Analysis and Summarization of the Experience of Developing Adaptive
Learning Systems in Higher Education
Kateryna P. Osadcha
1 a
, Viacheslav V. Osadchyi
1 b
, Vladyslav S. Kruglyk
1 c
Oleg M. Spirin
2,3 d
Bogdan Khmelnitsky Melitopol State Pedagogical University, 20 Hetmanska Str., Melitopol, 72300, Ukraine
University of Educational Management, 52A Sichovykh Striltsiv Str., Kyiv, 04053, Ukraine
Institute for Digitalisation of Education of the National Academy of Educational Sciences of Ukraine, 9 M. Berlynskoho
Str., Kyiv, 04060, Ukraine
Model of Adaptive Learning System, Adaptive Learning, Adaptive Learning System, Higher Education,
Personification of Learning, Professional Training, Individualization of Learning.
The article provides a brief analysis and summarization of the existing experience of developing adaptive
learning systems in higher education. Existing models of adaptive learning systems, which are necessary
for the educational process in higher education, are analyzed. Conclusions are made as for the requirements
for the design and modeling of the author’s adaptive system of future specialists’ professional training in a
blended learning environment. The main ones are requirements for the approaches to modeling, types of
adaptation implemented in the system, ways to ensure individualization and personification in the process of
both face-to-face learning and learning with the help of information and communication technologies.
In terms of socio-economic and evolutionary changes
in the society, science and technology modern edu-
cational process in higher education requires appro-
priate changes (Ryabinova, 2009) and modifications
of learning strategies. Among promising and rele-
vant technologies in education today there are adap-
tive learning technologies that help the educational
system to adapt to the specific features and needs of a
student and are typically controlled by the computa-
tional devices, adapting content for different learners’
needs and sometimes preferences (Shute and Zapata-
Rivera, 2007). With the rapid development of the ar-
tificial intelligence in education (Abuselidze and Ma-
maladze, 2021), adaptive learning system has become
the trend of web-based e-learning system (Chen and
Zhang, 2008).
Research and implementation of adaptive learn-
ing technologies has contributed to the development
of the adaptive learning system. Adaptive learning
system is a platform for individual learning, which
uses different techniques of artificial intelligence to
adapt instruction to the learner’s individual differ-
ences, such as the learning ability, preferences, learn-
ing style and learning goal etc. (Chen and Zhang,
Since the emergence and development of adap-
tive learning technologies, scientists have proposed
various models of adaptive learning systems: KFS
(Knowledge Flow Structure), which is based on the
concept of knowledge flow (Kurgan, 2013); DCM
(Dynamic Content Model), which uses a concept
map for the organization and presentation of knowl-
edge (Kristensen et al., 2007); model, designed by
Solovov (Solovov, 2010), the main concepts of which
are the educational element, content graph and spec-
ification of educational elements (de Marcos et al.,
2007); CDCGM (Competency-Driven Content Gen-
eration Model), which is focused on the availability of
all training materials for the electronic training course
developer; this materials are stored in the form of ed-
ucational units related to the competence bank; SHM
(Structural-Hierarchical Model), which provides tools
for describing the didactic structure of educational
units (Silkina and Sokolinsky, 2016). On the other
hand, Oxman and Wong (Oxman and Wong, 2014)
Osadcha, K., Osadchyi, V., Kruglyk, V. and Spirin, O.
Analysis and Summarization of the Experience of Developing Adaptive Learning Systems in Higher Education.
DOI: 10.5220/0010930000003364
In Proceedings of the 1st Symposium on Advances in Educational Technology (AET 2020) - Volume 2, pages 208-215
ISBN: 978-989-758-558-6
2022 by SCITEPRESS Science and Technology Publications, Lda. All rights reserved
prove that the use of adaptive learning in higher ed-
ucation has been slower to develop, and challenges
that likely contributed to slow adoption remain. It
is facilitated by partnerships between publishers and
adaptive learning companies. In 2010, Knewton ex-
panded beyond its initial GMAT prep product to part-
ner with large universities to create adaptive remedial
math education courses. In 2013 Career Education
Corporation partnered with CCKF (international edu-
cation technology firm) to build 300 adaptive courses
using its adaptive learning system RealizeIt. In 2017,
the University of Central Florida and Colorado Tech-
nical University partnered with RealizeIt to explore
how best to use an adaptive learning platform to in-
crease student success (Dziuban et al., 2017).
Despite the development of adaptive technologies,
a review of previous research works has shown that
a system that combines the capabilities of adaptive
technologies, individualization and personification in
the conditions of blended learning in a higher educa-
tional institution has not been modeled and developed
yet. Such a system is needed to improve the train-
ing of future professionals, which is becoming more
technological, student-centered and variable. In or-
der to develop a new adaptive learning system, it is
advisable to analyze and summarize the existing ex-
perience of adaptive learning systems development in
higher education. This is the aim of our research,
oriented for the identification of the requirements for
the design and modeling of our own adaptive learning
system for future professionals’ training in a blended
learning environment.
Methods of research:
methods of specification and systematization of
theoretical knowledge were used for the develop-
ment of the research objectives
methods of analysis and summarization of
psycho-educational, specialized and technical
sources on the use of adaptive learning technolo-
gies in order to identify the structure and charac-
teristics of existing adaptive learning systems and
requirements for our own adaptive system of in-
dividualization and personification of future pro-
fessionals’ training in a blended learning environ-
3.1 Analysis of Existing Adaptive
Systems in Higher Education
Using the search tools of Google Scholar, ERIC, Web
of Science and Scopus, we were searching for sci-
entific papers on the development of adaptive learn-
ing systems which could be used in higher education.
We highlighted those that were publicly available:
60,462 in ERIC, 92 in Web of Science, 183 in
Scopus. Of the 2,780,000 articles in Google Scholar,
we singled out articles by Russian and Ukrainian au-
thors. We analyzed studies representing the devel-
opment of adaptive learning systems (platforms) in
higher education.
Burdaev (Burdaev, 2006) proposed an adaptive
system EOS “KARKAS”, which is aimed at training
and testing of students of economic specialties. It in-
cludes the following components: an output machine
to provide training; output machine for adaptive test-
ing; learner error analyzer. This system contains a
number of models: 1) a model of learning, character-
ized by the following parameters: learning objectives;
types of errors occurring during the assessment tasks
execution; time of the assessment tasks execution;
need for assistance while executing a task; 2) models
of the learners, characterized by the following param-
eters: psychological type of students’ behavior; level
of students’ intellectual development; level of readi-
ness for the subject under research; motivation. The
adaptability of learning in EOS “KARKAS” is real-
ized in the fact that at each checkpoint a selection of
the learning model takes place depending on the level
of learner’s knowledge. As a result, such parameters
as sequence, depth and forms of content presentation
are modified.
The structure of Pedagogically Adaptive Learning
System based on Learning Styles, designed by Sia-
daty and Taghiyareh (Siadaty and Taghiyareh, 2007),
includes the domain knowledge module, the learner
model, the pedagogical module and the interface
module (figure 1).
The domain model is a knowledge representation
of the materials that the learner has to learn and in-
cludes a set of domain concepts such as facts, lessons
and problems forming a kind of semantic network.
The learner model is a hybrid model, i.e., it consists
of a stereotype model (which classifies the learners
based on their entry behaviors or characteristics) and
an overlay model (which is used to represent users’
knowledge of the concepts of the subject domain).
The pedagogical module assumes responsibility for
making decisions about what will be learned, how it
Analysis and Summarization of the Experience of Developing Adaptive Learning Systems in Higher Education
Figure 1: Architecture of the system (Siadaty and Taghiyareh, 2007).
will be learned, when it will be learned. The inter-
face module delivers the personalized contents to the
learners and receives their feedback as well.
The adaptive learning system, proposed by Chen
and Zhang (Chen and Zhang, 2008), is oriented for
learning style and cognitive state. Its architecture is
comprised of the media space, domain model, learner
model, instruction model, adaptive model and user
interface. Media space includes the instructional re-
sources database (all kinds of teaching materials, such
as text, picture, audio, video, cartoon, etc.) and in-
structional resources description models (teaching re-
sources by SCORM standard). Domain Model is
the repository of storing and structuring the instruc-
tional content in the particular domain, such as a
course. Domain Model includes the learning objec-
tives hierarchy and domain ontology. Learner Model
is used to provide a foundation for diagnosing the
learning process, providing the adaptive learning sup-
port for learners. Instruction Model is used to simu-
late the teacher’s teaching strategies; it stores the spe-
cific teaching rules. Adaptive model stores the adap-
tive rules of the system, including the content adapta-
tion rules and adaptive navigation support rules. User
Interface provides the interaction function between
learners and adaptive learning system.
The adaptive distance learning system, proposed
by Gorohovskiy and Troyanovskaya (Gorohovskiy
and Troyanovskaya, 2015), includes the following
modules: module for collecting data on student’s ac-
tivities (to provide primary data on direct and indirect
assessment); module for issuing methodical materi-
als, which directly displays a lecture or practical ma-
terials; automatic module for data processing and is-
suance of material for processing primary evaluation
data and appropriate selection of training materials
and assessment elements (figure 2). In this compo-
sition, it suits the peculiarities of student’s perception
of educational material.
Red (Red, 2010) described RATOS-AI, an intelli-
gent adaptive system for the development and main-
tenance of distance learning courses, consisting of
the following elements: 1) module for each role
of a teacher (teacher-methodologist module, teacher-
consultant or tutor module, teacher-designer of train-
ing courses module); 2) core IASDL of RASOS-AI;
3) four knowledge bases (subject area, separate aca-
demic course, reference model of knowledge, current
model of pharmacist’s knowledge), database of train-
ing protocols, database of electronic publications and
database of training scenarios; 4) information sys-
tem of monitoring of learning; 5) repository of edu-
cational elements; 6) training system and assessment
system module; 7) systems of communication and ac-
cess to the single information space of University, as
well as the subsystem “Dean’s Office”.
The adaptive system of distance learning and
knowledge assessment EduPRO, presented by Fe-
doruk (Fedoruk, 2010), includes a model of lecture
material structuring, model of adaptive testing and a
model of decision-making on transitions between lev-
els of complexity in the adaptive testing system. The
system makes it possible to organize the process of
individualized learning, allowing teachers to form an
individual structure of educational material and iden-
tify the moment of students’ readiness for the transi-
tion to a more complicated level of material.
Information and training system ICT PROFF
(Huang and Shiu, 2012) uses modified psychologi-
cal tests adapted to the computer procedure of inter-
viewing respondents with automatic calculation of the
coefficients of personalized models of learning mate-
AET 2020 - Symposium on Advances in Educational Technology
Figure 2: Technological structure of adaptive distance learning system (Gorohovskiy and Troyanovskaya, 2015).
rial and subsequent calculation of external support of
the learning process. ICT PROFF system basically
uses a modern intelligent CAD software environment
MVTU version 3.0, designed for detailed analysis and
study of dynamic processes in technical, economic
and social systems. The developed adaptive system
of personalized professional training of students al-
lows building the predicted trajectories of knowledge
mastering for each student that can be used for the
formation of homogeneous educational groups.
User-centric adaptive learning system was de-
signed by Huang and Shiu (Huang and Shiu, 2012).
It uses sequential pattern mining to construct adaptive
learning paths based on users’ collective intelligence
and employs Item Response Theory (IRT) with col-
laborative voting approach to estimate learners’ abili-
ties for recommending adaptive materials. Such adap-
tive learning, which is oriented for the user, is com-
parable to expert-designed learning and learners are
more satisfied and learn efficiently. The system archi-
tecture is illustrated in figure 3.
Vlasenko (Vlasenko, 2014) has described an
adaptive distance learning system in the field of in-
formation technology, which is based on the basic
components used in existing distance learning sys-
tems, namely: blocks (diagnostics of the initial level
of knowledge, formulation of learning objectives, de-
sign and correction of curriculum, testing, model de-
sign, formation of educational elements, correction of
model, assessment of achievements); databases (per-
sonal test tasks, entry-level test knowledge tasks, test
tasks to assess learning outcomes), models (learner
model, adaptation model). Adaptation of the system
to the learner is carried out on the basis of a model
which, in addition to standard parameters, includes
such parameters as the degree of learning outcomes
achievement, system of learner’s advantages, individ-
ual curriculum, etc. Adaptation at the stage of plan-
ning teaching is carried out by developing a curricu-
lum that, on the one hand, meets learner’s needs and
preferences and, on the other hand, provides training
which is appropriate to the competency model and
therefore meets the labor market requirements.
Yasuda et al. (Yasuda et al., 2015) offered adap-
Analysis and Summarization of the Experience of Developing Adaptive Learning Systems in Higher Education
5. Post-test stage (Steps 18~21): If the learning-path agent senses that the learner has already finished the entire
learning path, it notifies the test agent to provide post-test questions for the learner.
Figure 1. System architecture and operation procedure
Adaptive navigation support
The system collects user-created teaching materials from Web pages and blogs and divides these materials into
concept units. When users share their knowledge on the Web, they usually arrange concept units in order, like a list
or a catalog, based on their cognitions about domain knowledge. Each user-created teaching material presents a
concept sequence, which represents the user’s notion of learning order. The system discovers the concept sequences
that frequently occur in user-created materials. Thus, frequent concept sequences are collaboratively decided by
Internet users. The discovered sequential patterns are a kind of collective intelligence and are used to support
adaptive navigation.
Concept sequences analysis
The following example demonstrates the way to find concept-sequence patterns. Assume that five materials about
C++ programming are collected; then, the frequent concept sequences are generated by the following steps:
1. The concept order in each material is presented as a sequence. Table 1 shows the concept sequences in the five
2. Find frequent 1-itemset in which all the items’ support levels are higher than the threshold. In this example, the
minimum support is set to 40%, which means that the concept which appears at least twice in the five materials
will be a frequent concept.
3. If a concept is not included in frequent 1-itemset, it can be deleted; on the contrary, frequent concepts are
mapped to assigned numbers for analysis (see Table 2). Table 3 shows the concept sequences after mapping.
4. Use frequent 1-itemset to find other frequent sequences with different lengths. The GSP algorithm is employed
to generate candidate sequences and frequent sequences. Finally, the algorithm returns the maximal sequences.
Table 4 shows all frequent sequences and the sequences < 1 5 > and < 1 2 3 4 > are the maximal sequences.
Table 1. An example of concept sequences
Material ID Concept sequence
1 < data type, overload >
2 < introduction, data type, process control, class & object, function >
3 < data type, string & reference, class & object >
4 < data type, process control, class & object, function, overload >
5 < overload >
Figure 3: User-centric adaptive learning system architecture and operation procedure (Huang and Shiu, 2012).
tive learning system using a Bayesian network (fig-
ure 4). The system has 2 modes: testing mode and
learning mode. The testing mode gauges learners’
understanding in each course unit using the Expected
Value of Network Information (EVINI)-based adap-
tive testing scheme. In the proposed system, the learn-
ing mode assigns each learner drills on course units
that the learner is not good at. The Bayesian net
framework is used to calculate expected value of net-
work information. The configuration of the proposed
system includes such structural elements: the WEB
application server that runs HTML5-based drill con-
tents for both modes; Bayesian net server that infers
the probability that the learner has understood each
of the not-yet-set units, by examining the accuracy
of previous answers; the database server that stores
learners’ logs, which contain each learner’s drill an-
The developers included the following elements
into the adaptive information learning system (Fe-
dusenko et al., 2017): a subsystem of learning (sub-
system of working with D-graph, subsystem of work-
ing with student model), subsystem of knowledge as-
sessment (subsystem of task design, subsystem of as-
sessment), knowledge base and database. Its use al-
lows increasing the efficiency and quality of educa-
tion by selecting an individual learning path for each
To study a foreign language, an adaptive auto-
mated system Arcturus” was developed (Skliarova,
2016). It solves a number of tasks related to the au-
tomation of the processes of foreign language com-
petence development. The system has the following
features: differentiation of its elements according to
the level of complexity; automation of the process of
test tasks design with different levels of complexity;
multi-criteria methods for the evaluation of education
quality; methods for evaluating student’s psychophys-
ical characteristics while learning with the help of this
system; tools for modeling the process of student’s in-
dividual path in learning a foreign language; methods
for enhancing the quality of optimal control of the in-
dividual learning path; tools of control flow statement
of educational process of system; development of al-
gorithm of system functioning.
The system, proposed by Shershneva et al. (Sher-
shneva et al., 2018), is aimed at teaching mathematics.
This system consists of a subject area module, user
model (information about student, which is needed
to adapt educational content to his or her individ-
ual characteristics and monitor the learning process
in the electronic environment), adaptation model (au-
tomated navigation system and adaptation of educa-
tional content based on learner’s individual character-
istics), and model of learning outcomes assessment
(identification of the level of student’s subject com-
petence through the assessment of all its components)
(figure 5). The authors of this system state that it is a
universal system and it can serve as a basis for the or-
ganization of adaptive learning in the electronic envi-
ronment not only in the field of mathematics but also
in other disciplines of educational programs in vari-
ous fields of training in secondary, higher and extra-
curriculum education.
According to Toktarova and Fedorova (Toktarova
and Fedorova, 2020) in order to train students in
mathematics in the information-educational environ-
ment it is recommended to introduce such adaptive
system which is based on the adaptation of train-
ing to students’ individual features, management of
learning process in the information-educational en-
vironment, use of mobile devices for training, and a
AET 2020 - Symposium on Advances in Educational Technology
Figure 4: Conceptual model of adaptive information system (Yasuda et al., 2015).
Figure 5: Structural scheme of the adaptive system of web-based teaching (Shershneva et al., 2018).
set of educational-methodological and technological
3.2 Identification of Requirements for
an Adaptive System of
Individualization and
Personalization of Future
Specialists’ Professional Training in
a Blended Learning Environment
Based on the analysis of the above mentioned models
of adaptive systems, we have identified the follow-
ing requirements for an adaptive system of individual-
ization and personalization of future specialists’ pro-
fessional training in a blended learning environment.
The system should:
1) be based on polyparadigmatic and systematic ap-
proaches to its modeling, which involve the use
of an open cluster of approaches to learning, their
integrated application in a structure of intercon-
nected subsystems;
2) provide the adaptation of educational materi-
als, learning outcomes monitoring, devices (PC,
smartphone, tablet computer), and face-to-face
classes to the students’ individual characteristics;
3) enhance a learner-centered approach in the pro-
cess of both face-to-face learning and learning
with the help of information and communication
technologies; in order to implement this system
the following should be done: automated study of
student’s individual features, tutoring and support
of student’s individual educational program, indi-
vidualization of learning process, development of
student’s individual features and his or her new
characteristics according to personal educational
needs, monitoring and recording of student’s in-
dividual progress;
4) provide the personalization of the electronic edu-
cational environment as well as learning environ-
Analysis and Summarization of the Experience of Developing Adaptive Learning Systems in Higher Education
5) include both modern educational technologies (in-
teractive methods, intensification, project work
and creative learning, etc.) and information
and communication technologies (distance learn-
ing technologies, analysis and processing of big
amount of data) for future specialists’ profes-
sional training in a higher educational establish-
6) include subsystems that characterize certain areas
of future professionals’ training (adaptation, indi-
vidualization, personalization of training) and re-
flect the mixed nature of training;
7) be implemented as a working prototype of an
adaptive system for different groups of stakehold-
ers and use an adaptive system for individualiza-
tion and personalization of future professionals’
training in a blended learning environment.
Based on the analysis of the existing adaptive
technologies (Osadcha et al., 2020) and ICT for indi-
vidualization (Kruglik and Chorna, 2020) and person-
ification (Osadchyi and Krasheninnik, 2020) of train-
ing and in order to implement the requirements for
the system, we can conclude that it is appropriate to
implement the following learning tools in an adaptive
system of individualization and personalization of fu-
ture specialists’ professional training in the context
of blended learning: Moodle platform and plug-ins
for adaptive learning, capabilities and properties of
Moodle for the implementation of individualization
of learning (competence module and progress block,
tools for imposing necessary restrictions on learning
elements, means of multicriteria assessment, tools for
multivariate presentation of educational information,
etc.), a set of information and communication tech-
nologies and modern technical means of learning to
ensure the personification of learning. This will al-
low us to design an adaptive system of individualiza-
tion and personalization of future professionals’ pro-
fessional training in a blended learning environment,
which will consequently promote the impact of dis-
tance technologies on the improvement and intensifi-
cation of learning in higher educational institutions.
Analysis of adaptive learning systems and their mod-
els showed that these solutions have a narrow applied
character (teaching mathematics, languages or teach-
ing students of a particular specialty). They do not
contain all necessary elements for educational pro-
cess organization or do not have the structural ele-
ments and functional features required by teachers
and students in the modern educational process. We
have also generalized the requirements for the adap-
tive system of individualization and personalization
of future specialists’ professional training in the con-
ditions of blended learning. These requirements are
as follows: system modeling has to be done accord-
ing to polyparadigmatic and systematic approaches;
it should take into account the tasks of adaptation,
individualization and personalization of future pro-
fessionals’ training; the system should be structured
in accordance with the functional purpose of its ele-
ments; the system should be implemented in the form
of a working prototype based on the Moodle platform
tools. The adaptive learning system should be easy
to use in the process of learning, have an intuitive in-
terface and appropriate structure, as well as the tools
which are necessary for future professionals’ effective
This research was funded by a grant from the Ministry
of Education and Science of Ukraine (0120U101970).
Abuselidze, G. and Mamaladze, L. (2021). The impact of
artificial intelligence on employment before and dur-
ing pandemic: A comparative analysis. Journal of
Physics: Conference Series, 1840(1):012040.
Burdaev, V. P. (2006). Adaptive learning system in
EOS “KARKAS”. Artificial Intelligence, (3):458–
467. 2006 3/
Razdel6/01 Burdaev.pdf.
Chen, S. and Zhang, J. (2008). The adaptive learning sys-
tem based on learning style and cognitive state. In
2008 International Symposium on Knowledge Acqui-
sition and Modeling, pages 302–306.
de Marcos, L., Pages, C., Martinez, J.-J., and Gutierrez,
J.-A. (2007). Competency-based learning object se-
quencing using particle swarms. In 19th IEEE In-
ternational Conference on Tools with Artificial Intel-
ligence(ICTAI 2007), volume 2, pages 111–116.
Dziuban, C., Howlin, C., Johnson, C., and Moskal,
P. (2017). An adaptive learning partnership.
Fedoruk, P. (2010). The use of the EduPRO system for
adaptive learning process organizing. In Proceedings
of the 8th IASTED International Conference on Web-
Based Education, WBE 2010, pages 7–11.
Fedusenko, O. V., Fedusenko, A. O., and Domanetska, I. M.
(2017). Conceptual model of adaptive learning infor-
AET 2020 - Symposium on Advances in Educational Technology
mation system. Upravlinnia rozvytkom skladnykh sys-
tem, 32:86–90.
Gorohovskiy, A. and Troyanovskaya, T. (2015). Informa-
tion technology for building the adaptive system of
distance learning. Scientific Works of Vinnytsia Na-
tional Technical University, (2). https://works.vntu.
Huang, S.-L. and Shiu, J.-H. (2012). A User-Centric Adap-
tive Learning System for E-Learning 2.0. Journal
of Educational Technology & Society, 15(3):214–225. 3/16.pdf.
Kristensen, T., Lamo, Y., Mughal, K., Tekle, K. M., and
Bottu, A. K. (2007). Towards a dynamic, content
based e-learning platform. In Proceedings of the 10th
IASTED International Conference on Computers and
Advanced Technology in Education, CATE ’07, page
107–114, USA. ACTA Press.
Kruglik, V. S. and Chorna, A. V. (2020). Using the Moodle
platform to individualize the training of future profes-
sionals in a blended learning environment. In Informa-
tion technologies in education, science and technol-
ogy: theses add. V International Scientific-practical
Conf. (Cherkasy, May 21-23, 2020), pages 159–160.
Cherkasy State Technological University, Cherkasy.
Kurgan, G. S. (2013). Cloud technologies of inter-
net education based on the knowledge repre-
sentation model. Bulletin of the Buryat State
University. Mathematics, computer science,
Osadcha, K., Osadchyi, V., Semerikov, S., Chemerys, H.,
and Chorna, A. (2020). The review of the adaptive
learning systems for the formation of individual ed-
ucational trajectory. CEUR Workshop Proceedings,
Osadchyi, V. V. and Krasheninnik, I. V. (2020). LMS Moo-
dle as a tool for personalizing the training of future
professionals. In Information technologies in educa-
tion, science and technology: theses add. V Interna-
tional. scientific-practical Conf. (Cherkasy, May 21-
23, 2020), pages 169–170. Cherkasy State Technolog-
ical University, Cherkasy.
Oxman, S. and Wong, W. (2014). White paper: Adap-
tive learning systems. Integrated Education Solutions,
pages 6–7.
Red, O. A. (2010). Intelligent adaptive distance learning
system RATOS-AI (part 2.) Conceptual model of the
system for training pharmacists. Zaporozhye Medical
Journal, (12, 4):28–36.
Ryabinova, E. N. (2009). Adaptive system of personalized
professional training of students of technical universi-
ties. Mashinostroenie, Moscow.
Shershneva, V. A., Vainshtein, Y. V., and Kochetkova, T. O.
(2018). Adaptive system of web-based teaching. Pro-
gram Systems: Theory and Applications, 9(4):179–
Shute, V. J. and Zapata-Rivera, D. (2007). Adap-
tive Technologies, chapter 24. Routledge.
Siadaty, M. and Taghiyareh, F. (2007). PALS2: Pedagog-
ically Adaptive Learning System based on Learning
Styles. In Seventh IEEE International Conference
on Advanced Learning Technologies (ICALT 2007),
pages 616–618.
Silkina, N. S. and Sokolinsky, L. B. (2016). Survey of
adaptive e-learning models. Bulletin of the South Ural
State University. Series: Computational Mathematics
and Software Engineering, 5(4):61–76.
Skliarova, O. N. (2016). Adaptive automated learning sys-
tem for learning a foreign language “Aktur”: Method-
ology and requirements. In Regularities and Trends
in the Development of Science in Modern Society:
Proceedings of International Conference, volume 2,
pages 159–162, Ufa. AETERNA.
Solovov, A. V. (2010). Mathematical modeling of e-
learning content, navigation and processes in the con-
text of international standards and specifications. Re-
search Center for the Problems of the Quality of Pro-
fessional Training, Moscow.
Toktarova, V. I. and Fedorova, S. N. (2020). Theoretical
and methodological bases for designing the concept
of the adaptive system of mathematical training of stu-
dents in the conditions of electronic educational envi-
ronment of the higher educational institution. Siberian
pedagogical journal, (3):74–83.
Vlasenko, A. A. (2014). Development of an adaptive dis-
tance learning system in the field of information tech-
nology. PhD thesis.
Yasuda, K., Kawashima, H., Hata, Y., and Kimura, H.
(2015). Implementation of an adaptive learning
system using a bayesian network. In The 11th
International Conference Mobile Learning 2015,
pages 157–159.
Analysis and Summarization of the Experience of Developing Adaptive Learning Systems in Higher Education