatian banks wherein an increase in prices, unemployment, interest rate and the depreciation of the Croatian kuna exchange rate increases their level. On the other hand, in the short-run the results are rather mixed. Conclusion: To avoid crises, effective bank management and regulatory/supervisory institutions should be able to recognize and quantify these effects. This is a necessary precondition for implementation of an adequate prudential and monetary policy measures for reducing the level of the non-performing placements and off-balance sheet liabilities.
Keywords: non-performing placements and off-balance sheet liabilities, non-performing loans, economic and financial crises, credit risk, classification of placements and off-balance sheet liabilities
Published: 04.12.2017; Views: 205; Downloads: 54
.pdf Full text (467,97 KB)
This document has many files! More...

Search done in 0.15 sec.
Back to top
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica