Pub Date : 2024-07-31DOI: 10.1109/TLT.2024.3435979
Christian Gießer;Johannes Schmitt;Emma Löwenstein;Christian Weber;Veit Braun;Rainer Brück
Digital technologies have transformed medical care and education by providing rapid access to knowledge and advanced methods, such as augmented reality and haptic feedback. These technologies are improving the efficiency of healthcare professionals and the quality of medical education. Particularly in Germany, where a shortage of skilled workers and an aging population are increasing pressure on the healthcare system, digital methods can help to optimize workflows and improve training. The integration of haptic feedback in this context makes it possible to make virtual objects tangible, increasing immersion and ultimately learning success. The application presented, SkillsLab+, uses augmented reality and haptic feedback via a data glove to provide a digitized version of the analog SkillsLab medical training programme. SkillsLab+ was evaluated using standardized questionnaires (Igroup Presence Questionnaire, presence, and haptic questionnaires). In order to determine the learning outcomes of the students, an AB test was carried out comparing the final grades. At the same time, a subjective questionnaire was used to assess whether students felt better prepared for the exam. In this context, this article aims to evaluate the learning success and compare the results with the previous proof of concept study of 2022. The results of the comparison show an improvement in the responses to the SkillsLab+ questionnaire in 2023. The result of the examination also improved compared to the group without AR experience. This shows the improvement in application and learning with the help of augmented reality and haptic feedback. They were more confident, had better results, and felt better prepared for the exams.
数字技术通过提供快速获取知识的途径和先进方法(如增强现实和触觉反馈),改变了医疗保健和教育。这些技术正在提高医疗专业人员的工作效率和医疗教育的质量。特别是在德国,熟练工人的短缺和人口老龄化正在增加医疗系统的压力,数字化方法有助于优化工作流程和改善培训。在这种情况下,触觉反馈的集成使虚拟对象变得有形成为可能,增加了沉浸感,最终提高了学习的成功率。所展示的应用软件 SkillsLab+ 通过数据手套使用增强现实技术和触觉反馈,提供了模拟 SkillsLab 医学培训课程的数字化版本。SkillsLab+ 采用标准化问卷(Igroup 临场感问卷、临场感和触觉问卷)进行评估。为了确定学生的学习成果,进行了 AB 测试,比较最终成绩。同时,还使用了主观问卷来评估学生是否感觉为考试做了更好的准备。在此背景下,本文旨在评估学习的成功率,并将结果与之前 2022 年的概念验证研究进行比较。比较结果显示,2023 年学生对 SkillsLab+ 问卷的回答有所改善。与没有 AR 体验的小组相比,考试成绩也有所提高。这表明,在增强现实和触觉反馈的帮助下,应用和学习能力得到了提高。他们更加自信,成绩更好,感觉为考试做了更好的准备。
{"title":"SkillsLab+—A New Way to Teach Practical Medical Skills in an Augmented Reality Application With Haptic Feedback","authors":"Christian Gießer;Johannes Schmitt;Emma Löwenstein;Christian Weber;Veit Braun;Rainer Brück","doi":"10.1109/TLT.2024.3435979","DOIUrl":"10.1109/TLT.2024.3435979","url":null,"abstract":"Digital technologies have transformed medical care and education by providing rapid access to knowledge and advanced methods, such as augmented reality and haptic feedback. These technologies are improving the efficiency of healthcare professionals and the quality of medical education. Particularly in Germany, where a shortage of skilled workers and an aging population are increasing pressure on the healthcare system, digital methods can help to optimize workflows and improve training. The integration of haptic feedback in this context makes it possible to make virtual objects tangible, increasing immersion and ultimately learning success. The application presented, SkillsLab+, uses augmented reality and haptic feedback via a data glove to provide a digitized version of the analog SkillsLab medical training programme. SkillsLab+ was evaluated using standardized questionnaires (Igroup Presence Questionnaire, presence, and haptic questionnaires). In order to determine the learning outcomes of the students, an AB test was carried out comparing the final grades. At the same time, a subjective questionnaire was used to assess whether students felt better prepared for the exam. In this context, this article aims to evaluate the learning success and compare the results with the previous proof of concept study of 2022. The results of the comparison show an improvement in the responses to the SkillsLab+ questionnaire in 2023. The result of the examination also improved compared to the group without AR experience. This shows the improvement in application and learning with the help of augmented reality and haptic feedback. They were more confident, had better results, and felt better prepared for the exams.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"2034-2047"},"PeriodicalIF":2.9,"publicationDate":"2024-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141865662","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-26DOI: 10.1109/TLT.2024.3425959
Andrea Zanellati;Stefano Pio Zingaro;Maurizio Gabbrielli
Academic dropout remains a significant challenge for education systems, necessitating rigorous analysis and targeted interventions. This study employs machine learning techniques, specifically random forest (RF) and feature tokenizer transformer (FTT), to predict academic attrition. Utilizing a comprehensive dataset of over 40 000 students from an Italian university, the research incorporates a range of variables, including demographic information, prior educational metrics, and real-time academic performance indicators. We present a nuanced comparative evaluation of the RF and FTT models, highlighting their predictive accuracy and interpretative capabilities. Our empirical results demonstrate the effectiveness of machine learning in managing student attrition, with FTT models outperforming RF models in terms of predictive accuracy and achieving a sensitivity rate of 81%. Significantly, the inclusion of historical academic data enhances the models' ability to identify students at increased risk of dropping out. Furthermore, we apply advanced explanatory techniques, such as shapley additive explanations, to investigate the discriminative power of these models across different student profiles. This provides valuable insights into the key variables influencing dropout risk, contributing to a more holistic understanding of the issue. In addition, we conduct a fairness analysis to ensure the ethical robustness of our predictive models, making them not only effective but also equitable tools.
{"title":"Balancing Performance and Explainability in Academic Dropout Prediction","authors":"Andrea Zanellati;Stefano Pio Zingaro;Maurizio Gabbrielli","doi":"10.1109/TLT.2024.3425959","DOIUrl":"10.1109/TLT.2024.3425959","url":null,"abstract":"Academic dropout remains a significant challenge for education systems, necessitating rigorous analysis and targeted interventions. This study employs machine learning techniques, specifically random forest (RF) and feature tokenizer transformer (FTT), to predict academic attrition. Utilizing a comprehensive dataset of over 40 000 students from an Italian university, the research incorporates a range of variables, including demographic information, prior educational metrics, and real-time academic performance indicators. We present a nuanced comparative evaluation of the RF and FTT models, highlighting their predictive accuracy and interpretative capabilities. Our empirical results demonstrate the effectiveness of machine learning in managing student attrition, with FTT models outperforming RF models in terms of predictive accuracy and achieving a sensitivity rate of 81%. Significantly, the inclusion of historical academic data enhances the models' ability to identify students at increased risk of dropping out. Furthermore, we apply advanced explanatory techniques, such as shapley additive explanations, to investigate the discriminative power of these models across different student profiles. This provides valuable insights into the key variables influencing dropout risk, contributing to a more holistic understanding of the issue. In addition, we conduct a fairness analysis to ensure the ethical robustness of our predictive models, making them not only effective but also equitable tools.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"2140-2153"},"PeriodicalIF":2.9,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10612222","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141774818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In recent years, there has been an increasing trend of utilizing artificial intelligence (AI) methodologies over traditional statistical methods for predicting student performance in e-learning contexts. Notably, many researchers have adopted AI techniques without conducting a comprehensive investigation into the most appropriate and accurate approach to employ. Additionally, determining the optimal input parameters for each AI technique remains a pertinent question in this domain. This study employs machine learning (ML) and artificial neural networks (ANN) to predict student grades within a programming tutoring system. The experiment involved university students whose interaction data with the e-learning system were analyzed and used for predictions. By identifying the structural relationships between the properties of the input data, this research aims to determine the most efficient AI method for accurately predicting student performance in e-learning systems. The structure of the input data in these systems is described by variables related to individual student activities, so correlations between variables were a natural starting point for further theoretical considerations. In this manner, by applying a filtering technique based on the minimum redundancy–maximum relevance (mrMR) criterion, it was shown that correlations among predictors and between predictors and the target variable play a significant role in defining the appropriate model for predicting student grades. The results showed that ANN (the Levenberg–Marquardt algorithm with Bayesian regularization) outperformed ML methods, achieving the highest prediction accuracy. The results obtained from this study can be of great importance for learning technologies engineering and AI in general.
近年来,利用人工智能(AI)方法而非传统统计方法预测电子学习环境中学生成绩的趋势日益明显。值得注意的是,许多研究人员在采用人工智能技术时,并没有对最合适、最准确的方法进行全面调查。此外,确定每种人工智能技术的最佳输入参数仍然是该领域的一个相关问题。本研究采用机器学习(ML)和人工神经网络(ANN)来预测编程辅导系统中的学生成绩。实验涉及大学生,对他们与电子学习系统的交互数据进行了分析并用于预测。通过确定输入数据属性之间的结构关系,本研究旨在确定最有效的人工智能方法,以准确预测电子学习系统中的学生成绩。这些系统中输入数据的结构是由与学生个人活动相关的变量来描述的,因此变量之间的相关性自然成为进一步理论考虑的出发点。通过这种方式,应用基于最小冗余-最大相关性(mrMR)准则的过滤技术,证明了预测变量之间以及预测变量与目标变量之间的相关性在确定预测学生成绩的适当模型方面起着重要作用。结果表明,ANN(采用贝叶斯正则化的 Levenberg-Marquardt 算法)优于 ML 方法,预测准确率最高。本研究获得的结果对学习技术工程和人工智能具有重要意义。
{"title":"Predicting Student Performance in a Programming Tutoring System Using AI and Filtering Techniques","authors":"Miloš Ilić;Goran Keković;Vladimir Mikić;Katerina Mangaroska;Lazar Kopanja;Boban Vesin","doi":"10.1109/TLT.2024.3431473","DOIUrl":"10.1109/TLT.2024.3431473","url":null,"abstract":"In recent years, there has been an increasing trend of utilizing artificial intelligence (AI) methodologies over traditional statistical methods for predicting student performance in e-learning contexts. Notably, many researchers have adopted AI techniques without conducting a comprehensive investigation into the most appropriate and accurate approach to employ. Additionally, determining the optimal input parameters for each AI technique remains a pertinent question in this domain. This study employs machine learning (ML) and artificial neural networks (ANN) to predict student grades within a programming tutoring system. The experiment involved university students whose interaction data with the e-learning system were analyzed and used for predictions. By identifying the structural relationships between the properties of the input data, this research aims to determine the most efficient AI method for accurately predicting student performance in e-learning systems. The structure of the input data in these systems is described by variables related to individual student activities, so correlations between variables were a natural starting point for further theoretical considerations. In this manner, by applying a filtering technique based on the minimum redundancy–maximum relevance (mrMR) criterion, it was shown that correlations among predictors and between predictors and the target variable play a significant role in defining the appropriate model for predicting student grades. The results showed that ANN (the Levenberg–Marquardt algorithm with Bayesian regularization) outperformed ML methods, achieving the highest prediction accuracy. The results obtained from this study can be of great importance for learning technologies engineering and AI in general.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"1931-1945"},"PeriodicalIF":2.9,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141774820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-24DOI: 10.1109/TLT.2024.3430225
Po-Chun Huang;Ying-Hong Chan;Ching-Yu Yang;Hung-Yuan Chen;Yao-Chung Fan
Question generation (QG) task plays a crucial role in adaptive learning. While significant QG performance advancements are reported, the existing QG studies are still far from practical usage. One point that needs strengthening is to consider the generation of question group