A Semi-supervised Learning-Based Diagnostic Classification Method Using Artificial Neural Networks

Xue, Kang; Bradshaw, Laine

doi:10.3389/fpsyg.2020.618336

Cited by 7 publications

(5 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CDAs involve (1) analyzing the test items and identifying cognitive skills involved, and (2) mathematical modeling of test takers’ skill mastery patterns according to their responses to the test and the identified cognitive skills. Recent years have witnessed the development of a variety of cognitive diagnosis models (CDMs) and their application to educational assessment (e.g., Liu et al, 2018 ; Aryadoust, 2021 ; He et al, 2022 ; Min et al, 2022a , b ), including the rule space model, the tree-based regression, the FUSION Model, G-DINA, ACDM, C-RUM, DINO, DINA, RRUM, G-DINA, the deep CDM, the sequential hierarchical CDM, and the semi-supervised learning ANN for diagnostic classification ( Zhang and Wang, 2020 ; Xue and Bradshaw, 2021 ; Gao et al, 2022 ).…”

Section: Literature Reviewmentioning

confidence: 99%

Exploring the relationship between metacognitive awareness and Chinese EFL learners’ listening skills

Wang

Min

et al. 2023

Front. Psychol.

View full text Add to dashboard Cite

Listening causes great difficulties for EFL learners and little is known concerning the contribution of EFL learners’ metacognitive awareness to their listening performance and to their mastery of listening subskill. In the present study, the Metacognitive Awareness Listening Questionnaire (MALQ) and an in-house listening test were used to collect data from 567 Chinese EFL college students. The G-DINA package in R was adopted to identify students’ mastery patterns of listening subskills. The correlations of test takers’ MALQ results and their listening scores and listening subskills mastery probability were analyzed, respectively, to investigate how test participants’ metacognitive awareness relates to their language proficiency and listening subskills. According to the study, learners’ metacognitive awareness has a significant positive relationship with their listening performance at overall and subskills levels. The findings of the study provide additional evidence for using the MALQ as an instrument to interpret learners’ metacognitive awareness of listening strategies. It is thus recommended that theorists and language teachers involve metacognitive awareness of strategies in listening instructions.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Exploring the relationship between metacognitive awareness and Chinese EFL learners’ listening skills

Wang

Min

et al. 2023

Front. Psychol.

View full text Add to dashboard Cite

show abstract

“…The research goal of semisupervised learning is to understand how combining labeled and unlabeled data can change the machine learning behavior and allow for the design of algorithms that take advantage of such a combination. Xue and Bradshaw (2021) first provided a semisupervised learning ANN method for CDM. The semisupervised learning architecture could refine the classification accuracy based on the initial classification obtained from two more constrained DCMs (i.e., DINA and DINO models).…”

Section: Artificial Neural Network and Semisupervised Learningmentioning

confidence: 99%

“…As one subfield of machine learning, ANNs (Goodfellow et al, 2016) have been proposed as an attractive approach to convert a pattern of item responses into latent variables (Cui et al, 2016; Cui et al, 2017; Paulsen, 2019; Xue & Bradshaw, 2021). In the current project, semisupervised learning ANNs are introduced into the IRT research area.…”

Section: Introductionmentioning

confidence: 99%

Semisupervised Learning Method to Adjust Biased Item Difficulty Estimates Caused by Nonignorable Missingness in a Virtual Learning Environment

Xue

Huggins-Manley

Leite

2021

Educational and Psychological Measurement

Self Cite

View full text Add to dashboard Cite

In data collected from virtual learning environments (VLEs), item response theory (IRT) models can be used to guide the ongoing measurement of student ability. However, such applications of IRT rely on unbiased item parameter estimates associated with test items in the VLE. Without formal piloting of the items, one can expect a large amount of nonignorable missing data in the VLE log file data, and this is expected to negatively affect IRT item parameter estimation accuracy, which then negatively affects any future ability estimates utilized in the VLE. In the psychometric literature, methods for handling missing data have been studied mostly around conditions in which the data and the amount of missing data are not as large as those that come from VLEs. In this article, we introduce a semisupervised learning method to deal with a large proportion of missingness contained in VLE data from which one needs to obtain unbiased item parameter estimates. First, we explored the factors relating to the missing data. Then we implemented a semisupervised learning method under the two-parameter logistic IRT model to estimate the latent abilities of students. Last, we applied two adjustment methods designed to reduce bias in item parameter estimates. The proposed framework showed its potential for obtaining unbiased item parameter estimates that can then be fixed in the VLE in order to obtain ongoing ability estimates for operational purposes.

show abstract

“…16 Semi-supervised learning merges the labeled data with a great deal of unlabeled data when being trained. 17 This can dramatically improve the accuracy of learning. 18 In unsupervised learning, no labeled data exist, and therefore, a machine is able to identify any possible patterns in the training data.…”

Section: Introductionmentioning

confidence: 99%

“…The collection of labeled data for supervised learning basically needs skilled human agents and experiments 16 . Semi‐supervised learning merges the labeled data with a great deal of unlabeled data when being trained 17 . This can dramatically improve the accuracy of learning 18 .…”

Section: Introductionmentioning

confidence: 99%

Applications, functions, and accuracy of artificial intelligence in restorative dentistry: A literature review

Tabatabaian

Vora

Mirabbasi

2023

J Esthet Restor Dent

View full text Add to dashboard Cite

ObjectiveThe applications of artificial intelligence (AI) are increasing in restorative dentistry; however, the AI performance is unclear for dental professionals. The purpose of this narrative review was to evaluate the applications, functions, and accuracy of AI in diverse aspects of restorative dentistry including caries detection, tooth preparation margin detection, tooth restoration design, metal structure casting, dental restoration/implant detection, removable partial denture design, and tooth shade determination.OverviewAn electronic search was performed on Medline/PubMed, Embase, Web of Science, Cochrane, Scopus, and Google Scholar databases. English‐language articles, published from January 1, 2000, to March 1, 2022, relevant to the aforementioned aspects were selected using the key terms of artificial intelligence, machine learning, deep learning, artificial neural networks, convolutional neural networks, clustering, soft computing, automated planning, computational learning, computer vision, and automated reasoning as inclusion criteria. A manual search was also performed. Therefore, 157 articles were included, reviewed, and discussed.ConclusionsBased on the current literature, the AI models have shown promising performance in the mentioned aspects when being compared with traditional approaches in terms of accuracy; however, as these models are still in development, more studies are required to validate their accuracy and apply them to routine clinical practice.Clinical Significance: AI with its specific functions has shown successful applications with acceptable accuracy in diverse aspects of restorative dentistry. The understanding of these functions may lead to novel applications with optimal accuracy for AI in restorative dentistry.

show abstract

A Semi-supervised Learning-Based Diagnostic Classification Method Using Artificial Neural Networks

Cited by 7 publications

References 31 publications

Exploring the relationship between metacognitive awareness and Chinese EFL learners’ listening skills

Exploring the relationship between metacognitive awareness and Chinese EFL learners’ listening skills

Semisupervised Learning Method to Adjust Biased Item Difficulty Estimates Caused by Nonignorable Missingness in a Virtual Learning Environment

Applications, functions, and accuracy of artificial intelligence in restorative dentistry: A literature review

Contact Info

Product

Resources

About