Machine Learning Adoption in Educational Institutions: Role of Internet of Things and Digital Educational Platforms

Li, Jiuxiang; Wang, Rufeng

doi:10.3390/su15054000

Cited by 2 publications

(1 citation statement)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The DSS assists educators in making sound decisions, providing individualized teaching, and improving learning outcomes. This paper [15] examined numerous pedagogical strategies for college English learning systems. It examines the social learning, gamification, and adaptive strategies that may increase student engagement and language learning.…”

Section: Related Workmentioning

confidence: 99%

IoT-enabled Personalized English Learning in Colleges using Big Data Analysis and Decision Support System

2023

Preprint

View full text Add to dashboard Cite

In recent years, the achievements of technology, particularly in the Internet of Things (IoT) and computer technology, have hastened their incorporation into education. To create novel educational opportunities for improving the effects of teaching and learning on management decision-making. On the other hand, this study represents establishing a personalized, IoT-enabled environment for learning college English that employs big data analysis and a decision support system based on a data mining algorithm. Educational analytics generates useful learning outcomes by analyzing provided data, enhancing numerous personalized learning experiences in Chinese, French, and English. The study aims to improve college and university students' English learning experiences using IoT devices, classroom data collection, and data mining techniques. Big data analysis examines the collected data, yielding insightful results that improve real-time customization of English learning experiences. The recommended platform includes an intelligent decision-support system that uses the ARTXP algorithm data mining model based on time series data from English learning resources downloaded by college students to provide each user with personalized educational instructions. The building structure includes a specific information model based on student profiles and preferred learning methods. The site's database of learning resources is available in English knowledge points. The expectation-maximization (E.M.) strategy groups users with similar learning patterns, whereas the recommendation model selects and predicts learning outcomes for adjacent users. The approach employs time series data from English language learning resources and is built on the Cross-Industry Standard Process for Data Mining (CRISP-DM) paradigm. The platform's accuracy, precision, and stability are demonstrated in testing results, emphasizing its ability to significantly boost the efficacy of college English learning.

show abstract

Section: Related Workmentioning

confidence: 99%