RGAN-EL: A GAN and ensemble learning-based hybrid approach for imbalanced data classification     

《Information processing & management》2023,60(2):103235

Imbalanced sample distribution is usually the main reason for the performance degradation of machine learning algorithms. Based on this, this study proposes a hybrid framework (RGAN-EL) combining generative adversarial networks and ensemble learning method to improve the classification performance of imbalanced data. Firstly, we propose a training sample selection strategy based on roulette wheel selection method to make GAN pay more attention to the class overlapping area when fitting the sample distribution. Secondly, we design two kinds of generator training loss, and propose a noise sample filtering method to improve the quality of generated samples. Then, minority class samples are oversampled using the improved RGAN to obtain a balanced training sample set. Finally, combined with the ensemble learning strategy, the final training and prediction are carried out. We conducted experiments on 41 real imbalanced data sets using two evaluation indexes: F1-score and AUC. Specifically, we compare RGAN-EL with six typical ensemble learning; RGAN is compared with three typical GAN models. The experimental results show that RGAN-EL is significantly better than the other six ensemble learning methods, and RGAN is greatly improved compared with three classical GAN models.  相似文献   

Blended learning in higher education: professional development in a Hong Kong university     

Jennifer Catharine Evans  Hennie Yip  Kannass Chan  Christine Armatas  Ada Tse 《高等教育研究与发展》2020,39(4):643-656

ABSTRACT

Online learning has become a ubiquitous part of the educational landscape and how teachers are supported in developing approaches to teaching online is a fundamental aspect of the students’ learning experience. Based on the implementation of a professional development course on becoming an online teacher offered in a blended learning mode at one university in Hong Kong, this article proposes that offering this type of professional development in a blended mode is very effective in facilitating enhanced usage of the university’s learning management system. In a blended mode, teachers are actively engaged with blended learning and were found to make more extensive use of features/tools in Blackboard after they attended the professional development course. Results support that offering professional development in a blended mode provides teachers with an authentic student perspective, at the same time as they take guided steps in the teacher’s role in blended learning.  相似文献   

How and why are educators using Instagram?     

《Teaching and Teacher Education》2020

Social media are commonplace in many educators’ lives, but their Instagram activities have received no prior attention in the empirical literature. We therefore created and disseminated a survey regarding educators’ Instagram use. Analyses of 841 responses suggested participants were generally intensive users of Instagram who engaged in the exchange of both professional knowledge and wisdom, as well as affective support. In addition to identifying benefits to Instagram use, some participants offered critiques of Instagram’s professional utility. We discuss the implications of these findings for educators’ work in a digital era and the future of research on educators’ social media activities.  相似文献   

Positivity and quality of college life of business students: The mediating role of learning approaches     

《Studies in Educational Evaluation》2020

Drawing upon the causal agency theory, this study examined the direct and indirect (via learning approaches) links between positivity and quality of college life (QCL) of business students in a transitioning market, Vietnam. Two studies were conducted to test these relationships using structural equation modeling. Findings from study 1, based on a sample of 428 business students, showed that positivity was positively related to QCL. Further, deep learning approaches mediated the relationship between positivity and QCL. Findings from study 2, based on a sample of 416 business students, reconfirmed the role of positivity in QCL. However, the indirect relationship between positivity and QCL was not significant, demonstrating that surface learning approaches did not mediate the relationship between positivity and QCL. The findings contribute to the literature on positivity in higher education by confirming the overarching role that positivity plays, directly and indirectly (via deep learning approaches), in QCL.  相似文献   

Coordinating scaffolds for collaborative inquiry in a game-based learning environment     

Asmalina Saleh  Chen Yuxin  Cindy E. Hmelo-Silver  Krista D. Glazewski  Bradford W. Mott  James C. Lester 《科学教学研究杂志》2020,57(9):1490-1518

Collaborative inquiry learning affords educators a context within which to support understanding of scientific practices, disciplinary core ideas, and crosscutting concepts. One approach to supporting collaborative science inquiry is through problem-based learning (PBL). However, there are two key challenges in scaffolding collaborative inquiry learning in technology rich environments. First, it is unclear how we might understand the impact of scaffolds that address multiple functions (e.g., to support inquiry and argumentation). Second, scaffolds take different forms, further complicating how to coordinate the forms and functions of scaffolds to support effective collaborative inquiry. To address these issues, we identify two functions that needed to be scaffolded, the PBL inquiry cycle and accountable talk. We then designed predefined hard scaffolds and just-in-time soft scaffolds that target the regulation of collaborative inquiry processes and accountable talk. Drawing on a mixed method approach, we examine how middle school students from a rural school engaged with Crystal Island: EcoJourneys for two weeks (N=45). Findings indicate that hard scaffolds targeting the PBL inquiry process and soft scaffolds that targeted accountable talk fostered engagement in these processes. Although the one-to-one mapping between form and function generated positive results, additional soft scaffolds were also needed for effective engagement in collaborative inquiry and that these soft scaffolds were often contingent on hard scaffolds. Our findings have implications for how we might design the form of scaffolds across multiple functions in game-based learning environments.  相似文献   

The Use of a Mobile Learning Tool by Medical Students in Undergraduate Anatomy and its Effects on Assessment Outcomes     

Nikola Golenhofen  Felix Heindl  Claudia Grab-Kroll  David A.C. Messerer  Tobias M. Böckers  Anja Böckers 《Anatomical sciences education》2020,13(1):8-18

Hand-held devices have revolutionized communication and education in the last decade. Consequently, mobile learning (m-learning) has become popular among medical students. Nevertheless, there are relatively few studies assessing students' learning outcomes using m-learning devices. This observational study presents an anatomy m-learning tool (eMed-App), an application developed to accompany an anatomy seminar and support medical students' self-directed learning of the skeletal system. Questionnaire data describe where, how frequently, and why students used the app. Multiple choice examination results were analyzed to evaluate whether usage of the app had an effect on test scores. The eMed-App application was used by 77.5% of the students, mainly accessed by Android smartphones, and at students' homes (62.2%) in order to prepare themselves for seminar sessions (60.8%), or to review learning content (67%). Most commonly, students logged on for less than 15 minutes each time (67.8%). Frequent app users showed better test results on items covering eMed-App learning content. In addition, users also achieved better results on items that were not related to the content of the app and, thus, gained better overall test results and lower failure rates. The top quartile of test performers used the eMed-App more frequently compared to students in lower quartiles. This study demonstrated that many students, especially the high-performing ones, made use of the eMed-App. However, the app itself did not result in better outcomes, suggesting that top students might have been more motivated to use the app than students who were generally weak in anatomy.  相似文献   

Machine learning based system for managing energy efficiency of public sector as an approach towards smart cities     

《International Journal of Information Management》2021

Energy efficiency of public sector is an important issue in the context of smart cities due to the fact that buildings are the largest energy consumers, especially public buildings such as educational, health, government and other public institutions that have a large usage frequency. However, recent developments of machine learning within Big Data environment have not been exploited enough in this domain. This paper aims to answer the question of how to incorporate Big Data platform and machine learning into an intelligent system for managing energy efficiency of public sector as a substantial part of the smart city concept. Deep neural networks, Rpart regression tree and Random forest with variable reduction procedures were used to create prediction models of specific energy consumption of Croatian public sector buildings. The most accurate model was produced by Random forest method, and a comparison of important predictors extracted by all three methods has been conducted. The models could be implemented in the suggested intelligent system named MERIDA which integrates Big Data collection and predictive models of energy consumption for each energy source in public buildings, and enables their synergy into a managing platform for improving energy efficiency of the public sector within Big Data environment. The paper also discusses technological requirements for developing such a platform that could be used by public administration to plan reconstruction measures of public buildings, to reduce energy consumption and cost, as well as to connect such smart public buildings as part of smart cities. Such digital transformation of energy management can increase energy efficiency of public administration, its higher quality of service and healthier environment.  相似文献   

Chinese university EFL teachers’ beliefs and practices of classroom writing assessment     

《Studies in Educational Evaluation》2020

This study investigates the extent to which university teachers’ beliefs about classroom writing assessment are congruent with their self-perceived practices in English-as-a-foreign-language (EFL) contexts, and what factors contribute to belief-practice inconsistencies. Drawing on data from a survey of 136 Chinese university EFL writing teachers and ten teacher interviews, results showed a degree of belief-practice alignment regarding assessment for learning (AfL) practices that make learning explicit, but belief-practice discrepancies were more salient. AfL practices that empower students to take responsibility in writing assessment were perceived to be more important than assessment of learning practices; however, the reverse was found in teachers’ practice. Impacts of micro-level factors including assessment training, teaching experience, student attributes, meso-level school factors, and macro-level assessment culture are discussed, and implications are drawn.  相似文献   

Making Plans for Michael: providing for a student with moderate learning difficulties in a secondary academy     

Dennis Mays 《Support for Learning》2020,35(1):83-100

The profile of a student with learning difficulties is described and also the learning context in 2017. Previous models of provision are then described in terms of their aetiology with discussion of strengths and shortcomings. Some influential features of curriculum planning and delivery are identified. A model of provision involving specific literacy teaching and differentiation is advocated.  相似文献   

Evaluating the evidence base for evidence-based instructional practices in chemistry through meta-analysis     

Md Tawabur Rahman  Scott E. Lewis 《科学教学研究杂志》2020,57(5):765-793

Investigating the effectiveness of instructional practices provides an evidence base to inform instructional decisions. Synthesizing research studies on instructional effectiveness provides an estimate of the generalizability of effectiveness across settings, along with an exploration of factors that may moderate the impact, which cannot be achieved within individual studies. This study sought to provide a synthesis of evidence-based instructional practices (EBIPs) particular to chemistry through meta-analysis. Ninety-nine studies were analyzed comprising a broader view of chemistry specific studies than past meta-analyses. The results showed that EBIPs feature a demonstrably positive impact on students' academic performance in chemistry, although assessment topic coverage and setting size emerged as relevant moderators of impact and prevented making definitive conclusions of the relative impact of each EBIP. In examining publication bias, an asymmetric distribution of studies based on standard error (SE) and effect size was found, indicative of potential publication bias. To explore the potential impact of bias, the trim and fill method was employed resulting in a range for the overall weighted effect size from 0.29 to 0.62. The study concludes that evidence-based instructional practices have demonstrated effectiveness even in consideration of potential publication bias, as the range of effect sizes remains positive, but highlights the continued need to publish null findings in the research literature.  相似文献