Search

This research was carried out to compare selected forecasting methods, such as the following: Artificial Neural Networks (ANNs), Classification and Regression Trees (CARTs), Chi-squared Automatic Interaction Detector (CHAID), Fuzzy Logic Toolbox (FUZZY), Multivariant Adaptive Regression Splines (MARSs), Regression Trees (RTs), Rough Set Theory (RST), and Support Regression Trees (SRTs), in the context of determining the temperature of brine from vertical ground heat exchangers used by a heat pump heating system. The subject of the analysis was a public building located in Poland, in a temperate continental climate zone. The results of this study indicate that the models based on Rough Set Theory (RST) and Artificial Neural Networks (ANNs) achieved the highest accuracy in predicting brine temperature, with the choice of the preferred method depending on the input variables used for modeling. Using three independent variables (mean outdoor air temperature, month of the heating season, mean solar irradiance), Rough Set Theory (RST) was one of the best models, for which the evaluation rates were as follows: CV RMSE 21.6%, MAE 0.3 °C, MAPE 14.3%, MBE 3.1%, and R2 0.96. By including an additional variable (brine flow rate), Artificial Neural Networks (ANNs) achieved the most accurate predictions. They had the following evaluation rates: CV RMSE 4.6%, MAE 0.05 °C, MAPE 1.7%, MBE 0.4%, and R2 0.99. [ABSTRACT FROM AUTHOR]

Simple Summary: This study aimed to estimate body weight from various biometric measurements and features such as genotype (share of Suffolk and Polish Merino genotypes), birth weight (BiW), sex, birth type and body weight at 12 months of age (LBW) and some body measurements such as withers height (WH), sacrum height (SH), chest depth (CD), chest width (CW), chest circumference (CC), shoulder width (SW) and rump width (RW). Three hundred and forty-four animals were used in the study. Data mining and machine learning algorithms such as Random Forest Regression, Support Vector Regression and classification and regression tree were used to estimate the body weight from various features. Results show that the random forest procedure may help breeders improve characteristics of great importance. In this way, the breeders can get an elite population and determine which features are essential for estimating the body weight of the herd in Poland. The study's main goal was to compare several data mining and machine learning algorithms to estimate body weight based on body measurements at a different share of Polish Merino in the genotype of crossbreds (share of Suffolk and Polish Merino genotypes). The study estimated the capabilities of CART, support vector regression and random forest regression algorithms. To compare the estimation performances of the evaluated algorithms and determine the best model for estimating body weight, various body measurements and sex and birth type characteristics were assessed. Data from 344 sheep were used to estimate the body weights. The root means square error, standard deviation ratio, Pearson's correlation coefficient, mean absolute percentage error, coefficient of determination and Akaike's information criterion were used to assess the algorithms. A random forest regression algorithm may help breeders obtain a unique Polish Merino Suffolk cross population that would increase meat production. [ABSTRACT FROM AUTHOR]

Here, the capability of the Bat algorithm optimised extreme learning machines ELM (Bat‐ELM) is demonstrated for river water temperature (Tw) modelling in the Orda River, Poland. Results using the multilayer perceptron neural network (MLPNN), the classification and regression Tree (CART) and the multiple linear regression (MLR) models were presented for comparison. The models were developed according to two scenarios: (1) using air temperature (Ta) as input for predicting Tw, and (2) using Ta and the periodicity (i.e., day, month and year number). River Tw calibration and validation results derived from air temperature and the periodicity show its potential application. The Bat‐ELM accurately predicts the Tw and surpassed all other models with coefficient of correlation (R) values ranging within the limits of 0.973 to 0.981, and the Nash‐Sutcliffe efficiency (NSE) values will fall within the interval of 0.947 to 0.963. Findings from this research also highlight the robustness of the Bat‐ELM using the periodicity by enhancing its ability to estimate river Tw. [ABSTRACT FROM AUTHOR]

Motivation: the contemporary phenomenon of financial exclusion, in the sphere of its reasons, consequences and activities aimed at its reduction can be connected, e.g., with using new technologies and financial innovations. The new dimension of such exclusion is created by the digital financial exclusion developed through a diverse set of behavioral, environmental and demographic factors. Their identification and analysis has become an essential activity influencing, e.g., the effectiveness of selective choice and application of proper tools to reduce this exclusion. Aim: identification and assessment of the determinants related to digital financial exclusion as a barrier in the adoption of mobile banking services, considered from the perspective of their impact on the segmentation of the analysed population. Results: the ranking, identified by the authors, regarding the importance of predictors indicated that the dependent variable — Y (i.e. people who have an online bank account classified based on the mobile forms of its use) is most influenced by the generation factor — X4 (1.0), followed by: personal innovativeness — X2 (0.92), digital skills — X1 (0.90) and the perceived risks of new technologies — X3 (0.66). [ABSTRACT FROM AUTHOR]

The aim of the study was to evaluate the spectrum of AIDS-defining malignancies (ADMs) and non-AIDS-defining malignancies (NADMs) in HIV-infected patients in Poland. Material and methods: A retrospective observational study was conducted among HIV-infected adult patients who developed a malignancy between 1995 and 2012 in a Polish cohort. Malignancies were divided into ADMs and NADMs. Non-AIDS-defining malignancies were further categorised as virus-related (NADMs-VR) and unrelated (NADMs-VUR). Epidemiological data was analysed according to demographic data, medical history, and HIV-related information. Results were analysed by OR, EPITools package parameters and Fisher's exact test. Results: In this study 288 malignancies were discovered. The mean age at diagnosis was 41.25 years (IQR20-81); for ADMs 38.05 years, and for NADMs-VURs 46.42 years; 72.22% were male, 40.28% were co-infected with HCV. The risk behaviours were: 37.85% IDU, 33.33% MSM, and 24.31% heterosexual. Mean CD4+ at the diagnosis was 282 cells/mm³ (for ADMs 232 and for NADMs-VUR 395). Average duration of HIV infection at diagnosis was 5.69 years. There were 159 (55.2%) ADMs and 129 (44.8%) NADMs, among whom 58 (44.96%) NADMs-VR and 71 (55.04%) NADMs-VUR. The most frequent malignancies were: NHL (n = 76; 26.39%), KS (n = 49; 17.01%), ICC (n = 34; 11.81%), HD (n = 23; 7.99%), lung cancer (n = 18; 6.25%) and HCC (n = 14; 4.86%). The amount of NADMs, NADMs-VURs in particular, is increasing at present. Male gender (OR = 1.889; 95% CI: 1.104-3.233; p = = 0.024), advanced age: 50-60 years (OR = = 3.022; 95% CI: 1.359-6.720; p = 0.01) and = 60 years (OR = 15.111; 95% CI: 3.122-73.151; p < 0.001), longer duration of HIV-infection and successful HAART (OR = 2.769; 95% CI: 1.675-4.577; p = 0) were independent predictors of NADMs overall, respectively. Conclusions: In a Polish cohort NHL was the most frequent malignancy among ADMs, whereas HD was the most frequent among NADMs. Increased incidence of NADMs appearing in elderly men with longer duration of HIV-infection and with better virological and immunological control was confirmed. As HIV-infected individuals live longer, better screening strategies, especially for NADMs-VUR, are needed. The spectrum of cancer diagnoses in Poland currently does not appear dissimilar to that observed in other European populations. [ABSTRACT FROM AUTHOR]

Triticale is a promising food crop that combines the yield potential and grain quality of wheat with the disease and environmental tolerance of rye. The objective of this study was to evaluate the impact of genotype, environment and crop management on spring and winter triticale yield variability, using data from 31 locations across the whole of Poland, from 2009 to 2017, with the Classification and Regression Tree (CART) analysis. It was found that CART is able to detect differences in spring and winter triticale successful growth. The yield variability of spring triticale was more dependent on the soil quality than winter triticale because of a shorter cycle duration, which increases sensitivity to nutrient supply and weather conditions. Spring triticale also needs to be sown as soon as possible to ensure a successful establishment. A strong dependence of yield variability on the availability of water for the winter triticale was observed. When growing winter triticale in Poland, with periodic excess water especially during autumn and early spring, the use of fungicides and growth regulators should be taken into account. [ABSTRACT FROM AUTHOR]

In this study, a statistical model, combining principal components analysis (PCA), stepwise-canonical discriminant analysis (stepwise-CDA), classification and regression tree (CART), partial least squares-discriminant analysis (PLS-DA) and an innovative multidimensional analysis (MDA), was build up to predict the geographical origin of edible porcini (Boletus sect. Boletus). To this purpose, the elemental signatures of 180 commercial and manually harvested samples from different Italian production areas, China and Poland, were chemometrically elaborated. PCA differentiated Italian products from Chinese and Polish mushrooms. Based on the fusion of PCA and hierarchical cluster analysis (HCA), MDA identified elements such as Na, Mn, Fe, Cu and Cd as powerful discriminating variables. Finally, highly accurate and trained stepwise-CDA, CART and PLS-DA models, were able to predict the geographical origin of a survey of commercial porcini, through few metals (Mg, Mn, and Fe). The provenance reported on the labelling of these products was confirmed. Nevertheless, both models revealed that a commercial sample, with a claimed Italian origin, consisted of Chinese mushrooms. Overall, the combination of standard and innovative chemometric techniques demonstrated to support a reliable authentication of the geographical origin of porcini, thus, protecting the Italian production from fraud. • A traceability system for protecting the Italian porcino was built up. • Porcini from China, Poland and Italy, including PGI mushrooms, were considered. • Samples were screened by ICP-MS and elaborated by multivariate statistics. • A restricted pool of traceability markers was determined. • The traceability model was applied on commercial porcini to reveal potential fraud. [ABSTRACT FROM AUTHOR]

Objectives: The use of effective combinated antiretroviral therapy has significantly improved the prognosis of patients with HIV infection. Although current antiretroviral regimens are very effective in inhibiting viral replication, its elimination is not a viable goal of treatment. Despite cART, non–AIDS-defining bacterial infections are still a serious problem. The spectrum of these infections, and in particular the proportion of particular bacterial pathogens, is not sufficiently described in the scientific literature., Methods: In the study, HIV-infected patients followed at the HIV Out-Patient Clinic in Warsaw were registered in the clinic from 1 January 2007 to 31 July 2016. Survival analysis included 558 patients who met the study criteria., Results: Among 251 (44.9%) of those with positive culture, the most common bacterial pathogen was Staphylococcus aureus (33%) and Escherichia coli (11.1%). The most common bacteria in the upper respiratory tract was Staphylococcus aureus (26.6%). In urine cultures the most common bacteria was Escherichia coli (9.5%). Staphylococcus aureus (2.3%) and Staphylococcus epidermidis (2.3%) were the most common bacterial cultures in the wound. In skin cultures the most common bacteria was Staphylococcus aureus (3.9%). The highest number of positive cultures was obtained from the upper respiratory tract -166 (66.1%)., Conclusion: Non–AIDS-defining bacterial infections are a common clinical problem in HIV-infected patients despite the introduction of antiretroviral therapy and the pathogens that cause these infections are a very diverse group., (© National Institute of Public Health – National Institute of Hygiene)