Polyphenols from Slovenian hops (Humulus lupulus L.) of the Aurora variety were extracted by different methods and using classical solvents and several deep eutectic solvents (DES) based on choline ...chloride as the hydrogen bond acceptor component. The obtained extract solutions were analyzed by HPLC for the content of extracted α- and β-acids and extracted xanthohumol. It was found that choline chloride:phenol DES concentrated aqueous solution had an extraction efficiency close to that of diethyl ether, which is considered one of the best classical extraction solvents for polyphenols from hops. The comparison of the extraction efficiency with other choline chloride-based DESs showed that the chemical similarity of the phenol ring in the solvent DES with the polyphenols in hops may be crucial for a highly efficient extraction with choline chloride:phenol DES. On the other hand, the choice of extraction method and the viscosity of the solvents tested seem to play only a minor role in this respect. As far as we know, this is the first study to attempt to relate extraction efficiency in the extraction of hydrophobic solutes to the compressibility of the DES extractants, the latter of which may be correlated with the extent of hydrophobic hydration around the DES components. In addition, using the heating and stirring method for the preparation of choline chloride-based DES concentrated aqueous solutions we found no support for the occurrence of water in two different roles (in the structural and in the dilution role) in these solvents.
In this paper, we propose a new indirect method for constructing the radio frequency layer of radio environment map (RF-REM) called self-tuning method (STM). The proposed STM takes into account the ...characteristics of the operating environment and performs estimation of the transmitter parameters, i.e. its location, antenna diagram, antenna azimuth, transmit power, as well the parameters of the propagation model to obtain the best match between the available measurements and the predicted signal levels. We compare STM to several most often considered existing methods using different numbers of randomly distributed measurements, which could in practice be obtained in a participatory-like manner. The performance evaluation of the methods is performed in terms of averaged root mean square error (
RMSE
¯
) and 95% confidence interval (CI) calculated between the constructed RF-REMs and the reference RF-REM, as well as in terms of false alarm zone ratio (FAZR) and correct detection zone ratio (CDZR
1
). The analysis shows the robustness of the STM to various spatial distributions of measurements and its fast convergence and low residual root mean square error compared to the inverse distance weighted (IDW) method, the inverse distance square weighted method (IDW2), the Kriging method, and the location estimation-based method (LIvE).
The authenticity and geographical origin of wines produced in Slovenia were investigated by a combination of IRMS and SNIF-NMR methods. A total of 102 grape samples of selected wines were carefully ...collected in three different wine-growing regions of Slovenia in 1996, 1997, and 1998. The stable isotope data were evaluated using principal component analysis (PCA) and linear discriminant analysis (LDA). The isotopic ratios to discriminate between coastal and continental regions are the deuterium/hydrogen isotopic ratio of the methylene site in the ethanol molecule (D/H)II and δ13C values; including also δ18O values in the PCA and LDA made possible separation between the two continental regions Drava and Sava. It was found that δ18O values are modified by the meteorological events during grape ripening and harvest. The usefulness of isotopic parameters for detecting adulteration or watering and to assess the geographical origin of wines is improved only when they are used concurrently. Keywords: Slovenian wines; natural stable isotope ratios; PCA; LDA; geographical origin; authenticity
In the last years, customer churn prediction has been very high on the agenda of telecommunications service providers. Among customers predicted as churners, highly influential customers deserve ...special attention, since their churns can also trigger churns of their peers. The aim of this study is to find good predictors of churn influence in a mobile service network. To this end, a procedure for determining the weak ground truth on churn influence is presented and used to determine the churn influence of prepaid customers. The determined scores are used to identify good churn-influence predictors among 74 candidate features. The identified predictors are finally used to build a churn-influence-prediction model. The results show that considerably better churn prediction results can be achieved using the proposed model together with the classical churn-prediction-model than by using the classical churn-prediction model alone. Moreover, the successfully predicted churners by the combined approach also have a greater number of churn followers. A successful retention of the predicted churners could greatly affect churn reduction since it could also prevent the churns of these followers.
Churn prediction has received much attention in the last decade. With the evolution of social networks and social network analysis tools in recent years, the consideration of social ties in churn ...prediction has proven promising. One possibility is to use energy diffusion models to model the spread of influence through a social network. This paper proposes a novel churn prediction diffusion model based on sociometric clique and social status theory. It describes the concept of energy in the diffusion model as an opinion of users, which is transformed to user influence using the derived social status function. Furthermore, a novel diffusion model prediction scheme applicable to a single user or a small subset of users is described: the Targeted User Subset Churn Prediction Scheme. The scheme allows fast churn prediction using limited computing resources. The diffusion model is evaluated on a real dataset of users obtained from the largest Slovenian mobile service provider, using the F-measure and lift curve. The empirical results show a significant improvement in prediction accuracy of the proposed method compared with the basic spreading activation technique (SPA) diffusion model. More specifically, our approach outperforms a basic SPA diffusion model by 116 % in terms of lift in the fifth percentile.
Isotopic ratios determined by SNIF-NMR and IRMS methods were used in combination with chemometric methods PCA, KANN and cluster analysis for the detection of wine chaptalisation and differentiation ...of wines according to the geographical origin. Selected wines from the three wine-growing regions of Slovenia were chosen for the analysis since Slovenia, small by surface, but pedologically and climatically diverse, offers interesting possibilities for studying the influence of this diversity upon the isotopic ratios in molecules of natural products. We found that the separation of wines of the Coastal region from the wines of the continental regions Sava and Drava is very good. On the other hand, the separation between wines from the Sava and the Drava region is not satisfactory. This is not surprising since the climatic differences between these two regions are small when compared with the differences between the continental and Coastal regions. Regarding the chaptalisation, the considerable improvement by combining both SNIF-NMR and IRMS is obtained. PCA and KANN give comparable separation of wines according to the geographical origin, but PCA is less time consuming. In the case of enrichment of wines from the Drava region by beet sugar better separation between natural and enriched wines is obtained using KANN method. In all cases cluster analysis shows poorer efficiency than PCA and KANN.
Posljednjih godina, predviđanje odljeva korisnika jedna je on važnijih tema među pružateljima telekomunikacijskih usluga. Među odlazećim korisnicima, oni najutjecajniji zaslužuju posebnu pažnju, jer ...njihov odljev može okinuti i odljev sljedbenika. Cilj ovog članka je pronalazak dobrih prediktora utjecaja odljeva na mobilne uslužne mreže. U tu svrhu, razvijena je metoda za njihovu identifikaciju među 74 potencijalna kandidata. Identificirani prediktori su potom korišteni za konačnu izgradnju modela predviđanja odljeva korisnika. Znatno bolji rezultati ostvaruju se kada se koristi predloženi model u kombinaciji s klasičnim modelom, nego kada se klasični model koristi zasebno. štoviše, kombiniranim predviđanjem izdvojeni utjecajni korisnici imaju veći broj sljedbenika. Uspješno zadržavanje predviđenog odljeva moglo bi uvelike utjecati na njegovo smanjenje, pošto bi samim time spriječilo i odljev sljedbenika.