Ensemble Performance Research Articles

Decision Tree Ensembles to Predict Coronavirus Disease 2019 Infection: A Comparative Study

The coronavirus disease 2019 (Covid-19) pandemic has affected most countries of the world. The detection of Covid-19 positive cases is an important step to fight the pandemic and save human lives. The polymerase chain reaction test is the most used method to detect Covid-19 positive cases. Various molecular methods and serological methods have also been explored to detect Covid-19 positive cases. Machine learning algorithms have been applied to various kinds of datasets to predict Covid-19 positive cases. The machine learning algorithms were applied on a Covid-19 dataset based on commonly taken laboratory tests to predict Covid-19 positive cases. These types of datasets are easy to collect. The paper investigates the application of decision tree ensembles which are accurate and robust to the selection of parameters. As there is an imbalance between the number of positive cases and the number of negative cases, decision tree ensembles developed for imbalanced datasets are applied. F-measure, precision, recall, area under the precision-recall curve, and area under the receiver operating characteristic curve are used to compare different decision tree ensembles. Different performance measures suggest that decision tree ensembles developed for imbalanced datasets perform better. Results also suggest that including age as a variable can improve the performance of various ensembles of decision trees.

Open-Source Neural Architecture Search with Ensemble and Pre-trained Networks

The training and optimization of neural networks, using pre-trained, super learner and ensemble approaches is explored. Neural networks, and in particular Convolutional Neural Networks (CNNs), are often optimized using default parameters. Neural Architecture Search (NAS) enables multiple architectures to be evaluated prior to selection of the optimal architecture. Our contribution is to develop, and make available to the community, a system that integrates open source tools for the neural architecture search (OpenNAS) of image classification models. OpenNAS takes any dataset of grayscale, or RGB images, and generates the optimal CNN architecture. Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO) and pre-trained models serve as base learners for ensembles. Meta learner algorithms are subsequently applied to these base learners and the ensemble performance on image classification problems is evaluated. Our results show that a stacked generalization ensemble of heterogeneous models is the most effective approach to image classification within OpenNAS.

The role of Russian pianists in the formation of accompaniment art

The Russian tradition of piano performance has been winning international recognition for several centuries. The names of S.V. Rachmaninoff, S.T. Richter, K.N. Igumnov, A.B. Goldenweiser and others, are inscribed in the history of the piano music and pedagogics. At the same time, such a sphere as accompaniment remains unheralded. The author of the research attempts to estimate the role of the above mentioned pianists in the formation of accompaniment art. Based on the analysis of the experience of performance and pedagogical work of the pianists, the author reveals their importance for the development of the Russian accompaniment tradition. This topic hasn’t been critically considered and analyzed. However, the history of piano music is rich in examples when concert pianists take on the role of accompanists. Their contribution to the practice of ensemble performance has influenced the development of accompaniment art. The work of S.V. Rachmaninoff, S.T. Richter, K.N. Igumnov, and A.B. Goldenweiser has influenced various aspects of accompaniment art: the extension of functions of an accompanist; the importance of the role of an accompanist in the interpretation of music pieces; the extension of the pedagogical function of an accompanist in the ensemble; the formation of a methodological background based on the accompaniment experience.   

Moving QoE for monitoring DASH video streaming: models and a study of multiple mobile clients

Objective Quality of Experience (QoE) for Dynamic Adaptive Streaming over HTTP (DASH) video streaming has received considerable attention in recent years. While there are a number of objective QoE models, a limitation of the current models is that the QoE is provided after the entire video is delivered; also, the models are on a per client basis. For content service providers, QoE observed is important to monitor to understand ensemble performance during streaming such as for live events or concurrent streaming when multiple clients are streaming. For this purpose, we propose Moving QoE (MQoE, in short) models to measure QoE during periodically during video streaming for multiple simultaneous clients. Our first model MQoE_RF is a nonlinear model considering the bitrate gain and sensitivity from bitrate switching frequency. Our second model MQoE_SD is a linear model that focuses on capturing the standard deviation in the bitrate switching magnitude among segments along with the bitrate gain. We then study the effectiveness of both models in a multi-user mobile client environment, with the mobility patterns being based on traces from a train, a car, or a ferry. We implemented the study on the GENI testbed. Our study shows that our MQoE models are more accurate in capturing the QoE behavior during transmission than static QoE models. Furthermore, our MQoE_RF model captures the sensitivity due to bitrate switching frequency more effectively while MQoE_SD captures the sensitivity due to the magnitude of the bitrate switching. Either models are suitable for content service providers for monitoring video streaming based on their preference.

A digital tool for prevention and management of cold weather injuries\u2014Cold Weather Ensemble Decision Aid (CoWEDA)

This paper describes a Cold Weather Ensemble Decision Aid (CoWEDA) that provides guidance for cold weather injury prevention, mission planning, and clothing selection. CoWEDA incorporates current science from the disciplines of physiology, meteorology, clothing, and computer modeling. The thermal performance of a cold weather ensemble is defined by endurance times, which are the time intervals from initial exposure until the safety limits are reached. These safety limits correspond to conservative temperature thresholds that provide a warning of the approaching onset of frostbite and/or hypothermia. A validated six-cylinder thermoregulatory model is used to predict human thermal responses to cold while wearing different ensembles. The performance metrics, model, and a database of clothing properties were integrated into a user-friendly software application. CoWEDA is the first tool that allows users to build their own ensembles from the clothing menu (i.e., jackets, footwear, and accessories) for each body region (i.e., head, torso, lower body, hands, feet) and view their selections in the context of physiological strain and the operational consequences. Comparison of predicted values to skin and core temperatures, measured during 17 cold exposures ranging from 0 to −40°C, indicated that the accuracy of CoWEDA prediction is acceptable, and most predictions are within measured mean ± SD. CoWEDA predicts the risk of frostbite and hypothermia and ensures that a selected clothing ensemble is appropriate for expected weather conditions and activities. CoWEDA represents a significant enhancement of required clothing insulation (IREQ, ISO 11079) and wind chill index-based guidance for cold weather safety and survival.

Blind methods to build choice-based ensembles

This paper aims at developing new models to combine the best of two paradigms: the performance of ensembles and the transparency of choice models. Specifically, the work explores several blind methods to build ensembles of single choice-based models. They were fit using a dataset that includes rational, emotional and attentional variables, all of them gathered from humans during a choice task. Two main strategies, 1-Learner and N-Learners type ensembles, were analyzed in terms of their accuracy as well as frequency of best-model metrics. The results point out the superior performance of N-Learners ensembles and show the potential of personalized arrangements.

Vom schmausenden zum andächtigen Studenten?

Abstract The texts in student song collections of the 17th century deal on the one hand with pleasures of student lives and on the other hand with common spiritual themes; many songs are intended for ensemble performance (e.g. the songs by E. Widmann). The practices in compiling manuscript collections (Johann Heckius, Christian Clodius, etc.) show how repertoires mix and adaptations and translations are created; the Clodius manuscript satirises learned topoi and the presentation of spiritual collections in its preface. Topoi in the texts and some examples of hymnbooks explicitly intended for students (Joachim Feller etc.) are discussed. Finally, in Michael Wiedemann’s Poetische Gefangenschafften, a literarisation of the different facets of student song practices can be observed.

Classification with ensembles and case study on functional magnetic resonance imaging

The ensemble is a technique that strategically combines basic models to achieve better accuracy rates. Diversity, combination methods, and selection topology are the main factors determining ensemble performance. Consequently, it is a challenging task to design an efficient ensemble scheme. Even though numerous paradigms have been proposed to classify ensemble schemes, there is still much room for improvement. This paper proposes a general framework for creating ensembles in the context of classification. Specifically, the ensemble framework consists of four stages: objectives, data preparing, model training, and model testing. It is comprehensive to design diverse ensembles. The proposed ensemble approach can be used for a wide variety of machine learning tasks. We validate our approach on real-world datasets. The experimental results show the efficiency of the proposed approach.

The Student Bayan and Accordion Orchestra at Kharkiv I. P. Kotlyarevsky National University of Arts: specifics of formation and professional development

Statement of the problem. The purpose of this article is to consider the evolution of the creative activity of the student training collective – the Orchestra of Bayans and Accordions – and to determine the role of its founder, Honored Artist of Ukraine, Professor Oleksandr Ivanovych Nazarenko, a conductor, an outstanding representative of the Ukrainian bayan art (second half of the 20th – early 21st centuries). Relevance and scientific novelty of the study. The team under his leadership has existed for over 28 years, it has achieved significant success and acquired its own creative form, and its activities attract the attention of the artistic community and arouse scientific interest, which determines the relevance of this topic. O. Nazarenko’s composer creativity were covered by Kharkiv bayan players and scientists Yu. Dyachenko (2012), M. Plushenko (2017), S. Ptashenko (2013), I. Snedkov (2016), A. Strilets (2018), but the authors did not address to consideration of O. Nazarenko’s activity as an orchestral conductor and the problems of performing skills of the orchestra of bayans and accordions at Kharkiv National University of Arts, the head of which he is. The research methodology is based on a set of historical, genre-style and interpretive approaches. A comprehensive analysis of the activities of the student orchestra and its leader O. Nazarenko allowed to identify certain stages of professional evolution and the main directions of team development. Particular attention is paid to the consideration of O. Nazarenko’s conducting activity and the principles of his work with a student orchestra composed of homogeneous instruments. Based on the analysis of the artist’s work, the issues of specifics of teaching methods, selection of quality repertoire, peculiarities of arrangement for orchestra of bayans and accordions are investigated. Results and conclusions of the study. O. Nazarenko’s multifaceted activity as the director and conductor of the Student Bayan-Accordion Orchestra is very important for preserving in the repertoire and updating works of foreign and Ukrainian, in particular, Kharkiv, composers, and his education of young professional musicians contributes to the development of the Ukrainian folk instrumental performing. Under the guidance of the master, students master a wide range of instrumental capabilities – a bright palette of stroke techniques and techniques of sound production, smooth bellows movement, develop their ideas about working on a piece of music and learn orchestral thinking. Thus, the main task of the Student Bayan and Accordion Orchestra at Kharkiv National University of Arts is to present a qualitative repertoire, master various orchestra arrangement techniques and peculiarities of filigree ensemble performance. For the first time, a complete repertoire list of the orchestra was compiled, which gives an idea of the scale and content of its activities, demonstrates the principles of selection of works that reflect the artistic taste and preferences of the conductor.

The importance of horizontal model resolution on simulated precipitation in Europe – from global to regional models

Abstract. Precipitation is a key climate variable that affects large parts of society, especially in situations with excess amounts. Climate change projections show an intensified hydrological cycle through changes in intensity, frequency, and duration of precipitation events. Still, due to the complexity of precipitation processes and their large variability in time and space, climate models struggle to represent precipitation accurately. This study investigates the simulated precipitation in Europe in available climate model ensembles that cover a range of horizontal model resolutions. The ensembles used are global climate models (GCMs) from CMIP5 and CMIP6 (∼100–300 km horizontal grid spacing at mid-latitudes), GCMs from the PRIMAVERA project at sparse (∼80–160 km) and dense (∼25–50 km) grid spacing, and CORDEX regional climate models (RCMs) at sparse (∼50 km) and dense (∼12.5 km) grid spacing. The aim is to seasonally and regionally over Europe investigate the differences between models and model ensembles in the representation of the precipitation distribution in its entirety and through analysis of selected standard precipitation indices. In addition, the model ensemble performances are compared to gridded observations from E-OBS. The impact of model resolution on simulated precipitation is evident. Overall, in all seasons and regions the largest differences between resolutions are seen for moderate and high precipitation rates, where the largest precipitation rates are seen in the RCMs with the highest resolution (i.e. CORDEX 12.5 km) and the smallest rates in the CMIP GCMs. However, when compared to E-OBS, the high-resolution models most often overestimate high-intensity precipitation amounts, especially the CORDEX 12.5 km resolution models. An additional comparison to a regional data set of high quality lends, on the other hand, more confidence to the high-resolution model results. The effect of resolution is larger for precipitation indices describing heavy precipitation (e.g. maximum 1 d precipitation) than for indices describing the large-scale atmospheric circulation (e.g. the number of precipitation days), especially in regions with complex topography and in summer when precipitation is predominantly caused by convective processes. Importantly, the systematic differences between low resolution and high resolution also remain when all data are regridded to common grids of 0.5∘×0.5∘ and 2∘×2∘ prior to analysis. This shows that the differences are effects of model physics and better resolved surface properties and not due to the different grids on which the analysis is performed. PRIMAVERA high resolution and CORDEX low resolution give similar results as they are of similar resolution. Within the PRIMAVERA and CORDEX ensembles, there are clear differences between the low- and high-resolution simulations. Once reaching ∼50 km the difference between different models is often larger than between the low- and high-resolution versions of the same model. For indices describing precipitation days and heavy precipitation, the difference between two models can be twice as large as the difference between two resolutions, in both the PRIMAVERA and CORDEX ensembles. Even though increasing resolution improves the simulated precipitation in comparison to observations, the inter-model variability is still large, particularly in summer when smaller-scale processes and interactions are more prevalent and model formulations (such as convective parameterisations) become more important.

MET-LDPC Code Ensembles of Low Code Rates With Exponentially Few Small Weight Codewords

This work studies the design of MET-LDPC code ensembles at low code rates with good threshold performances and exponentially few small weight codewords. There was a notable study on the condition, so called the ` t-value condition', for exponentially few small weight codewords. Meanwhile, it was shown that by introducing degree-one variable nodes, the threshold performances of MET-LDPC code ensembles of low rates can be significantly improved. However, the degree-one variable nodes may result in small weight codewords and thus must be carefully introduced to MET-LDPC code ensembles. Despite the importance, the existing t-value condition was developed only for MET-LDPC code ensembles without degree-one variable nodes. This work extends the t-value condition to MET-LDPC code ensembles with degree-one variable nodes, which includes the existing work as a special case. The extended t-value condition provides useful insights into the contributions of degree-one variable nodes to the distribution of small weight codewords. Thus, the results of this work allow us to design MET-LDPC code ensembles of low rates with both good threshold performances and exponentially few small weight codewords. In addition, it will be demonstrated that MET-LDPC codes at finite lengths based on the designed code ensembles have good error-rate performances both in the waterfall and low-error-rate regions.

CREATIVE STRATEGIES FOR THE GUITAR CLASS AT I. P. KOTLYAREVSKY KHNUA

Introduction. The guitar class, opened by V. Dotsenko in 1989, recently celebrated its 30th anniversary and presented the university with many winners of international competitions, ensemble groups and new scholarly discourses. Together with the constant changes in society’s requirements for academic education and musician’s activities, this encourages us to estimate its achievements and prospects at the present stage. The aim of the article is to identify the key vectors of the guitar class of Kharkiv National University of Arts at the present stage. In accordance with the goal, such methods are chosen as historical, which allows to reveal the dynamics of development of the Kharkiv guitar school in the period of its formation to the present; typological – to identify key areas of activity of the guitar class at the present stage. Results and Discussion. The study of the Kharkiv guitar school and guitar class of KhNUA from its formation to the present day allows us to identify the leading vectors and key features of their activities, among which it is proposed to distinguish two main ones: innovation and multivectority. Already at the stage of formation, the Kharkiv guitar school proved to be innovative – it was in Kharkiv where the first guitar club in Ukraine and the USSR was opened, within which the first guitar quartet in the USSR soon appeared, the first in Ukraine scholarly conference dedicated to guitar art, it was one of the first to join the digitalization process, conducting online performances and successfully presenting the guitar orchestra at the international level, resulting in two Grand Prix in 2020. Already within the activities of the guitar club, another leading feature of the Kharkiv guitar school – multivectority – has declared itself. Gathering like-minded people to share experiences and get acquainted with samples of modern guitar art, the club “nurtured” teachers, masters of instruments, and musicians-ensembles. All the directions initiated in the last century deepen and continue to branch out in the XXI century in the activities of the guitar class KhNUA: educational one is supplemented by scientific (conferences, defense of PhD theses), pedagogical one – by methodical complex (methodical works of V. Dotsenko), solo and ensemble performance – by the orchestra. Conclusions. Innovativeness and multivectority become leading features of the guitar class of KhNUA at the present stage. In recent years, the school’s activities are supplemented by such vectors as the formation of a guitar orchestra (2016), cooperation with European institutions of higher music education (Erasmus), active immersion in the digitalization process, in particular, online competitions and online broadcasts of the concerts, which fit its activity into the latest trends in the development of musical performance and education and shows the involvement in the European standards of artistic activity.

Threshold Computation for Spatially Coupled Turbo-Like Codes on the AWGN Channel.

In this paper, we perform a belief propagation (BP) decoding threshold analysis of spatially coupled (SC) turbo-like codes (TCs) (SC-TCs) on the additive white Gaussian noise (AWGN) channel. We review Monte-Carlo density evolution (MC-DE) and efficient prediction methods, which determine the BP thresholds of SC-TCs over the AWGN channel. We demonstrate that instead of performing time-consuming MC-DE computations, the BP threshold of SC-TCs over the AWGN channel can be predicted very efficiently from their binary erasure channel (BEC) thresholds. From threshold results, we conjecture that the similarity of MC-DE and predicted thresholds is related to the threshold saturation capability as well as capacity-approaching maximum a posteriori (MAP) performance of an SC-TC ensemble.

Spline-rule ensemble classifiers with structured sparsity regularization for interpretable customer churn modeling

An important business domain that relies heavily on advanced statistical- and machine learning algorithms to support operational decision-making is customer retention management. Customer churn prediction is a crucial tool to support customer retention. It allows an early identification of customers who are at risk to abandon the company and provides the ability to gain insights into why customers are at risk. Hence, customer churn prediction models should complement predictive performance with model insights. Inspired by their ability to reconcile strong predictive performance and interpretability, this study introduces rule ensembles and their extension, spline-rule ensembles, as a promising family of classification algorithms to the customer churn prediction domain. Spline-rule ensembles combine the flexibility of a tree-based ensemble classifier with the simplicity of regression analysis. They do, however, neglect the relatedness between potentially conflicting model components which can introduce unnecessary complexity in the models and compromises model interpretability. To tackle this issue, a novel algorithmic extension, spline-rule ensembles with sparse group lasso regularization (SRE-SGL) is proposed to enhance interpretability through structured regularization. Experiments on fourteen real-world customer churn data sets in different industries (i) demonstrate the superior predictive performance of spline-rule ensembles with sparse group lasso over a set well yet powerful benchmark methods in terms of AUC and top decile lift; (ii) show that spline-rule ensembles with sparse group lasso regularization significantly outperform conventional rule ensembles whilst performing at least as well as conventional spline-rule ensembles; and (iii) illustrate the interpretable nature of a spline-rule ensemble model and the advantage of structured regularization in SRE-SGL by means of a case study on customer churn prediction for a telecommunications company.

Evaluating the Performance of a WRF Physics Ensemble in Simulating Rainfall over Lao PDR during Wet and Dry Seasons

Dynamical downscaling of General Circulation Model (GCM) data for any region has been made possible due to a set of physics options and model dynamics within the Weather Research and Forecasting (WRF) model. This study evaluated the performance of an ensemble of physics options in simulating rainfall during wet and dry seasons of Lao PDR. The model evaluation criteria focused on identifying the optimum physics options for a range of scenarios. No single combination of physics options performed well in all scenarios reflecting the importance of using different parameterizations according to the geographic location and the intended application of the results. For the dry season, none of the ensemble members performed satisfactorily for the southern region of Lao PDR, while all the ensemble members performed well for the northern and central regions. While almost all the WRF simulations overestimated the rainfall during the wet season, BMJ for cumulus physics performed better in the northern and central regions, and KF performed better in the south region. The YSU scheme performed best as the planetary boundary layer for both wet and dry seasons, while WSM5 for the wet season and Lin for the dry season gave the best model performance as the microphysics option.

The International Workshop on Osteoarthritis Imaging Knee MRI Segmentation Challenge: A Multi-Institute Evaluation and Analysis Framework on a Standardized Dataset.

To organize a multi-institute knee MRI segmentation challenge for characterizing the semantic and clinical efficacy of automatic segmentation methods relevant for monitoring osteoarthritis progression. A dataset partition consisting of three-dimensional knee MRI from 88 retrospective patients at two time points (baseline and 1-year follow-up) with ground truth articular (femoral, tibial, and patellar) cartilage and meniscus segmentations was standardized. Challenge submissions and a majority-vote ensemble were evaluated against ground truth segmentations using Dice score, average symmetric surface distance, volumetric overlap error, and coefficient of variation on a holdout test set. Similarities in automated segmentations were measured using pairwise Dice coefficient correlations. Articular cartilage thickness was computed longitudinally and with scans. Correlation between thickness error and segmentation metrics was measured using the Pearson correlation coefficient. Two empirical upper bounds for ensemble performance were computed using combinations of model outputs that consolidated true positives and true negatives. Six teams (T 1-T 6) submitted entries for the challenge. No differences were observed across any segmentation metrics for any tissues (P = .99) among the four top-performing networks (T 2, T 3, T 4, T 6). Dice coefficient correlations between network pairs were high (> 0.85). Per-scan thickness errors were negligible among networks T 1-T 4 (P = .99), and longitudinal changes showed minimal bias (< 0.03 mm). Low correlations (ρ < 0.41) were observed between segmentation metrics and thickness error. The majority-vote ensemble was comparable to top-performing networks (P = .99). Empirical upper-bound performances were similar for both combinations (P = .99). Diverse networks learned to segment the knee similarly, where high segmentation accuracy did not correlate with cartilage thickness accuracy and voting ensembles did not exceed individual network performance.See also the commentary by Elhalawani and Mak in this issue.Keywords: Cartilage, Knee, MR-Imaging, Segmentation © RSNA, 2020Supplemental material is available for this article.

Effects of hip protective clothing on thermal wear comfort of clothing ensembles

PurposeThis paper aims to examine the influence of hip protective clothing on ensemble performance attributes related to thermal comfort. It also explores the effect on protective pads of various materials and the arrangements of material. The thermal comfort characteristics are thermal insulation and moisture vapour resistance.Design/methodology/approachFor this research, four ensembles of clothing were used: one ensemble without hip protective clothing and three ensembles with hip protective clothing. A thermal manikin was used to test the thermal insulation and moisture vapour resistance of the ensembles.FindingsThe findings revealed that incorporating hip protective clothing into the clothing ensembles influenced the thermal resistance and moisture vapour resistance of the ensemble. In the “all zones group,” the influence of the hip protective clothing depended on clothing style, with hipster-style clothing producing insignificant changes. In the “hip zones group” and “stomach and hip zones group,” hip protective clothing strongly influenced the thermal comfort attributes of ensembles. Pad material and volume play important roles in these changes in thermal comfort attributes.Originality/valueThese outcomes are useful for the design and engineering of hip protective clothing, where maximizing protection while minimizing thermal and moisture vapour resistance is critical for wear comfort and adherence in warm or hot conditions. The designer should consider that material, volume and thickness of protective pad affect the overall thermal comfort attributes of the hip protective clothing.

Climate change effects Management with the approach of the uncertainty of Atmosphere-Ocean General Circulation Models in Hamadan Province, Iran

INTRODUCTION: Since Iran is located in the semi-arid belt, it has faced such issues as drought, dust crisis, and intensified migration. The assessment of the effects of climate change includes identifying some key aspects of uncertainties used to estimate its impacts, such as uncertainties in the context of Atmosphere-Ocean General Circulation Models (AOGCMs): in regional-scale climatology, in statistical or dynamic downscaling methods, and parametric and structural uncertainties in different models. One of the most important sources of uncertainty in climate change is the use of different AOGCMs that produce different outputs for climate variables. METHODS: In this study, to investigate the uncertainty of AOGCM models, the downscaled data of the NASA Earth Exchange Global Daily Downscaled Projections dataset obtained from 21 AOGCMs with medium Representative Concentration Pathway4.5 scenario were downloaded from the NASA site for 81 cells in Hamadan Province, Iran. After the validation of the models, they were evaluated against the criteria of the coefficient of determination and model efficiency coefficient in comparison with the data of the Hamedan synoptic station in the statistical period of 1976-2005. To reduce the uncertainty of AOGCMs, the ensemble performance (EP) of models was used in Climate Data Operators software. FINDINGS: It was revealed that MRI-CGCM3, MPI-ESM-LR, BNU-ESM, ACCESS1-0, MIROC-ESM, MIROC-ESM-CHEM, and MPI-ESM-MR models had better performance than similar models. It was also found that IPSL-CM5A-LR, CNRM-CM5, CSIRO-Mk3-6-0, CESM1-BGC, and GFDL-ESM2M had the lowest correlation between observational and simulation data of mean monthly precipitation. CONCLUSION: According to the results, this method could provide a good estimate in the base period (1976-2005), compared to the data of the Hamedan synoptic station, and was more accurate compared to the single implementation method of each AOGCM model. The results of EP of models in the future period (2020-2049) showed that precipitation will not change considerably in the future and will increase by 0.23 mm. In addition, the average, maximum, and minimum annual temperatures will increase by 1.54°C, 1.7°C, and 1.40°C, respectively.

On Talent Training and Cultural Development of Saxophone under Network Technology

Saxophone as a kind of musical instrument is unique in shape, playing method, playing skill, timbre and keeping way. The continuous development of network technology provides more possibilities for talent training, and popularizes Saxophone teaching, which can increase the choice of musical instruments for music lovers. Saxophone can further strengthen the performance of ensemble in group performance. This paper studies the relationship between talent training and cultural development of saxophone under the background of network technology, and deeply studies its important value in cultural shaping. After that, it explores how to popularize Saxophone more effectively and how to promote cultural production.

FOLKLORE, DANCE IN THE CONTEXT OF MODELING IDEOLOGICAL MESSAGES

Studying Macedonian culture, we can not help noticing the particular role of folklore ensembles in fostering traditional music and dances, with a view to cherishing the national characteristics. This process is directed by the highest political bodies, which have disseminated the idea in a few spheres. Firstly, by means of actualization of certain matrices in the national folk ensemble Tanec, which was the benchmark followed by amateur ensembles. On the other hand, state television and radio MRTV, started broadcasting performances of folk music ensembles and programs with specific contents, i.e. where folklore prevailed. Analyzing the situation with the folk dance ensemble Tanec, we can notice that its Statute, as well as its first director Mr Manuel Chuchkov (senior political official) emphasized application, promotion and actualization of folklore in the context of socio-ideological engagement. Several papers written by Chuchkov, consider the usage of folk dances by placing them in historical and ideological contents. Such are the examples of folk dances from this period, into which drama elements are imputed, giving the dances specific historical features and being supposed to encourage patriotic feelings. Folklore used to be used as a tool in the socialist period, but it is still being actualized, in Macedonia nowadays.