Ensemble Setting Research Articles

Generalization Performance of Pure Accuracy and its Application in Selective Ensemble Learning.

The pure accuracy measure is used to eliminate random consistency from the accuracy measure. Biases to both majority and minority classes in the pure accuracy are lower than that in the accuracy measure. In this paper, we demonstrate that compared with the accuracy measure and F-measure, the pure accuracy measure is class distribution insensitive and discriminative for good classifiers. The advantages make the pure accuracy measure suitable for traditional classification. Further, we mainly focus on two points: exploring a tighter generalization bound on pure accuracy based learning paradigm and designing a learning algorithm based on the pure accuracy measure. Particularly, with the self-bounding property, we build an algorithm-independent generalization bound on the pure accuracy measure, which is tighter than the existing bound of an order O(1/√N) (N is the number of instances). The proposed bound is free from making a smoothness or convex assumption on the hypothesis functions. In addition, we design a learning algorithm optimizing the pure accuracy measure and use it in the selective ensemble learning setting. The experiments on sixteen benchmark data sets and four image data sets demonstrate that the proposed method statistically performs better than the other eight representative benchmark algorithms.

Soul

<i>Soul</i>

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.

FEEL: Framework for the Integration of Entity Extraction and Linking Systems

Entity extraction and linking (EEL) is an important task of the Semantic Web that allows us to identify real-world objects from text and associate them with their respective resources from a Knowledge Base. Thus, one purpose of the EEL task is to extract knowledge from text. In recent years, several systems have been proposed for addressing such a task in several domains, languages, and knowledge bases. In this sense, some systems that combine the benets of varied EEL systems have been proposed in a kind of ensemble system (like in Machine Learning) to provide better performance and extractions than using a single system. However, there are no clear indications for the selection, conguration, and result integration of EEL systems in an ensemble setting. This paper proposes a framework for the integration of EEL systems by providing recommendations for the selection of systems, the conguration of input parameters, the execution of systems, and the nal integration of results through a ltering strategy that measures the occurrence of entities and detects the overlapping of entities. Based on the proposed framework, we implemented a system using existing EEL systems (through publicly available APIs). The experiments were performed through the GERBIL framework. Our results demonstrate an improvement of the micro/macroprecision and recall of the implemented system regarding the selected individual EEL systems over seven datasets.

A Motivational Sequence Model of High School Ensemble Students’ Intentions to Continue Participating in Music

Grounded in a hierarchical model of intrinsic and extrinsic motivation (HMIEM), the primary aim of this study was to test a full motivational sequence at the contextual level in a high school ensemble setting (Social-Contextual Factors → Psychological Needs → Motivation → Consequences). I specifically examined the relationships between multifaceted variables within this sequence, including teacher-created social contexts, psychosocial needs, types of motivation, and consequences. A secondary purpose of this study was to determine whether gender would impact the results of the sequence of motivational processes. Structural equation modeling analysis with a sample of 425 high school ensemble students revealed that social-contextual factors provided by the teachers were related to satisfaction of fundamental autonomy, competence, and relatedness needs, which in turn influenced intrinsic motivation, positive motivational outcomes, and persistence in musical activities. The multistep invariance analysis also revealed the model to be invariant for males and females. The results of the study supported the HMIEM and validated the application of the motivational sequence in the context of music education.

On detecting urgency in short crisis messages using minimal supervision and transfer learning.

Humanitarian disasters have been on the rise in recent years due to the effects of climate change and socio-political situations such as the refugee crisis. Technology can be used to best mobilize resources such as food and water in the event of a natural disaster, by semi-automatically flagging tweets and short messages as indicating an urgent need. The problem is challenging not just because of the sparseness of data in the immediate aftermath of a disaster, but because of the varying characteristics of disasters in developing countries (making it difficult to train just one system) and the noise and quirks in social media. In this paper, we present a robust, low-supervision social media urgency system that adapts to arbitrary crises by leveraging both labeled and unlabeled data in an ensemble setting. The system is also able to adapt to new crises where an unlabeled background corpus may not be available yet by utilizing a simple and effective transfer learning methodology. Experimentally, our transfer learning and low-supervision approaches are found to outperform viable baselines with high significance on myriad disaster datasets.

Early Socialization and Opinions of Musicianship Among Preservice Music Teachers

The development of musicianship is a fundamental learning outcome for music students. The purpose of this study was to examine the early socialization experiences of preservice music teachers, as well as their opinions about musicianship. A total of 138 undergraduate music education students completed a three-part online questionnaire. The large ensemble setting was the most common source of learning and participants believed this setting contributed to the development of overall musicianship more so than any other source of learning. “Learning songs from notation” and “Music analysis” were perceived as most valuable in developing musicianship. Kruskal–Wallis tests showed differences in conceptions of musicianship based on the instrument played, but not among other socialization variables. Based on the findings, I conclude that preservice music teachers are being socialized to conceive of musicianship in ways that suit an existing school model, rather than contemporary and evolving music cultures found outside of schools.

FEEL: Framework for the integration of Entity Extraction and Linking systems

Entity extraction and linking (EEL) is an important task of the Semantic Web that allows to identify real-world objects from text and associate them with their respective resources from a Knowledge Base. Thus, one purpose of the EEL task is to extract knowledge from text. In recent years, several systems have been proposed for addressing such a task in several domains, languages, and knowledge bases. In this sense, some systems that combine the benefits of varied EEL systems have been proposed in a kind of ensemble system (like in Machine Learning) to provide better performance and extractions than using a single system. However, there are no clear indications for the selection, configuration, and result integration of EEL systems in an ensemble setting. This paper proposes a framework for the integration of EEL systems by providing recommendations for the selection of systems, the configuration of input parameters, the execution of systems, and the final integration of results through a filtering strategy that measures the occurrence of entities and detects the overlapping of entities. Based on the proposed framework, we implemented a system using existing EEL systems (through publicly available APIs). The experiments were performed through the GERBIL framework. Our results demonstrate an improvement of the micro/macro- precision and recall of the implemented system regarding the selected individual EEL systems over seven datasets.

Predictive verification for the design of partially exchangeable multi-model ensembles

The performance of an ensemble forecast, as measured by scoring rules, depends on its number of members. Under the assumption of ensemble member exchangeability, ensemble-adjusted scores provide unbiased estimates of the ensemble-size effect. In this study, the concept of ensemble-adjusted scores is revisited and exploited in the general context of multi-model ensemble forecasting. In particular, an ensemble-size adjustment is proposed for the continuous ranked probability score in a multi-model ensemble setting. The method requires that the ensemble forecasts satisfy generalised multi-model exchangeability conditions. These conditions do not require the models themselves to be exchangeable. The adjusted scores are tested here on a dual-resolution ensemble, an ensemble which combines members drawn from the same numerical model but run at two different grid resolutions. It is shown that performance of different ensemble combinations can be robustly estimated based on a small subset of members from each model. At no additional cost, the ensemble-size effect is investigated not only considering the pooling of potential extra-members but also including the impact of optimal weighting strategies. With simple and efficient tools, the proposed methodology paves the way for predictive verification of multi-model ensemble forecasts; the derived statistics can provide guidance for the design of future operational ensemble configurations without having to run additional ensemble forecast experiments for all the potential configurations.

Surface Permeability of Particulate Porous Media

The dispersion process in particulate porous media at low saturation levels takes place over the surface elements of constituent particles and, as we have found previously by comparison with experiments, can be accurately described by superfast nonlinear diffusion partial differential equations. To enhance the predictive power of the mathematical model in practical applications, one requires the knowledge of the effective surface permeability of the particle-in-contact ensemble, which can be directly related with the macroscopic permeability of the particulate media. We have shown previously that permeability of a single particulate element can be accurately determined through the solution of the Laplace–Beltrami Dirichlet boundary value problem. Here, we demonstrate how that methodology can be applied to study permeability of a randomly packed ensemble of interconnected particles. Using surface finite element techniques, we examine numerical solutions to the Laplace–Beltrami problem set in the multiply-connected domains of interconnected particles. We are able to directly estimate tortuosity effects of the surface flows in the particle ensemble setting.

Multi-task Stack Propagation for Neural Quality Estimation

Quality estimation is an important task in machine translation that has attracted increased interest in recent years. A key problem in translation-quality estimation is the lack of a sufficient amount of the quality annotated training data. To address this shortcoming, the Predictor-Estimator was proposed recently by introducing “word prediction” as an additional pre-subtask that predicts a current target word with consideration of surrounding source and target contexts, resulting in a two-stage neural model composed of a predictor and an estimator . However, the original Predictor-Estimator is not trained on a continuous stacking model but instead in a cascaded manner that separately trains the predictor from the estimator. In addition, the Predictor-Estimator is trained based on single-task learning only, which uses target-specific quality-estimation data without using other training data that are available from other-level quality-estimation tasks. In this article, we thus propose a multi-task stack propagation , which extensively applies stack propagation to fully train the Predictor-Estimator on a continuous stacking architecture and multi-task learning to enhance the training data from related other-level quality-estimation tasks. Experimental results on WMT17 quality-estimation datasets show that the Predictor-Estimator trained with multi-task stack propagation provides statistically significant improvements over the baseline models. In particular, under an ensemble setting, the proposed multi-task stack propagation leads to state-of-the-art performance at all the sentence/word/phrase levels for WMT17 quality estimation tasks.

Lyric approaches to songwriting in the classroom

Songwriting involves an awareness of form, structure, rhythm, harmony, melody, accompaniment and arrangement. In songs containing words, these elements combine with the lyric to propel a song into existence. Geared towards secondary and college settings, this article offers that starting the songwriting process with lyric creation is an engaging alternative to starting with more harmonic- and melodic-based approaches. Group activities and teamwork can allow for a more broadly engaged class or ensemble, and has implications for parallel use in core academic areas such as English or writing. This article will discuss song structure and forms, prosody, limiting and the creative process, and explore three lyric-centred approaches to songwriting that can jump-start lyric and song creation in a solo, ensemble or classroom setting.

Improved Credit Scoring Model Based on Bagging Neural Network

The problem of nonperforming loans is one of the biggest problems in the banking sector. In order to mitigate this problem, it is necessary to improve the methods of credit risk assessment. One way to minimize credit risk is to improve the assessment of the creditworthiness of the applicant. In order to make a more accurate assessment, many models have been developed using classification techniques. This paper demonstrates the use of classification techniques in the form of a single classifier or in a classifier ensemble setting. We proposed bagging as a model ensemble using artificial neural networks. In the experiment conducted with the Bosnian commercial banks dataset, the proposed model showed promising results according to evaluation criteria, especially after the process of feature selection. Both individual and wrapper feature selection methods were used. Bagging with neural network (NNBag) outperforms commonly used techniques with accuracy improvement from 1% to 5%. The superiority of the proposed model (NNBag) is confirmed on two widely available datasets for assessing creditworthiness. Based on experimental results on three datasets, it is proven that NNBag is suitable for use in the assessment of the creditworthiness of applicants.

The effects of frequent use of a web-based sight-reading software on eighth graders’ music notational literacy

Due to its potential of improving an individual’s music notational literacy and the ease of use within the ensemble setting, the purpose of this study was to determine if frequent use of a web-based sight-reading software (sightreadingfactory.com) in full band rehearsals and group lessons would improve a band student’s individual music notational literacy level. For this study, the researcher utilized the pretest–post-test control–group statistical design with three groups of eighth-grade band students. Group 1 (n = 25) used the software at the beginning of every full band rehearsal, Group 2 (n = 31) used the software at the beginning of every small group lesson rehearsal, and Group 3 (n = 23) did not use the software in any capacity and served as the control group. The study lasted for eight weeks. The researcher individually administered the pretest to all student participants in Week 1 of the study and the post-test during Week 8. In order to determine which treatment caused the greatest change in music notational literacy, the researcher compared the mean gain scores of each group using an ANOVA and found statistically significant findings (F = 3.84, df = 2, p = 0.026). Group 1 (n = 25, M = 2.80, SD = 1.76) students’ mean gain scores were significantly higher than Group 3’s (n = 20, M = 0.90, SD = 2.02, p = 0.006 indicating) evident that the web-based software was most effective in the full ensemble rehearsals.

Lagrangian tracking in stochastic fields with application to an ensemble of velocity fields in the Red Sea

Lagrangian tracking of passive tracers in a stochastic velocity field within a sequential ensemble data assimilation framework is challenging due to the exponential growth in the number of particles. This growth arises from describing the behavior of velocity over time as a set of possible combinations of the different realizations, before and after each assimilation cycle. This paper addresses the problem of efficiently advecting particles in stochastic flow fields, whose statistics are prescribed by an underlying ensemble, in a parallel computational framework (openMP). To this end, an efficient algorithm for forward and backward tracking of passive particles in stochastic flow-fields is presented. The algorithm, which employs higher order particle advection schemes, presents a mechanism for controlling the growth in the number of particles. The mechanism uses an adaptive binning procedure, while conserving the zeroth, first and second moments of probability (total probability, mean position, and variance). The adaptive binning process offers a tradeoff between speed and accuracy by limiting the number of particles to a desired maximum. To validate our method, we conducted various forward and backward particles tracking experiments within a realistic high-resolution ensemble assimilation setting of the Red Sea, focusing on the effect of the maximum number of particles, the time step, the variance of the ensemble, the travel time, the source location, and history of transport.

What’s the Problem? Exploring the Potential of Problem-Based Learning in an Ensemble Setting

Can you think of a research-supported strategy that simultaneously encourages critical and creative thinking; develops knowledge, skills, and affect; promotes meaningful connection with music; and creates lifelong learners? Problem-based learning (PBL) effectively meets and exceeds these criteria by providing an engaging opportunity for students to use higher-order thinking skills and create meaningful connections with the music they are studying through the context of real-life problem scenarios. An authentic problem with multiple solutions allows students to collaborate and develop into independent learners while actively engaging in the music they are studying. This strategy, used effectively for more than fifty years in other education fields, has rarely been used in music education, but PBL’s potential to positively influence student learning is well worth exploring.

An exploration of the self-selection of musical parts by members of a New Horizons concert band

Abstract This study examined the self-selection of musical parts (first, second, third or fourth) as perceived by members of a New Horizons concert band. Ensemble members’ self-reported part selection decisions, preferences for specific parts, perceived difficulties and benefits of the self-selection of musical parts, and suggestions for improvement of this part selection process were also examined. In this mixed methods study, an anonymous online questionnaire was used to collect data from (n=29) respondents, and semi-structured interviews were conducted with (n=9) participants. Results indicated that multiple factors influenced the self-selection of musical parts. These factors included, but may not be limited to: preferences for a particular part, the need for a balanced section, a need for all musical parts to be performed, personal musical skills, perceptions of the musical skill levels of other section members, and perhaps most important, a desire to make one’s best contribution to the ensemble. Suggested options for guiding ensemble members in the self-selection of musical parts, and for presenting members with strategies to improve musical skills while playing a variety of parts are discussed in the context of self-directed learning in an ensemble setting.

Ensemble outlier detection and gene selection in triple-negative breast cancer data

BackgroundLearning accurate models from ‘omics data is bringing many challenges due to their inherent high-dimensionality, e.g. the number of gene expression variables, and comparatively lower sample sizes, which leads to ill-posed inverse problems. Furthermore, the presence of outliers, either experimental errors or interesting abnormal clinical cases, may severely hamper a correct classification of patients and the identification of reliable biomarkers for a particular disease. We propose to address this problem through an ensemble classification setting based on distinct feature selection and modeling strategies, including logistic regression with elastic net regularization, Sparse Partial Least Squares - Discriminant Analysis (SPLS-DA) and Sparse Generalized PLS (SGPLS), coupled with an evaluation of the individuals’ outlierness based on the Cook’s distance. The consensus is achieved with the Rank Product statistics corrected for multiple testing, which gives a final list of sorted observations by their outlierness level.ResultsWe applied this strategy for the classification of Triple-Negative Breast Cancer (TNBC) RNA-Seq and clinical data from the Cancer Genome Atlas (TCGA). The detected 24 outliers were identified as putative mislabeled samples, corresponding to individuals with discrepant clinical labels for the HER2 receptor, but also individuals with abnormal expression values of ER, PR and HER2, contradictory with the corresponding clinical labels, which may invalidate the initial TNBC label. Moreover, the model consensus approach leads to the selection of a set of genes that may be linked to the disease. These results are robust to a resampling approach, either by selecting a subset of patients or a subset of genes, with a significant overlap of the outlier patients identified.ConclusionsThe proposed ensemble outlier detection approach constitutes a robust procedure to identify abnormal cases and consensus covariates, which may improve biomarker selection for precision medicine applications. The method can also be easily extended to other regression models and datasets.

HierFlat: flattened hierarchies for improving top-down hierarchical classification

Large-scale classification of structured data where classes are organized in a hierarchical structure is an important area of research. Top-down approaches that leverage the hierarchy during the learning and prediction phase are efficient for solving large-scale hierarchical classification. However, accuracy of top-down approaches is poor due to error propagation, i.e., prediction errors made at higher levels in the hierarchy cannot be corrected at lower levels. One of the main reasons behind errors at the higher levels is the presence of inconsistent nodes that are introduced due to the arbitrary process of creating these hierarchies by domain experts. In this paper, we propose two different data-driven approaches (local and global) for hierarchical structure modification that identifies and flattens inconsistent nodes present in the hierarchy. Our extensive empirical evaluation of the proposed approaches on several image and text datasets with varying distribution of features, classes and training instances per class shows improved classification performance over competing hierarchical modification approaches. Specifically, we see an improvement up to 7 $$\%$$ in Macro-F1 score with our best approach over best top-down baseline. We also show that our modified hierarchy leads to improved classification performance for classes with few training samples in comparison with flat approach. Further, our experimental evaluation shows that combining the prediction from flat and hierarchical model in an ensemble setting results in better classification performance.

Reducing Risk of Noise-Induced Hearing Loss in Collegiate Music Ensembles Using Ambient Technology

Student musicians are at risk for noise-induced hearing loss (NIHL) as they develop skills and perform during instructional activities. Studies using longitudinal dosimeter data show that pedagogical procedures and instructor behaviors are highly predictive of NIHL risk, thus implying the need for innovative approaches to increase instructor competency in managing instructional activities without interfering with artistic and academic freedom. Ambient information systems, an emerging trend in human-computer interaction that infuses psychological behavioral theories into technologies, can help construct informative risk-regulating systems. The purpose of this study was to determine the effects of introducing an ambient information system into the ensemble setting. The system used two ambient displays and a counterbalanced within-subjects treatment study design with six jazz ensemble instructors to determine if the system could induce a behavior change that alters trends in measures resulting from dosimeter data. This study assessed efficacy using time series analysis to determine changes in eight statistical measures of behavior over a 9-wk period. Analysis showed that the system was effective, as all instructors showed changes in a combination of measures. This study is in an important step in developing non-interfering technology to reduce NIHL among academic musicians.