Ensemble Performance Research Articles

Passing the Baton: Building Student Autonomy and Democracy in the Large Ensemble Setting

The purpose of this study was to explore the phenomena of participation in a democratic large ensemble experience in a secondary public school setting. Specific research questions included (a) Do high school band students feel capable of performing a music work without teacher intervention? (b) In what ways do high school band students describe the experience of performing in a student-led large ensemble? (c) What music decisions were most often made by high school band students in a student-led large ensemble? and (d) Were there any changes in high school students’ perceptions of autonomy following a student-led large ensemble music rehearsal and performance experience? Findings illustrated that the democratic experience increased student autonomy and music discrimination across larger distances in the classroom as students listened to other nonsimilar sections. Furthermore, student voice, self-efficacy, and personal affect also increased as a result of the experience. Students felt empowered to offer their rehearsal critiques; however, a lingering concern is that participants continued to feel that their peers would not listen to their opinions on rehearsal issues or strategy usage.

A new method for ensemble combination based on adaptive decision making

Ensemble classifiers methods are considered as one of the strongest classification approaches in different applications. A key factor in creating a successful ensemble is to design an optimal combiner that minimizes classification errors. Unfortunately, finding the best fusion methodology that maximizes ensemble performance is a challenge. Most popular ensemble classifiers systems use fixed fusion methods such as average and majority voting. For a given application, there is no clear understanding of why a fusion method might work better than other methods. In this work, decision-making based on Adaptive Power Mean Combiner (APMC) is investigated. A mathematical and experimental framework for ensemble classifier systems based on APMC is proposed. The theoretical results explain why a given algebraic combiner such as average, product, maximum, minimum, and others works best for a given dataset while providing poor results on other datasets. It was shown that selecting an optimal fusion method is strongly dependent on the statistics of base learners’ outputs. Theoretical results for a given ensemble condition show that an improvement in classification accuracy of ∼8% compared to the average fusion method is achieved. Guided by theoretical results, we propose an experimental ensemble-learning algorithm based on surrogate optimization method for searching fusion methods for a given ensemble condition. The performance trend predicted by the mathematical model is validated through several datasets and compared against different fusion methods. Experimental results show the proposed algorithm achieves notable classification results compared to several fusion methods.

Temporal Coordination in Piano Duet Networked Music Performance (NMP): Interactions Between Acoustic Transmission Latency and Musical Role Asymmetries

Today’s audio, visual, and internet technologies allow people to interact despite physical distances, for casual conversation, group workouts, or musical performance. Musical ensemble performance is unique because interaction integrity critically depends on the timing between each performer’s actions and when their acoustic outcomes arrive. Acoustic transmission latency (ATL) between players is substantially longer for networked music performance (NMP) compared to traditional in-person spaces where musicians can easily adapt. Previous work has shown that longer ATLs slow the average tempo in ensemble performance, and that asymmetric co-actor roles and empathy-related traits affect coordination patterns in joint action. Thus, we are interested in how musicians collectively adapt to a given latency and how such adaptation patterns vary with their task-related and person-related asymmetries. Here, we examined how two pianists performed duets while hearing each other’s auditory outcomes with an ATL of 10, 20, or 40 ms. To test the hypotheses regarding task-related asymmetries, we designed duets such that pianists had: (1) a starting or joining role and (2) a similar or dissimilar musical part compared to their co-performer, with respect to pitch range and melodic contour. Results replicated previous clapping-duet findings showing that longer ATLs are associated with greater temporal asynchrony between partners and increased average tempo slowing. While co-performer asynchronies were not affected by performer role or part similarity, at the longer ATLs starting performers displayed slower tempos and smaller tempo variability than joining performers. This asymmetry of stability vs. flexibility between starters and joiners may sustain coordination, consistent with recent joint action findings. Our data also suggest that relative independence in musical parts may mitigate ATL-related challenges. Additionally, there may be a relationship between co-performer differences in empathy-related personality traits such as locus of control and coordination during performance under the influence of ATL. Incorporating the emergent coordinative dynamics between performers could help further innovation of music technologies and composition techniques for NMP.

Closing the Performance Gap between Siamese Networks for Dissimilarity Image Classification and Convolutional Neural Networks.

In this paper, we examine two strategies for boosting the performance of ensembles of Siamese networks (SNNs) for image classification using two loss functions (Triplet and Binary Cross Entropy) and two methods for building the dissimilarity spaces (FULLY and DEEPER). With FULLY, the distance between a pattern and a prototype is calculated by comparing two images using the fully connected layer of the Siamese network. With DEEPER, each pattern is described using a deeper layer combined with dimensionality reduction. The basic design of the SNNs takes advantage of supervised k-means clustering for building the dissimilarity spaces that train a set of support vector machines, which are then combined by sum rule for a final decision. The robustness and versatility of this approach are demonstrated on several cross-domain image data sets, including a portrait data set, two bioimage and two animal vocalization data sets. Results show that the strategies employed in this work to increase the performance of dissimilarity image classification using SNN are closing the gap with standalone CNNs. Moreover, when our best system is combined with an ensemble of CNNs, the resulting performance is superior to an ensemble of CNNs, demonstrating that our new strategy is extracting additional information.

Improving the performance of bagging ensembles for data streams through mini-batching

Often, machine learning applications have to cope with dynamic environments where data are collected in the form of continuous data streams with potentially infinite length and transient behavior. Compared to traditional (batch) data mining, stream processing algorithms have additional requirements regarding computational resources and adaptability to data evolution. They must process instances incrementally because the data’s continuous flow prohibits storing data for multiple passes. Ensemble learning achieved remarkable predictive performance in this scenario. Implemented as a set of (several) individual classifiers, ensembles are naturally amendable for task parallelism. However, the incremental learning and dynamic data structures used to capture the concept drift increase the cache misses and hinder the benefit of parallelism. This paper proposes a mini-batching strategy that can improve memory access locality and performance of several ensemble algorithms for stream mining in multi-core environments. With the aid of a formal framework, we demonstrate that mini-batching can significantly decrease the reuse distance (and the number of cache misses). Experiments on six different state-of-the-art ensemble algorithms applying four benchmark datasets with varied characteristics show speedups of up to 5X on 8-core processors. These benefits come at the expense of a small reduction in predictive performance.

Prediction of hand-wrist maturation stages based on cervical vertebrae images using artificial intelligence.

To predict the hand-wrist maturation stages based on the cervical vertebrae (CV) images, and to analyse the accuracy of the proposed algorithms. A total of 499 pairs of hand-wrist radiographs and lateral cephalograms of 455 orthodontic patients aged 6-18years were used for developing the prediction model for hand-wrist skeletal maturation stages. The hand-wrist radiographs and the lateral cephalograms were collected from two university hospitals and a paediatric dental clinic. After identifying the 13 anatomic landmarks of the CV, the width-height ratio, width-perpendicular height ratio and concavity ratio of the CV were used as the morphometric features of the CV. Patients' chronological age and sex were also included as input data. The ground truth data were the Fishman SMI based on the hand-wrist radiographs. Three specialists determined the ground truth SMI. An ensemble machine learning methods were used to predict the Fishman SMI. Five-fold cross-validation was performed. The mean absolute error (MAE), round MAE and root mean square error (RMSE) values were used to assess the performance of the final ensemble model. The final ensemble model consisted of eight machine learning models. The MAE, round MAE and RMSE were 0.90, 0.87 and 1.20, respectively. Prediction of hand-wrist SMI based on CV images is possible using machine learning methods. Chronological age and sex increased the prediction accuracy. An automated diagnosis of the skeletal maturation may aid as a decision-supporting tool for evaluating the optimal treatment timing for growing patients.

Artistic and conceptual tasks of a musician in solo and ensemble performance

The relevance of this study is justified by the necessity to investigate the tasks for the improvement of musician’s professional skills. Artistic perception of the surrounding world is based on active artistic and conceptual thinking. The purpose of this study is to define artistic and conceptual tasks of a musician. In addition, the primary purpose of this research is to consider and analyze the tasks of a performing musician. The methodological background of this study is shaped by theoretical methods of scientific knowledge. For this, the study involved such research methods as analysis and synthesis of information, as well as analytical, cultural and comparative methods. The first stage of the study was a theoretical analysis of academic literature. For the sake of this study, the types of musical performances and interpretations of works as well as the main tasks of the performing musician were considered. It was determined that musical performance is a form of art that involves the reproduction of music in a variety of ways. As a result, it was established that the task of a musician is to decipher the emotional and sensual image created by the author of the work.

Современное состояние и перспективы вузовского обучения по классу ансамбля духовых инструментов в Китае

Ensemble playing is an important component of band performance, but the Chinese higher school pays insufficient attention to this academic discipline, which is not in tune with requirements of modern ensemble orchestra performance. The research objective is as follows: to improve ensemble training, to reach a new level of ensemble music education. The author identifies specificity of ensemble training in China, summarizes poorly investigated organizational problems, which constitutes scientific originality of the study. As a result, the researcher determines the basic trends in educational process optimization: consolidation and extension of ensemble performance skills, stage-by-stage training, repertoire optimization and rehearsal activity focus on preparing for concert performance.

An ensemble soft weighted gene selection-based approach and cancer classification using modified metaheuristic learning

Abstract Hybrid algorithms are effective methods for solving optimization problems that rarely have been used in the gene selection procedure. This paper introduces a novel modified model for microarray data classification using an optimized gene subset selection method. The proposed approach consists of ensemble feature selection based on wrapper methods using five criteria, which reduces the data dimensions and time complexity. Five feature ranking procedures, including receiver operating characteristic curve, two-sample T-test, Wilcoxon, Bhattacharyya distance, and entropy, are used in the soft weighting method. Besides, we proposed a classification method that used the support vector machine (SVM) and metaheuristic algorithm. The optimization of the SVM hyper-parameters for the radial basis function (RBF) kernel function is performed using a modified Water Cycle Algorithm (mWCA). The results indicate that the ensemble performance of genes-mWCA SVM (EGmWS) is considered an efficient method compared to similar approaches in terms of accuracy and solving the uncertainty problem. Five benchmark microarray datasets, including leukemia, MicroRNA-Breast, diffuse large B-cell lymphoma, prostate, and colon, are employed for experiments. The highest and lowest numbers of genes are related to prostate with 12 533 genes and MicroRNA-Breast with 1926 genes, respectively. Besides, the highest and lowest numbers of samples are MicroRNA-Breast with 132 samples and colon with 62 samples, respectively. The results of classifying all data by applying effective genes of the EF-WS yielded high accuracies in microarray data classification. In addition to the robustness and simplicity of the proposed method, the model’s generalizability is another crucial aspect of the method that can be further developed to increase the accuracy while reducing classification error.

Collaborating in Isolation: Assessing the Effects of the Covid-19 Pandemic on Patterns of Collaborative Behavior Among Working Musicians

The Covid-19 pandemic severely limited collaboration among musicians in rehearsal and ensemble performance, and demanded radical shifts in collaborative practices. Understanding the nature of these changes in music creators' patterns of collaboration, as well as how musicians shifted prioritizations and adapted their use of the available technologies, can offer invaluable insights into the resilience and importance of different aspects of musical collaboration. In addition, assessing changes in the collaboration networks among music creators can improve the current understanding of genre and style formation and evolution. We used an internet survey distributed to music creators, including performers, composers, producers, and engineers, all active before and during the pandemic, to assess their perceptions of how their music, collaborative practice, and use of technology were impacted by shelter-in-place orders associated with Covid-19, as well as how they adapted over the course of the pandemic. This survey was followed by Zoom interviews with a subset of participants. Along with confirming previous results showing increased reliance on nostalgia for musical inspiration, we found that participants' collaborative behaviors were surprisingly resilient to pandemic-related changes. In addition, participant responses appeared to be driven by a relatively small number of underlying factors, representing approaches to musical collaboration such as musical extroversion or musical introversion, inspiration clusters such as activist musicking, and style or genre clusters.

Perturbing Topography in a Convection‐Allowing Ensemble Prediction System for Heavy Rain Forecasts

AbstractFour methods to perturb model terrain are demonstrated in a convection‐allowing scale (3 km) ensemble prediction system (EPS) for heavy rain forecasts. The impact of methods was examined in terms of ensemble mean, spread‐skill relationship and probabilistic forecast. The study was carried out for four major precipitation events. It is found that: (a) using different combinations of topography smoothing and interpolation is a promising way to perturb model topography. Even perturbing the topography alone can greatly improve heavy rain forecasts. The benefit of ensemble forecasts increases with the increase in rainfall amount. (b) Adding random perturbations to model topography is not ideal and could hurt ensemble performance due to a too noisy structure although it increases ensemble spread. Perturbation structure plays a more important role than perturbation size. (c) Using the terrain difference between a higher and lower resolution model to estimate possible errors in model terrain is explored. By adding such terrain differences to the terrain‐generating‐scheme based perturbation (the control experiment) can not only enlarge perturbation size but also keep a good spatial structure. Such a modified ensemble performed similarly in ensemble mean forecasts but improved the ensemble spread and probabilistic forecast. It is recommended that perturbed model terrain should be included in operational EPSs to improve heavy precipitation forecasts. The simple terrain‐generating‐scheme based perturbation method, as described in this study, is effective and can be implemented in an existing operational EPS without extra computing cost.

Collaborative learning experiences in the university jazz/creative music ensemble: Student perspectives on instructional communication

While the ensemble is a ubiquitous learning environment within jazz education, opportunities to learn through engagement in ensemble performances and industry-level recording opportunities are rare classroom environments tertiary jazz music institutions offer. This qualitative study examines jazz performance contexts within an Australian tertiary music course, exploring students’ learning experience spanning three diverse collaborative projects across nine months. Phenomenological analysis explores the instructional relationship outlining connection between the student and instruction, the subject matter that is taught, and the connection between the student and the teacher as master improviser. Findings outline substantive teacher crafting of learning, relationship building and learning experiences garnered from interpersonal learning relationships, and the application of content with pedagogy that aims to build a positive learning climate between improvising teachers and their students. The author contends that a phenomenological perspective can highlight this diversity and emphasize effective interpersonal strategies and ensemble pedagogies that enhance student learning and potentially enculturate richer and more sophisticated musicianship in students and their developing creative abilities.

Oropharyngeal cancer patient stratification using random forest based-learning over high-dimensional radiomic features

To improve risk prediction for oropharyngeal cancer (OPC) patients using cluster analysis on the radiomic features extracted from pre-treatment Computed Tomography (CT) scans. 553 OPC Patients randomly split into training (80%) and validation (20%), were classified into 2 or 3 risk groups by applying hierarchical clustering over the co-occurrence matrix obtained from a random survival forest (RSF) trained over 301 radiomic features. The cluster label was included together with other clinical data to train an ensemble model using five predictive models (Cox, random forest, RSF, logistic regression, and logistic-elastic net). Ensemble performance was evaluated over the independent test set for both recurrence free survival (RFS) and overall survival (OS). The Kaplan–Meier curves for OS stratified by cluster label show significant differences for both training and testing (p val < 0.0001). When compared to the models trained using clinical data only, the inclusion of the cluster label improves AUC test performance from .62 to .79 and from .66 to .80 for OS and RFS, respectively. The extraction of a single feature, namely a cluster label, to represent the high-dimensional radiomic feature space reduces the dimensionality and sparsity of the data. Moreover, inclusion of the cluster label improves model performance compared to clinical data only and offers comparable performance to the models including raw radiomic features.

Forecasting Particulate Pollution in an Urban Area: From Copernicus to Sub-Km Scale

Particulate air pollution has aggravated cardiovascular and lung diseases. Accurate and constant air quality forecasting on a local scale facilitates the control of air pollution and the design of effective strategies to limit air pollutant emissions. CAMS provides 4-day-ahead regional (EU) forecasts in a 10 km spatial resolution, adding value to the Copernicus EO and delivering open-access consistent air quality forecasts. In this work, we evaluate the CAMS PM forecasts at a local scale against in-situ measurements, spanning 2 years, obtained from a network of stations located in an urban coastal Mediterranean city in Greece. Moreover, we investigate the potential of modelling techniques to accurately forecast the spatiotemporal pattern of particulate pollution using only open data from CAMS and calibrated low-cost sensors. Specifically, we compare the performance of the Analog Ensemble (AnEn) technique and the Long Short-Term Memory (LSTM) network in forecasting PM2.5 and PM10 concentrations for the next four days, at 6 h increments, at a station level. The results show an underestimation of PM2.5 and PM10 concentrations by a factor of 2 in CAMS forecasts during winter, indicating a misrepresentation of anthropogenic particulate emissions such as wood-burning, while overestimation is evident for the other seasons. Both AnEn and LSTM models provide bias-calibrated forecasts and capture adequately the spatial and temporal variations of the ground-level observations reducing the RMSE of CAMS by roughly 50% for PM2.5 and 60% for PM10. AnEn marginally outperforms the LSTM using annual verification statistics. The most profound difference in the predictive skill of the models occurs in winter, when PM is elevated, where AnEn is significantly more efficient. Moreover, the predictive skill of AnEn degrades more slowly as the forecast interval increases. Both AnEn and LSTM techniques are proven to be reliable tools for air pollution forecasting, and they could be used in other regions with small modifications.

Software effort estimation accuracy prediction of machine learning techniques: A systematic performance evaluation

AbstractSoftware effort estimation accuracy is a key factor in effective planning, controlling, and delivering a successful software project within budget and schedule. The overestimation and underestimation both are the key challenges for future software development, henceforth there is a continuous need for accuracy in software effort estimation. The researchers and practitioners are striving to identify which machine learning estimation technique gives more accurate results based on evaluation measures, datasets and other relevant attributes. The authors of related research are generally not aware of previously published results of machine learning effort estimation techniques. The main aim of this study is to assist the researchers to know which machine learning technique yields the promising effort estimation accuracy prediction in software development. In this article, the performance of the machine learning ensemble and solo techniques are investigated on publicly and non‐publicly domain datasets based on the two most commonly used accuracy evaluation metrics. We used the systematic literature review methodology proposed by Kitchenham and Charters. This includes searching for the most relevant papers, applying quality assessment (QA) criteria, extracting data, and drawing results. We have evaluated a state‐of‐the‐art accuracy performance of 35 selected studies (17 ensemble, 18 solo) using mean magnitude of relative error and PRED (25) as a set of reliable accuracy metrics for performance evaluation of accuracy among two techniques to report the research questions stated in this study. We found that machine learning techniques are the most frequently implemented in the construction of ensemble effort estimation (EEE) techniques. The results of this study revealed that the EEE techniques usually yield a promising estimation accuracy than the solo techniques.

Comparison of CMIP6 and CMIP5 models in simulating mean and extreme precipitation over East Africa

AbstractThis study examines the improvement in Coupled Model Intercomparison Project Phase Six (CMIP6) models against the predecessor CMIP5 in simulating mean and extreme precipitation over the East Africa region. The study compares the climatology of the precipitation indices simulated by the CMIP models with the CHIRPS data set using robust statistical techniques for 1981–2005. The results display the varying performance of the general circulation models (GCMs) in the simulation of annual and seasonal precipitation climatology over the study domain. CMIP6 multi‐model ensemble mean (hereafter MME) shows improved performance in the local annual mean cycle simulation with a better representation of the rainfall within the two peaks, especially the MAM rainfall relative to their predecessor. Moreover, simulation of extreme indices is well captured in CMIP6 models relative to CMIP5. The CMIP6‐MME performed better than the CMIP5‐MME with lesser biases in simulating Simple Daily Intensity Index (SDII), consecutive dry days (CDD), and very heavy precipitation days &gt;20 mm (R20mm) over East Africa. Remarkably, most CMIP6 models are unable to simulate extremely wet days (R95p). Some CMIP6 models (e.g., NorESM2‐MM and CNRM‐CM6‐1) depict robust performance in reproducing the observed indices across all analyses. OND season shows wet biases for some indices (i.e., R95p, PRCPTOT), except for SDII, CDD, and R20mm in CMIP6 models. Consistent with other studies, the mean ensemble performance for both CMIP5/6 shows better performance as compared with individual models due to the cancellation of some systematic errors in the individual models. Generally, CMIP6 depicts improved performance in the simulation of MAM rainfall compared with CMIP5 models. However, the new model generation is still marred by uncertainty, thereby depicting unsatisfactory performance over the East Africa domain. This calls for further investigation into the sources of persistent systematic biases and a methodology for identifying individual models with robust features that can accurately simulate observed patterns for future usage.

Assessment of CMIP6 Performance and Projected Temperature and Precipitation Changes Over South America

We evaluate the performance of a large ensemble of Global Climate Models (GCMs) from the Coupled Model Intercomparison Project Phase 6 (CMIP6) over South America for a recent past reference period and examine their projections of twenty-first century precipitation and temperature changes. The future changes are computed for two time slices (2040–2059 and 2080–2099) relative to the reference period (1995–2014) under four Shared Socioeconomic Pathways (SSPs, SSP1–2.6, SSP2–4.5, SSP3–7.0 and SSP5–8.5). The CMIP6 GCMs successfully capture the main climate characteristics across South America. However, they exhibit varying skill in the spatiotemporal distribution of precipitation and temperature at the sub-regional scale, particularly over high latitudes and altitudes. Future precipitation exhibits a decrease over the east of the northern Andes in tropical South America and the southern Andes in Chile and Amazonia, and an increase over southeastern South America and the northern Andes—a result generally consistent with earlier CMIP (3 and 5) projections. However, most of these changes remain within the range of variability of the reference period. In contrast, temperature increases are robust in terms of magnitude even under the SSP1–2.6. Future changes mostly progress monotonically from the weakest to the strongest forcing scenario, and from the mid-century to late-century projection period. There is an increase in the seasonality of the intra-annual precipitation distribution, as the wetter part of the year contributes relatively more to the annual total. Furthermore, an increasingly heavy-tailed precipitation distribution and a rightward shifted temperature distribution provide strong indications of a more intense hydrological cycle as greenhouse gas emissions increase. The relative distance of an individual GCM from the ensemble mean does not substantially vary across different scenarios. We found no clear systematic linkage between model spread about the mean in the reference period and the magnitude of simulated sub-regional climate change in the future period. Overall, these results could be useful for regional climate change impact assessments across South America.

Broken Automatons and Barbed Ecologies in Ligia Lewis's Choreographic Imaginary

AbstractThis article considers choreographer Ligia Lewis's hour-long ensemble performance Water Will (in Melody) to theorize on the relationship between ecological fugitivity and black fugitive movement. It explores how Lewis's choreography disrupts the colonial space-times of colonialism and slavery by offering portals into other space-times. In Water Will (in Melody), racialized assemblages break down from overuse and from glaring surveillance in the form of illumination. The last few minutes of the piece evoke an ambivalent postapocalyptic space-time where darkness becomes textured with what seems to be moonlight peeking into a wet cave. This ending evokes the ecological of histories of fugitivity and the earthiness of Édouard Glissant's concept of opacity, both frequently overlooked in discussions of black fugitivity. The final section traces Lewis's fugitive choreography into what the article calls the barbed ecologies of the hills of the Dominican Republic and Haiti, sites of black and indigenous marronage and symbiosis.

VIA “Chervona Ruta” in the context of variety- ensemble performance of Ukraine

The aim of the article is to clarify the artistic role of the ensemble “Chervona Ruta” in the context of Ukrainian musical culture. The relevance of the study lies in the development of principles of a new vision, trends in the development of the ensemble “Chervona Ruta” in the context of Ukrainian pop and ensemble performance and its role in the development of musical culture of Ukraine. The methodology of this study is the application of comparative-historical method, which allows us to trace the historical context of the ensemble and the context of the development of pop and ensemble art of Ukraine. The chronological method allows to determine the stages of formation and development of the team on the example of the analysis of concert and performance activities of the ensemble. Vocal and pop performance on the examplebof the ensemble “Chervona Ruta” appears as a dynamic cultural and artistic phenomenon. The song repertoire of the ensemble appears as a translator of the identity of Ukrainian culture, which is confirmed by the presence of folk intonations and the involvement of appropriatebinstruments. The study of the processes of formation and development of ensembles allows us to identify the traditions of Ukrainian pop music, which is a prerequisite for the formation and development of musical art in Ukraine. Despite the existing achievements in the study of ensemble performance, the issues of the influence of ensemble work on Ukrainian artistic music culture remain insufficiently studied, which highlights the need for a comprehensive analysis of the specifics of pop vocal and ensemble performance, especially the band “Chervona Ruta” as a creative phenomenon of pop ensemble. The creative path of the ensemble “Chervona Ruta” began a new stage in the formation of pop song repertoire, which differs from the previous significant changes in genre richness, functional features and new means of performance. The popularization of Ukrainian pop song contributed to the development of television, the improvement of sound recording and reproducing equipment, the emergence of electromusical instruments. All this contributed to the emergence of numerous amateur vocal and instrumental ensembles – a hallmark of a new era in the development of popular music. The advent of VIA brought new ways of artistic expression to the stage – new timbre paints, the use of electromusical instruments with their specifics, the use of various electronic systems, the strange sound of voices in extreme tension. Conclusions. Ensemble art in various genre and stylistic forms has always played a significant role in social life and has enjoyed the widest popularity among composers, performers and listeners in all historical epochs and in general remains popular today. The rise and prosperity of VIA coincided with a period of intensive scientific and technical discoveries – radio engineering, electronics, sound recording. Participants of vocal-instrumental ensembles can be called musicians-performers of a new type, they are at the same time singers, musicians, actors and authors. The new domestic VIA combined the features of big beat and enriched them with national elements, in their programs there is a tendency to synthesize with theater, choreography. A new youth spectator stood out from the former regular audience of the stage, the regulatory functions of the mass media increased.

Experimental evaluation of ensemble classifiers for imbalance in Big Data

Datasets are growing in size and complexity at a pace never seen before, forming ever larger datasets known as Big Data. A common problem for classification, especially in Big Data, is that the numerous examples of the different classes might not be balanced. Some decades ago, imbalanced classification was therefore introduced, to correct the tendency of classifiers that show bias in favor of the majority class and that ignore the minority one. To date, although the number of imbalanced classification methods have increased, they continue to focus on normal-sized datasets and not on the new reality of Big Data. In this paper, in-depth experimentation with ensemble classifiers is conducted in the context of imbalanced Big Data classification, using two popular ensemble families (Bagging and Boosting) and different resampling methods. All the experimentation was launched in Spark clusters, comparing ensemble performance and execution times with statistical test results, including the newest ones based on the Bayesian approach. One very interesting conclusion from the study was that simpler methods applied to unbalanced datasets in the context of Big Data provided better results than complex methods. The additional complexity of some of the sophisticated methods, which appear necessary to process and to reduce imbalance in normal-sized datasets were not effective for imbalanced Big Data.