Towards an open university based on machine learning for the teaching service support system using backpropagation neural networks

The combination of information technology and machine learning fuels the rapid evolution of today's educational landscape. Revolutions in both fields and a common goal of improving education drive this transformative journey. In a time when resources and information are more readily available t...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Soft computing (Berlin, Germany) Jg. 28; H. 5; S. 4531 - 4549
1. Verfasser: Wang, Jianjun
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Berlin/Heidelberg Springer Berlin Heidelberg 01.03.2024
Springer Nature B.V
Schlagworte:
Adaptive algorithms
Application of Soft Computing
Artificial Intelligence
Back propagation networks
Colleges & universities
Computational Intelligence
Control
Data analysis
Data mining
Distance learning
Education
Effectiveness
Engineering
Genetic algorithms
Information technology
Machine learning
Mathematical Logic and Foundations
Mechatronics
Neural networks
Online instruction
Resource management
Robotics
Students
Support services
Support systems
Teachers
Teaching
Teaching machines
Teaching support service system
Backpropagation neural network
Development university network
Adaptive genetic algorithm
Machine learning
ISSN:1432-7643, 1433-7479
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The combination of information technology and machine learning fuels the rapid evolution of today's educational landscape. Revolutions in both fields and a common goal of improving education drive this transformative journey. In a time when resources and information are more readily available than ever, traditional teaching strategies are changing to include digital tools that meet the various needs of students. For a teaching services support system (TSS), this paper proposed a novel machine learning-based model that utilizes the powerful backpropagation (BP) neural network, well known for its machine learning and data analysis capabilities. Increasing the effectiveness of online learning is the primary objective of the TSS, which focuses on contributing to a complete learning environment and promoting self-directed learning. This work closely examines the construction and functionality of the BP neural network within the TSS, contribution visions into input–output mechanisms, activation functions, and weight coefficients. This novel approach can bring concerning a digital age educational revolution by increasing the effectiveness and caliber of online learning, rekindling students’ enthusiasm for learning, and making the best use of teaching resources. In addition, the research explores the field of data-mining-based online teaching support services in Open Universities. It clarifies the system’s architecture, which includes virtual teaching modules, resource management, and user authentication. Machine learning methods such as adaptive genetic algorithms and BP neural networks optimize the system’s architecture. Experimental results achieved remarkable BP neural network accuracy and stability, significantly enhancing instructional quality and student engagement. The results show an impressive 83.4% accuracy, outperforming traditional methods such as SVM, KNN, DT, RF, and XGBoost. This demonstrates how learning outcomes and productivity can be enhanced by incorporating machine learning into education.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1432-7643
1433-7479
DOI:10.1007/s00500-024-09639-6