Ensemble Performance Research Articles

An improved 2-degree-of-freedom internal model proportional–integral–derivative controller design for stable time-delay processes

In this article, an enhanced 2-degree-of-freedom internal model control strategy for typical industrial processes with time-delay is developed. For the proposed controller, it is composed of an inner loop feedback controller which is designed based on the internal model control theory and a weighted set-point tracking controller. Note that the adjustment of set-point tracking performance and disturbance rejection characteristics can be decoupled by employing the developed strategy, which indicates that more degrees of freedom are obtained for the proposed controller design; thus, better ensemble performance and stronger robustness are anticipated by regulating these two controllers separately, which may not be achieved in the conventional internal model control method. Case studies on two kinds of stable processes with time-delay verify the effectiveness of the proposed scheme finally.

Efficient Facial Feature Learning with Wide Ensemble-Based Convolutional Neural Networks

Ensemble methods, traditionally built with independently trained de-correlated models, have proven to be efficient methods for reducing the remaining residual generalization error, which results in robust and accurate methods for real-world applications. In the context of deep learning, however, training an ensemble of deep networks is costly and generates high redundancy which is inefficient. In this paper, we present experiments on Ensembles with Shared Representations (ESRs) based on convolutional networks to demonstrate, quantitatively and qualitatively, their data processing efficiency and scalability to large-scale datasets of facial expressions. We show that redundancy and computational load can be dramatically reduced by varying the branching level of the ESR without loss of diversity and generalization power, which are both important for ensemble performance. Experiments on large-scale datasets suggest that ESRs reduce the remaining residual generalization error on the AffectNet and FER+ datasets, reach human-level performance, and outperform state-of-the-art methods on facial expression recognition in the wild using emotion and affect concepts.

Extreme Learning Machine-Based State Reconstruction for Automatic Attack Filtering in Cyber Physical Power System

Successful detection of false data injection attacks (FDIAs) and removal of state bias due to FDIAs are essential for ensuring secure power grids operation and control. This article first extends the approximate dc model of FDIA to a more general ac model that can handle both traditional and synchronized measurements. To automatically filter out the established FDIAs, we propose a state reconstruction scheme consisting of a contaminated state separation method, an enhanced bad data identification approach and a state recovery algorithm. In this scheme, a classifier is developed by aggregating a series of extreme learning machines (ELMs) to detect anomaly states caused by FDIAs. Gaussian random distribution and Latin hypercube sampling are adopted to initialize the input weights of base ELMs, which can provide more diversities to enhance the ensemble performance. Then, to identify the exact locations of the compromised measurements, a state forecasting-based bad data identification approach is proposed by exploiting the consistency between the forecasted and the received measurements. Finally, an effective state recovery algorithm applies quasi-Newton method and Armijo line search to address the possible system unobservable problem due to the removal of attacked measurements. Numerical tests on serval IEEE standard test systems verify the efficiency of the proposed FDIA model and state reconstruction scheme.

A Comparative Study of Incremental Semi-Supervised Subspace Clustering Ensemble Approaches and Performance Outcomes for High Dimensional Data

A Comparative Study of Incremental Semi-Supervised Subspace Clustering Ensemble Approaches and Performance Outcomes for High Dimensional Data

Interactive sound art and animated notation as an ensemble performance platform in primary level music education

This article showcases excerpts of my artistic research in progress. In particular, I demonstrate how an interdisciplinary approach combining knowledge from the fields of artistic research, Human Computer Interaction (HCI) and game studies mayinspire primary level music education of today. I highlight examples of novel digital music technology and present an innovate approach to using these for group performance exercises in the music classroom. In particular, I report from a study where my interactive sound art exhibition LINES, in combination with animated music notation, was used as a digital ensemble music platform. The data of the study comprises five workshop sessions with pre-schoolers using this platform. An autoethnographic method and analysis of video documentation of the workshop sessions were used as methods for the study. The results showed that LINES was both engaging and easily accessed. Moreover, it allowed the majority of the target group to perform musical exercises as an ensemble. I argue that the use of traditional instruments and traditional notation creates a democratic issue in primary level music education. Furthermore, with support from the study and related research, I argue that platforms such as this may democratize music education involving pupils aged 5-15 years.

Evaluation of the Quasi‐Biennial Oscillation in global climate models for the SPARC QBO‐initiative

AbstractQuasi‐biennial oscillations (QBOs) in thirteen atmospheric general circulation models forced with both observed and annually repeating sea surface temperatures (SSTs) are evaluated. In most models the QBO period is close to, but shorter than, the observed period of 28 months. Amplitudes are within ±20% of the observed QBO amplitude at 10 hPa, but typically about half of that observed at lower altitudes (50 and 70 hPa). For almost all models, the oscillation's amplitude profile shows an overall upward shift compared to reanalysis and its meridional extent is too narrow. Asymmetry in the duration of eastward and westward phases is reasonably well captured, though not all models replicate the observed slowing of the descending westward shear. Westward phases are generally too weak, and most models have an eastward time mean wind bias throughout the depth of the QBO. The intercycle period variability is realistic and in some models is enhanced in the experiment with observed SSTs compared to the experiment with repeated annual cycle SSTs. Mean periods are also sensitive to this difference between SSTs, but only when parametrized non‐orographic gravity wave (NOGW) sources are coupled to tropospheric parameters and not prescribed with a fixed value. Overall, however, modelled QBOs are very similar whether or not the prescribed SSTs vary interannually. A portrait of the overall ensemble performance is provided by a normalized grading of QBO metrics. To simulate a QBO, all but one model used parametrized NOGWs, which provided the majority of the total wave forcing at altitudes above 70 hPa in most models. Hence the representation of NOGWs either explicitly or through parametrization is still a major uncertainty underlying QBO simulation in these present‐day experiments.

The sound image of the domra in V. Solomin’s works as a representant of the sound image of modernity

The sound image of the domra in V. Solomin’s works as a representant of the sound image of modernity

Using Ensembles for Class-Imbalance Problem to Predict Maintainability of Open Source Software

To facilitate software maintenance and save the maintenance cost, numerous machine learning (ML) techniques have been studied to predict the maintainability of software modules or classes. An abundant amount of effort has been put by the research community to develop software maintainability prediction (SMP) models by relating software metrics to the maintainability of modules or classes. When software classes demanding the high maintainability effort (HME) are less as compared to the low maintainability effort (LME) classes, the situation leads to imbalanced datasets for training the SMP models. The imbalanced class distribution in SMP datasets could be a dilemma for various ML techniques because, in the case of an imbalanced dataset, minority class instances are either misclassified by the ML techniques or get discarded as noise. The recent development in predictive modeling has ascertained that ensemble techniques can boost the performance of ML techniques by collating their predictions. Ensembles themselves do not solve the class-imbalance problem much. However, aggregation of ensemble techniques with the certain techniques to handle class-imbalance problem (e.g., data resampling) has led to several proposals in research. This paper evaluates the performance of ensembles for the class-imbalance in the domain of SMP. The ensembles for class-imbalance problem (ECIP) are the modification of ensembles which pre-process the imbalanced data using data resampling before the learning process. This study experimentally compares the performance of several ECIP using performance metrics Balance and g-Mean over eight Apache software datasets. The results of the study advocate that for imbalanced datasets, ECIP improves the performance of SMP models as compared to classic ensembles.

СУЧАСНІ ПІДХОДИ ДО МУЗИЧНО-ВИКОНАВСЬКОЇ СПІВТВОРЧОСТІ СТУДЕНТА І КОНЦЕРТМЕЙСТЕРА ЗАКЛАДУ ВИЩОЇ ОСВІТИ

The article analyzes some theoretical and practical issues of improving the quality of performance of the concertmaster and student, which is caused by the tasks of vocational training and the requirements that occur in the field of contemporary music pedagogy regarding joint musical and creative activities of the student and the concertmaster. It is noted that the high level of ensemble culture allows the performers to find effective approaches in their practical activity. The necessity of interrelation of ensemble preparation of the concertmaster and the student with the general psychological, pedagogical and methodical preparation that promotes the solution of peculiar creative problems. It is proved that a clear awareness of the differences in the specifics of solo and joint performance, which is one of the leading principles of acquiring the accompanist required ensemble skills and knowledge. The issues of history, theory, techniques related to the features of ensemble performance: musical knowledge culture, personal qualities, problems of interpersonal interaction, creative balance. The conditions that ensure the quality of the joint performance process are defined. The corresponding professional and personally-significant qualities of the performers, whose presence provides productive work are characterized: artistic thinking, professional orientation, musical abilities, a single auditory perception of a musical work, taking into account the specificity of a musical instrument, quality, communicative qualities. The main stages of working together on a musical work are identified. It is noted that competently work of the concertmaster with the student should become the basis of successful concert and competition performances. It is concluded that the exchange of experience between the concertmaster and the student, a joint creative search for the disclosure of the artistic content of a musical work greatly enriches their personalities, broadens their worldview.

A data-driven multi-model ensemble for deterministic and probabilistic precipitation forecasting at seasonal scale

Seasonal precipitation forecasting is valuable for regional water management and agricultural food security. Current numerical models have large uncertainty in model structure, parameterization and initial conditions. Here, a data-driven multi-model ensemble is constructed using a series of statistical and machine learning methods with varying inputs. Deterministic precipitation forecasts are produced by the weighting of ensemble members using Bayesian model averaging (BMA) and probabilistic forecasts are generated by sampling from BMA predictive probability density function (PDF). Three mathematical metrics are used to evaluate the performance of precipitation forecasts, including Pearson’s correlation coefficient (PCC), root mean square error skill score (RMSESS) and continuous ranked probability skill score (CRPSS). The results demonstrate that the accuracy in the statistical ensemble is significantly higher than the North American multi-model ensemble (NMME) for both deterministic and probabilistic precipitation forecasts, especially at 1-month lead. Statistical models are considerably enhanced by incorporating wavelets, which decomposes the raw precipitation series into several different levels, potentially representing underlying precipitation patterns at different time-frequency scales. Selecting some good ensemble members can improve the ensemble performance, instead of including all the ensemble members with some inefficient models. Overall, the statistical ensemble can be considered as an effective complement of numerical models in both deterministic and probabilistic precipitation forecasts.

Evaluation of two hydrometeorological ensemble strategies for flash-flood forecasting over a catchment of the eastern Pyrenees

Abstract. This study aims at evaluating the performances of flash-flood forecasts issued from deterministic and ensemble meteorological prognostic systems. The hydrometeorological modeling chain includes the Weather Research and Forecasting Model (WRF) forcing the rainfall-runoff model MARINE dedicated to flash floods. Two distinct ensemble prediction systems accounting for (i) perturbed initial and lateral boundary conditions of the meteorological state and (ii) mesoscale model physical parameterizations have been implemented on the Agly catchment of the eastern Pyrenees with three subcatchments exhibiting different rainfall regimes. Different evaluations of the performance of the hydrometeorological strategies have been performed: (i) verification of short-range ensemble prediction systems and corresponding streamflow forecasts, for a better understanding of how forecasts behave; (ii) usual measures derived from a contingency table approach, to test an alert threshold exceedance; and (iii) overall evaluation of the hydrometeorological chain using the continuous rank probability score, for a general quantification of the ensemble performances. Results show that the overall discharge forecast is improved by both ensemble strategies with respect to the deterministic forecast. Threshold exceedance detections for flood warning also benefit from large hydrometeorological ensemble spread. There are no substantial differences between both ensemble strategies on these test cases in terms of both the issuance of flood warnings and the overall performances, suggesting that both sources of external-scale uncertainty are important to take into account.

Performance of statistical and machine learning ensembles for daily temperature downscaling

Temperature changes have widespread impacts on the environment, economy, and municipal planning. Generating accurate climate prediction at finer spatial resolution through downscaling could help better assess the future effects of climate change on a local scale. Ensembles of multiple climate models have been proven to improve the accuracy of temperature prediction. Meanwhile, machine learning techniques have shown high performance in solving various predictive modeling problems, which make them a promising tool for temperature downscaling. This study investigated the performance of machine learning (long short-term memory (LSTM) networks and support vector machine (SVM)) and statistical (arithmetic ensemble mean (EM) and multiple linear regression (MLR)) methods in developing multi-model ensembles for downscaling long-term daily temperature. A case study of twelve meteorological stations across Ontario, Canada, was conducted to evaluate the performance of the proposed ensembles. The results showed that both machine learning and statistical techniques performed well at downscaling daily temperature with multi-model ensembles and had similar performance with relatively high accuracy. The R2 of 12 stations ranged between 0.756 and 0.820 and RMSE ranged between 4.318 and 7.063 °C. Both machine learning and statistical ensembles for downscaling had difficulty in predicting extreme values for temperature below − 10 °C and above 20 °C. The results provided technical support for using statistical and machine learning methods to generate high-resolution daily temperature prediction.

Ensemble learning by means of a multi-objective optimization design approach for dealing with imbalanced data sets

Ensemble learning methods have already shown to be powerful techniques for creating classifiers. However, when dealing with real-world engineering problems, class imbalance is usually found. In such scenario, canonical machine learning algorithms may not present desirable solutions, and techniques for overcoming this problem must be used. In addition to using learning algorithms that alleviate the imbalance between classes, multi-objective optimization design (MOOD) approaches can be used to improve the prediction performance of ensembles of classifiers. This paper proposes a study of different MOOD approaches for ensemble learning. First, a taxonomy on multi-objective ensemble learning (MOEL) is proposed. In it, four types of existing approaches are defined: multi-objective ensemble member generation, multi-objective ensemble member selection, multi-objective ensemble member combination, and multi-objective ensemble member selection and combination. Additionally, new approaches can be derived by combining the previous ones, such as multi-objective ensemble member generation and selection, multi-objective ensemble member generation and combination and multi-objective ensemble member generation, selection and combination. With the given taxonomy, two experiments are conducted for comparing (1) the performance of the MOEL techniques for generating and aggregating base models on several imbalanced benchmark problems and (2) the performance of MOEL techniques against other machine learning techniques in a real-world imbalanced drinking-water quality anomaly detection problem. Finally, results indicate that MOOD is able to improve the predictive performance of existing ensemble learning techniques.

Classification of Interstitial Lung Abnormality Patterns with an Ensemble of Deep Convolutional Neural Networks

Subtle interstitial changes in the lung parenchyma of smokers, known as Interstitial Lung Abnormalities (ILA), have been associated with clinical outcomes, including mortality, even in the absence of Interstitial Lung Disease (ILD). Although several methods have been proposed for the automatic identification of more advanced Interstitial Lung Disease (ILD) patterns, few have tackled ILA, which likely precedes the development ILD in some cases. In this context, we propose a novel methodology for automated identification and classification of ILA patterns in computed tomography (CT) images. The proposed method is an ensemble of deep convolutional neural networks (CNNs) that detect more discriminative features by incorporating two, two-and-a-half and three- dimensional architectures, thereby enabling more accurate classification. This technique is implemented by first training each individual CNN, and then combining its output responses to form the overall ensemble output. To train and test the system we used 37424 radiographic tissue samples corresponding to eight different parenchymal feature classes from 208 CT scans. The resulting ensemble performance including an average sensitivity of 91,41% and average specificity of 98,18% suggests it is potentially a viable method to identify radiographic patterns that precede the development of ILD.

KalmanTune: A Kalman Filter Based Tuning Method to Make Boosted Ensembles Robust to Class-Label Noise

Boosting has been shown to be a very effective approach to training ensemble classification models. Although they perform very well, boosting algorithms are sensitive to class-label noise (where training data instances are mislabelled). As the level of class-label noise in the training dataset increases, the generalisation performance of ensembles trained using boosting decreases. This paper introduces KalmanTune, a tuning process that can be applied to ensemble models after they have been trained using a boosting algorithm that reduces the impact of class-label noise. KalmanTune frames the tuning of a trained ensemble model as a static state estimation problem that can be addressed using a Kalman filter. This approach exploits the sensor fusion capability of the Kalman filter to reduce the impact of class-label noise on the trained ensemble. This paper describes KalmanTune and an evaluation experiment performed using 34 multi-class datasets with 5 levels of synthetically induced class-label noise that demonstrates that applying KalmanTune after training can improve the performance of ensemble models trained using boosting, especially when training data contains noisy class-labels.

Improved Distributed Predictive Functional Control With Basic Function and PID Control Structure

It is known that constraints and disturbances in practice may affect the performance of distributed predictive functional control (DPFC) system greatly, thus it is necessary to develop a method to enhance the control performance further. Based on such background, a modified predictive functional control with basic function and PID control structure (BFPID-DPFC) is proposed for large-scale strong coupling system in this paper. In this approach, the performance index is reconstructed by utilizing the Proportional integral derivative (PID) factor and the weighting coefficient of basis functions firstly, then the ensemble control performance of the strong coupling system can be improved by adjusting the corresponding factors. Further, the coupling effect between subsystems can be eliminated by employing Nash game theory, then the improved DPFC approach is obtained. The comparisons between conventional DPFC method and the BFPID-DPFC approach are done in the simulation part, and the results show that the ensemble control performance of the proposed DPFC algorithm is better.

СОВРЕМЕННОЕ ИСПОЛНИТЕЛЬСТВО НА КАЗАХСКОМ КОБЫЗЕ

Global processes in the musical culture of Kazakhstan are the result of the numerous events that have taken place in the country over the past 20 years. The independence of the state has become a key factor that has had a decisive impact on the economic, socio-political and cultural development of the country. We have entered a new life, which has a rich cultural heritage and was carefully preserved by our ancestors. One of the proofs is the history of Kazakh kobyz art from ancient times to the present day. Modern kobyz art is closely connected with ancient history and has a rich natural tendency for new development, based on centuries of experience. Therefore, kobyz music of the XXth–XXIst centuries absorbed the traditions of European genres and styles, and is widely used in mass music, in various directions of ethnorock, art-rock, folk and others. Two lines of development of music for kobyz and music on kobyz existed in ancient times and nowadays. From here comes the divergence of creative direction among modern composers and in ensemble performance.

A scale space model of weighted average CNN ensemble for ASL fingerspelling recognition

A sign language recognition system facilitates communication between the deaf community and the hearing majority. This paper proposes a novel specialised convolutional neural network (CNN) model, SignNet, to recognise hand gesture signs by incorporating scale space theory to deep learning framework. The proposed model is a weighted average ensemble of CNNs – a low resolution network (LRN), an intermediate resolution network (IRN) and a high resolution network (HRN). Augmented versions of VGG-16 are used as LRN, IRN and HRN. The ensemble works at different spatial resolutions and at varying depths of CNN. The SignNet model was assessed with static signs of American Sign Language – alphabets and digits. Since there exists no sign dataset for deep learning, the ensemble performance is evaluated on the synthetic dataset which we have collected for this task. Assessment of the synthetic dataset by SignNet reported an impressive accuracy of over 92%, notably superior to the other existing models.

CHANGING MINDSET, PERCEPTIONS, LEARNING, AND TRADITION: AN "ADAPTIVE TEACHING FRAMEWORK" FOR TEACHING MUSIC ONLINE

This paper is based on the reflections and experiences from a participant researcher perspective and explores the creation of an inventory of core pedagogical components, called the adaptive teaching framework (ATF), for use in online teaching. This was developed as part of a graduate music teaching program (MTP) across more than 20 tertiary subjects. It involves a series of reflections, descriptions, discussion points, and suggestions, which specifically reference related learning theory, content review, modification of learning design, and pedagogy that were considered during the implementation of a new learner management system (LMS) platform (Canvas) at the start of 2020. Amid the initial phase of implementation, staff and students were also required to move suddenly into a fully online learning environment, as the COVID-19 pandemic took hold and the subsequent lockdown removed all face-to-face teaching, an essential part of the MTP that included music performance, classroom pedagogy, curriculum design, research, and ensemble performance, as examples of some of the wide-ranging subject areas. These two significant changes (LMS implementation and the COVID-19 pandemic) occurred concurrently, which heightened both the immediacy and demand for adaptive teaching design within a fully implemented online program. The paper overviews the development of the ATF, in response to these mandated changes, just three weeks into Semester One, 2020. The methodology employed was self-study and aspects of critical reflective practice, whereby the researcher reflected on the intersection of technology and 21st century learning in music education, drawing on established literature, research, and emerging learning models combined with creative pedagogies.

Вьетнам — Россия: диалог культур

The article provides information about the cultural connections of the Far-Eastern Region of Russia with the cultural activists of Vietnam, performances of dance ensembles, exchange of concert programs and organization of combined festivals. Separate attention is given to the selfl ess activities of reconstructing the traditional temple and the rituals of the recent representatives of the Le imperial family carried out by a representative of the dynasty Mrs. Le Thi Minh. Description is given of the historical facts and traditions of the culture of Vietnam, a characterization of the ritual costumes is presented, and information is given of the artistic work carried out by youth ensembles in Vladivostok in restoring Vietnam’s dance ritual culture with the assistance of Mrs. Le Thi Minh.