Citation: Aberšek, B.; Flogie, A.
Smart Education Systems Supported
by ICT and AI. Appl. Sci. 2023, 13,
10756. https://doi.org/10.3390/
app131910756
Received: 24 September 2023
Accepted: 26 September 2023
Published: 27 September 2023
Copyright: © 2023 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
applied
sciences
Editorial
Smart Education Systems Supported by ICT and AI
Boris Aberšek * and Andrej Flogie
Faculty of Natural Science and Mathematics, University of Maribor, 2000 Maribor, Slovenia; andrej.flogie@um.si
* Correspondence: boris.abersek@um.si
Contemporary society, the society of the future (Industry 4.0 and Society 5.0), will
require us to develop entirely new knowledge, skills and competencies, and consequently,
new ways of teaching and learning. Our aim with this Special Issue is to bring to attention
a form of teaching and learning that transcends these changes’ logic and rhetorical appeal.
Suppose we want to make substantial changes in the education process, whereby the
introduction of ICT and intelligent learning systems are classified as such. In that case,
the current education process must be led to the edge of chaos and then reformulated in
cognitive modeling. Suppose we want to introduce innovation to this process. In that case,
every aspect of the education process and system needs to be studied and reconsidered in
light of new and different social expectations.
The text discusses seven research papers that explore the intersection of education
and technology. These papers aim to address various challenges and improve different
aspects of the education system. Kim et al. [1] focus on the issue of high dropout rates
among university students. Dropout prediction models using machine learning have been
developed to prevent students from leaving their studies. However, meeting the needs
of consulting institutes and academic affairs offices has proven challenging. The authors
propose a Student Dropout Prediction (SDP) system, a hybrid model aiming to increase the
precision and recall rate in predicting dropouts. The model achieved a higher precision
value than existing models, and it also analyzed the reasons for dropping out, providing
valuable insights for counselling and personalized support. Ramírez Villegas et al. [2] ex-
plore the concept of ubiquitous learning in virtual higher education institutions. Ubiquitous
learning refers to learning available at all times and in all places. The paper presents the
U-Learning Model Supported by Learning Experiences and Connective Learning (U-CLX
Model), which measures ubiquitous learning in four dimensions: time, place, medium, and
context. The model provides a framework for assessing the level of ubiquitous learning in
virtual institutions and suggests ways to improve their operations. Apoki and Crisan [3]
discuss personalized adaptive learning, which combines personalized learning and adap-
tive learning to cater to individual needs and facilitate personal development. One of the
critical limitations of existing systems is the need for reusable personalized content and
logic. The paper proposes a modular framework called WASPEC for personalized adaptive
learning. The framework aims to foster the creation of reusable personalized content and
systems that can efficiently share information. An improved architecture, WASPEC 2.0, is
also presented to enhance flexibility. Karakolis et al. [4] focus on bridging the gap between
technological education and job market requirements. Technological professions evolve
rapidly, and higher education institutions often need help to keep up with the changing
skills requirements. The paper presents a skill and course recommender system that helps
learners select courses valuable for the job market. A curriculum design service also rec-
ommends curriculum updates based on job market needs. These services are built on a
text mining service that retrieves job posts and extracts relevant skills. The paper aims
to facilitate optimal decisions for learners and education decision-makers, ensuring that
education aligns with the job market’s needs. Aljohani et al. [5] utilize AI, deep learning,
and big data technologies to predict future market needs for sustainable skills in Saudi
Appl. Sci. 2023, 13, 10756. https://doi.org/10.3390/app131910756 https://www.mdpi.com/journal/applsci