Heterogeneous teaching evaluation network based offline course recommendation with graph learning and tensor factorization

Zhu, Yifan; Lü, Hao; Qiu, Ping; Shi, Kaize; Chambua, James; Niu, Zhendong

doi:10.1016/j.neucom.2020.07.064

Cited by 84 publications

(51 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In summary, it can be seen that most of the current models of teaching music in the college music teaching classroom do not involve intelligent algorithms based on the high and low differentiation of student group characteristics [ 21 ]. On the other hand, although a lot of basic research has been done in China on music teaching classroom teaching in colleges and universities, less research has been done on quantitative assessment of music teaching classroom teaching ability in combination with intelligent algorithms [ 22 ], and there are also no research and application of unified assessment models for the quality of teaching in music teaching classrooms in colleges and universities in terms of objectivity [ 23 ].…”

Section: Related Workmentioning

confidence: 99%

[Retracted] Compensated Fuzzy Neural Network‐Based Music Teaching Ability Assessment Model

Chen

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

College is the main place to carry out music teaching, and it is important to assess the music teaching ability in college effectively. Based on this, this paper firstly analyzes the necessity of music teaching ability assessment and briefly summarizes the application of neural network and deep learning technology in music teaching ability assessment and secondly designs an assessment model based on compensated fuzzy neural network algorithm and analyzes the accuracy of the model, finds out the causes of forming abnormal output by analysing the general dimensional conditions of the algorithm of the model, and proposes corresponding correction. Finally, the reliability and feasibility of the music teaching ability assessment model were experimentally verified by combining with teaching practice. The research results confirm the feasibility of the compensated fuzzy neural network algorithm in music teaching ability assessment, which has important reference significance for improving the quality of music teaching in colleges and universities.

show abstract

Section: Related Workmentioning

confidence: 99%

[Retracted] Compensated Fuzzy Neural Network‐Based Music Teaching Ability Assessment Model

Chen

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…The competency model assessment system is shown in Assessment of KS for the competence indicator (project module) (10) Evaluation of criteria for the competence indicator in the project (11) Assessment of the competence indicator (12) Assessment of competence (13) The evaluation of competences (competence) (14) The discipline, in general, contains a set of project modules and their corresponding KS modules. The assessment of each set (project module -KS module) coincides with the assessment of the competency indicator.…”

Section: Description Of the System Of Competency Indicators And Theirmentioning

confidence: 99%

“…However, a significant drawback of this approach can be called the attachment of research results to a specific training system. Summing up, we can formulate the following requirements for the developed model for assessing the achievement of competencies [10][11][12]: 1. Indicators of achievement of competencies should cover all types of activities in the process of which the development of competencies occurs.…”

Section: Introduction Development Of a Competency Modelmentioning

confidence: 99%

Soft models of competence assessment in professional education

2020

View full text Add to dashboard Cite

The article presents the results of research on the problem of finding new models for assessing students ' competencies in the context of global trends in modern professional education – the merger of competence and project approaches, the development of e-learning, and the introduction of digital technologies to support expert systems. An original development of one of the soft models of fuzzy multiparametric assessment of competencies is proposed, and the mathematical apparatus of the model is described taking into account the requirements of fuzzy logic.

show abstract

“…al. applied a Bayesian probabilistic tensor factorization on a three-dimensional tensor from network structured features and interactive activities [24]. Similarity-based methods aim to consider the responses of the nearest neighbors to a target as the target's response.…”

Section: Introductionmentioning

confidence: 99%

Undergraduate Grade Prediction in Chinese Higher Education Using Convolutional Neural Networks

Zhang

Cui

et al. 2021

LAK21: 11th International Learning Analytics and Knowledge Conference

View full text Add to dashboard Cite

Prediction of undergraduate grades before their course enrollments is beneficial to the student's learning plan on selective courses and failure warnings to compulsory courses in Chinese higher education. This study proposed to use a deep learning-based model composed of sparse attention layers, convolutional neural layers, and a fully connected layer, called Sparse Attention Convolutional Neural Networks (SACNN), to predict undergraduate grades. Concretely, sparse attention layers response to the fact that courses have different contributions to the grade prediction of the target course; convolutional neural layers aim to capture the one-dimensional temporal feature on these courses organized in terms; the fully connected layer is to complete the final classification based on achieved features. We collected a dataset including grade records, student's demographics and course descriptions from our institution in the past five years. The dataset contained about 54k grade records from 1307 students and 137 courses, where all mentioned methods were evaluated by the hold-out evaluation. The result shows SACNN achieves 81% prediction precision and 85% accuracy on the failure prediction, which is more effective than those compared methods. Besides, SACNN delivers a potential explanation to the reason of the predicted result, thanks to the sparse attention layer. This study provides a useful technique for personalized learning and course relationship discovery in undergraduate education. CCS CONCEPTS• Computing methodologies → Machine learning; Artificial intelligence; • Human-centered computing → Collaborative and social computing; • General and reference → Cross-computing tools and techniques.

show abstract

Heterogeneous teaching evaluation network based offline course recommendation with graph learning and tensor factorization

Cited by 84 publications

References 41 publications

[Retracted] Compensated Fuzzy Neural Network‐Based Music Teaching Ability Assessment Model

[Retracted] Compensated Fuzzy Neural Network‐Based Music Teaching Ability Assessment Model

Soft models of competence assessment in professional education

Undergraduate Grade Prediction in Chinese Higher Education Using Convolutional Neural Networks

Contact Info

Product

Resources

About