International Journal of Interactive Mobile Technologies (iJIM) – eISSN: 1865-7923 – Vol. 15, No. 10, 2021 Paper—The Intelligent Platform of Autonomous Learning in Post-Secondary Education The Intelligent Platform of Autonomous Learning in Post-Secondary Education https://doi.org/10.3991/ijim.v15i10.19523 Vadim Samusenkov () I.M. Sechenov Moscow State Medical University, Moscow, Russian Federation croc@bk.ru Vladimir Klyushin S.M. Nikolskii Institute of Mathematics, RUDN, Moscow, Russian Federation Valeriy Prasolov Financial University under the Government of the Russian Federation, Moscow, Russian Federation Konstantin Sokolovskiy Humanitarian and Technical Academy, Kokshetau, Kazakhstan Abstract—The study aimed to develop and test an autonomous learning intelligent platform's effectiveness in post-secondary education. It was conducted based on the Institute of Dentistry named after E.V. Borovsky in I.M. Sechenov First Moscow State Medical University (Moscow, Russia) and Humanitarian and technical academy (Kokshetau, Kazakhstan). This research involved 59 teachers and 390 students, who comprised the total sample of 449 respondents. The experiment consisted of three stages – introductory, experimental, and final. The introductory stage included the distribution of enrolled students into the experimental and control groups. Besides, at the introductory stage, the development of questionnaires directed at identifying students' and teachers' readiness to implement autonomous learning was performed. Apart from this, the involved educators were required to fill the learning platform with predetermined training content. Programmers developed the considered intelligent learning platform by prior agreement with educational institutions under study. The experimental stage aimed to introduce the designed model of autonomous learning based on the created intelligent platform. The final stage implied surveying of all study participants according to the developed questionnaires. After introducing the created autonomous learning model, it was revealed that 51.5% of enrolled teachers were ready for self-directed education at a high level, 20.4% – at a satisfactory level, 18.4% – at a moderate, and 9.7% – at a low level. Among the students of Sechenov University, 21% of respondents had a high level of readiness for autonomous learning based on intelligent platforms, 27% of students had a sufficient level, 35% – moderate, and 17% – low. Among the Humanitarian and technical academy students, 29% had a high readiness for autonomous learning, 30% iJIM ‒ Vol. 15, No. 10, 2021 49 https://doi.org/10.3991/ijim.v15i10.19523 mailto:croc@bk.ru Paper—The Intelligent Platform of Autonomous Learning in Post-Secondary Education were ready at a sufficient level, 25% at a moderate, and 16% at a low level. This study provided an opportunity to use the developed questionnaires and the model of autonomous learning in post-secondary education to research the implementation of self-directed training further. Keywords—Post-secondary education, mobile learning, autonomous learning, intelligent platforms. 1 Introduction In this day and age, the educational sector undergoes multiple transformations that lead to drastic changes in the teacher's and student's roles. In addition to active partic- ipation in the educational process, today's students can choose learning methods for their post-secondary education and manage their own educational trajectory, i.e., studying in the so-called autonomous mode. Though, for this process to be successful, several factors must be taken into consideration. In particular, the availability and accessibility of training materials and tools for obtaining knowledge can be provided by mobile learning and the presence of motivation for learning. The formation of autonomous education requires both technological and pedagogi- cal substantiation. The transition process is the most difficult and is best ensured if electronic devices are used in teaching already at the very early stages of education and school preparation [1]. Researchers agree that the teacher's role remains critical in autonomous learning, both in higher education and in secondary and post-secondary education [2,3]. Teach- er training should include increased readiness for technological change and mastery of mobile devices and the management of unique applications for learning and knowledge of specific pedagogical techniques focused on e-learning and greater stu- dent autonomy [4,5]. The research is devoted to the problem of the transformation of teaching from the classroom to autonomous using an intelligent learning system. It is necessary to de- termine whether such a transition will increase the quality of teaching without signifi- cant preliminary training, education, and increased readiness of teachers and students, or they will increase their level of readiness for autonomy in using such a system. In most cases, technological innovations at a high rate in many developing countries provoke such a transition without preparation, immediately using special training applications [6]. Therefore, the problem under study is extremely relevant and has been little studied in the scientific literature. The research is structured as follows: The Introduction briefly presents the back- ground, issues, and reasons for the research, its goals, and innovation; The literature review reviews the most significant works devoted to the research problem and em- phasizes the novelty and purpose of the work; Methods and Results provide data on the sample, research methods and the questionnaire used. The Results section is de- voted to a detailed analysis of the results obtained during the survey. The discussion introduces the findings of the research into the general discourse of the problem with related works. 50 http://www.i-jim.org Paper—The Intelligent Platform of Autonomous Learning in Post-Secondary Education 1.1 Literature review Modern scientific works emphasize the trend towards an increase in students' abil- ity to self-study, self-management, and self-assessment [7]. Research in this field is predominantly concentrated on the questions of equity and the social mobility of edu- cation seekers [8], positive relationship between virtual reality and satisfaction from learning, and situation-based education, oriented at the acquisition of the necessary skills, knowledge, or behavior due to the use of complex technologies [9]. Research- ers note that the vector of influence in modern education is transferred from the teach- er to the student, who is supposed to design a personal learning trajectory with the teacher’s help [10]. Such autonomous training is referred to as a way to build a per- sonality of a new level in the format and context of lifelong learning under the condi- tions of digitalization of education [11]. Some scholars oppose autonomous learning to a blended learning model, represent- ing the combination of traditional and e-learning educational approaches and allows one to manage the training process independently [12]. Mobile learning for these purposes may look most preferable due to mobile devices' total penetration into the social environment. At the same time, a broad range of literature is devoted to the study of mobile learning, which positively affects attendance and academic achieve- ments [13], and flipped learning aimed at improving students’ independence and in- volvement in the study process [14]. Scholars nowadays are pondering over the need to create, test, and implement au- tonomous learning intelligent platforms. MISNIS is considered one of the most prom- ising platforms for education since its main idea lies in analyzing social networks' impact on society [15]. Vast attention has also been paid to the usefulness of borrow- ing intelligent platforms and their prototypes from other areas of human activity [16]. A strong opinion exists that the Moodle platform, which provides freedom of choice and extensive communication capabilities, can become a basis for developing auton- omous learning intelligent platforms [17]. For such platforms, the natural integration of mobile access in implementing mobile learning becomes a regular part of the func- tionality [2]. The international practice provides numerous examples of the implementation of autonomous learning based on multimedia mobile and online platforms and technolo- gies and a system of smart classrooms [3,18]. Several researchers have investigated English language teachers’ perceptions of learner autonomy in terms of concept and practice in the higher education sector [19]. Scholars from the National Institute of Technology in Japan have thoroughly investigated autonomous learning and proposed an Advanced-Active Autonomous Learning System based on information and com- munication technology [20]. Great attention is also attached to augmented reality. It allows interactive and autonomous studying and the collaborative performance of laboratory practices with other students without a teacher's assistance [21]. Several researchers have also proposed an autonomous learning interaction model that in- volves both independent and direct training [22]. The most interesting studies of the process of introducing elements of an autono- mous learning system and the use of mobile devices at the stage of preschool educa- iJIM ‒ Vol. 15, No. 10, 2021 51 Paper—The Intelligent Platform of Autonomous Learning in Post-Secondary Education tion are given in many works [23]. Adequate transformation of the digital environ- ment familiar in our era into a learning environment for children will become the key to their future accelerated development and academic success [1,5]. Researchers em- phasize the importance and effectiveness of using special mobile applications for teaching preschoolers and schoolchildren and preparing teachers for them [24]. Autonomous learning is believed to stimulate students' initiative in training, pro- mote cooperative and self-directed learning ability, and improve teaching levels [25]. An essential part of motivation for students is the rich technologies used in mobile and cloud-based platforms [26], for example, the ability to automatically find illustra- tions or images associated with a complicated search phrase [27]. The students' moti- vation to learn intelligent platforms supporting the voice chat to effectively inspire students' interest in training and improve their autonomous learning effect is highly emphasized. As an option, scholars propose creating the method to establish the au- tonomous learning intelligent platform as one of the variants of support services for distance post-secondary learners [28]. The academic community remains unanimous that the ability to learn autonomously becomes one of the overall qualities that univer- sity students should have and starts to be an indispensable capability in their life after graduation [29]. Teachers play a significant role in providing students with an autonomous learning environment and proper instruction [30]. For this reason, to enhance reflection and learning motivation, it is recommended to provide just-in-time feedback about per- formance on learning tasks and give students some freedom over the choice of learn- ing tasks [31]. Particular consideration in scientific research is given to studying factors influenc- ing the students' learning outcomes [32,33]. It is indicated that web-based and mobile autonomous learning, grounded in humanism and constructivism ideas, has combined self-directed training and Internet/mobile technology and opened up a new learning path [34]. A large number of specialists currently analyze the structure of autonomous learning, its basic principles, role, and significance [35]. Many of them focus on au- tonomous training's main approaches, its challenges, and prospects for its implemen- tation [36]. The common point for all the above studies is recognizing the feasibility of intro- ducing autonomous learning as one of the essential aspects of modern education. However, many scientific works have not described transparent algorithms for its introduction or even proposed useful and valid models for its organization. The prob- lem of an intensive transition and rapid implementation of autonomous learning for students and teachers and the development of their readiness for such learning re- mains extremely little researched. There are no specific recommendations for using intelligent platforms in the educational field to support and implement such learning type. 1.2 Problem statement The analyzed scientific sources actualize the need for the development, testing, im- plementation, and verification of autonomous learning intelligent platforms' effective- 52 http://www.i-jim.org Paper—The Intelligent Platform of Autonomous Learning in Post-Secondary Education ness in post-secondary education. It is necessary to establish a clear connection be- tween the application of autonomous learning in higher educational institutions and students’ academic achievements. Significant is the problem of the effectiveness of the transition to autonomous learning and the level of its effectiveness. The objective of this work was to develop an intelligent platform for autonomous learning in post-secondary education. The achievement of this goal was possible after the solution of the following tasks: • Analyze the state of knowledge regarding the use of autonomous learning intelli- gent platforms in post-secondary education • Develop and test the model of autonomous learning in post-secondary education based on an intelligent platform • Determine the relationship between the use of autonomous learning intelligent platforms in post-secondary education and students’ academic achievements • Compare the obtained data with the available foreign experience in the indicated direction and determine standard and distinctive features • Conclude the effectiveness and further usefulness of autonomous learning intelli- gent platforms in post-secondary education. The scientific novelty of this research lies in the development of the autonomous learning model in post-secondary education based on an intelligent platform and ob- taining an assessment of the effectiveness of the transition to this type of education and an increase in the level of readiness for autonomous education among students and teachers in the case of using this system. 2 Materials and Methods 2.1 Research design and sample This study was carried out at the Institute of Dentistry named after E.V. Borovsky in I.M. Sechenov First Moscow State Medical University (Moscow, Russia) and Hu- manitarian and technical academy (Kokshetau, Kazakhstan). The research sample consisted of 449 people (59 teachers and 390 students). The study involved students of different specialties and academic years with various levels of ideas about future professional activities to show their readiness for autonomous learning and responsi- bility for their educational results. The research hypothesis assumed that intelligent platforms for autonomous learn- ing in post-secondary education contribute to an increase in teachers' and students' readiness to work in autonomous learning mode. The examination process consisted of three stages - introductory, experimental, and final. The introductory stage included dividing all students into experimental and control groups (EG and CG, respectively). Within this stage, the development of par- ticular questionnaires aimed at determining students' and teachers' readiness to im- plement autonomous learning was also performed. The involved educators were re- quired to fill the intelligent autonomous learning platform with pre-selected educa- iJIM ‒ Vol. 15, No. 10, 2021 53 Paper—The Intelligent Platform of Autonomous Learning in Post-Secondary Education tional content. Programmers developed this intelligent platform by prior agreement with educational institutions under study. The second stage - experimental - was to introduce the autonomous learning model based on the created intelligent platform into the educational process of two selected universities. At the final stage, a survey of all study participants (students and teachers) was conducted according to the devel- oped questionnaires. Each of them had 20 statements to which respondents were sup- posed to give a positive or negative answer (Yes/No). For each positive answer, a person was given 1 point. Correspondingly, for the negative answer, no points were awarded. Following the number of points scored, four levels of readiness for autono- mous learning could be distinguished (Tables 1 and 2): • High (18-20 points) • Satisfactory (15-17 points) • Moderate (11-14 points) • Low (less than 10 points). Table 1. Questionnaire on students’ readiness for autonomous learning Statement Answer Yes No 1. I know what knowledge, skills, and abilities a student of my specialty should master. 2. I can easily build my daily study program for mastering a future specialty. 3. Every day I create my own self-study plan and schedule. 4. I can find and process any information related to my specialty from various sources. 5. Preparing for classes, I compose questions and tasks to check my level of educational material assimilation. 6. I pay maximum attention to the preparation for classes connected with my specialization – I find and process relevant information from the teacher's sources. 7. I often prepare presentations and projects based on independently selected materials. 8. Among the teacher's bunch of information, I easily find the most relevant for its additional investigation. 9. When I receive a bad mark on a test, I figure out my knowledge gaps and improve my preparation methods. 10. I have a positive experience with distance learning courses offered to me as part of the training. 11. From time to time, I search and take interesting distance courses. 12. I am proficient in information and communication technologies. 13. I can work on an assignment together with my classmates according to a pre-defined plan. 14. In the course of performing a collective assignment, I can give recommendations concern- ing the study process. 15. I can work on creative and search assignments given by the teacher without external support. 16. I can independently select or develop interesting creative projects and work on them without the teachers' help. 17. I have a positive experience in preparing materials for various types of lessons together with my teachers. 18. I participated in a joint student-teacher discussion concerning the educational content of my training course. 19. I took part in professional competitions offered at my educational institution. 20. I took part in personally chosen competitions outside of my educational institution. 54 http://www.i-jim.org Paper—The Intelligent Platform of Autonomous Learning in Post-Secondary Education Table 2. Questionnaire on teachers’ readiness for autonomous learning Statement Answer Yes No 1. I actively involve students in the development and updating of training materials. 2. I support the involvement of students in the development of the course content. 3. I regularly conduct surveys among students to identify their interests to take their opinion into account during the further development of training material. 4. I take into account students' opinions when choosing forms of work in the class. 5. When using advanced tasks or organizing project activities, I always allow students to choose experimentally and search activity areas. 6. I believe that students should be allowed to adjust the content of the educational course at least partially. 7. I believe that students can plan their academic day on their own 8. I have a positive experience of collaborating with students while developing the content of the educational courses. 9. Together with my students, I participate in filling our university's electronic resources with educational content. 10. I am proficient in the use of information and communication technologies. 11. I have episodic/systematic positive examples of the introduction of autonomous learning elements in higher education. 12. I am experienced in using intelligent e-learning platforms. 13. I took short-term advanced training courses (seminars, hands-on sessions, workshops) on implementing autonomous learning in higher education. 14. I have already developed and tested a didactic toolkit for organizing autonomous student learning. 15. In my opinion, autonomous learning is not only a requirement of the time or a tribute to fashion – it is a way of teaching 21st-century students. 16. I believe that experimental methods of organizing autonomous learning in higher educa- tion are worth to be tested. 17. I would like to take part in an experiment on the organization of autonomous learning in higher education. 18. I believe that students are ready to implement autonomous learning and can work with electronic resources. 19. I have already worked with intelligent autonomous learning platforms. 20. I am sure that autonomous learning will provide a high level of motivation for productive educational and cognitive activities and high academic results. The validity of the tests used was checked by the method of re-passing the test by a group of 59 students from the sample used in the study, from the control and experi- mental groups in equal numbers, as well as by the same size group of students from those who did not take part in the study from the same universities (from the same general aggregate). The test was performed in two groups simultaneously and before the main study. The discrepancy between the pretest results did not exceed 1.84%, indicating the questionnaire's high validity. The study uses simple descriptive statistics using a detailed division of participants into groups according to the quality of readiness to more accurately and directly high- light the presence or absence of changes in this studied indicator. Further studies of the factors of change in readiness and their correlation between groups of participants by age, gender, and other significant signs make sense if proposing a form of imple- iJIM ‒ Vol. 15, No. 10, 2021 55 Paper—The Intelligent Platform of Autonomous Learning in Post-Secondary Education mentation of an intelligent autonomous learning system will show in this study a significant result of improving readiness. 2.2 Intervention The examination process provided for a certain level of interference in the consid- ered higher educational institutions' educational process. Though, the authors of the present study were given time to do research. 2.3 Ethical issues All study participants were aware of the investigation purpose. They perceived it positively and had no objections. The administration of educational institutions agreed to assist the experiment participants and financed developing an intelligent platform for autonomous learning. 2.4 Statistical analysis The investigation covered 390 students (192 from Sechenov University and 198 from Humanitarian and technical academy) and 59 teachers (30 from Sechenov Uni- versity and 29 from Humanitarian and technical academy). The surveying process was carried out in the Google Forms application, while the processing of its results was performed in the Microsoft Excel spreadsheet. The survey outcomes are presented in Table 3 and Fig. 1. 3 Results In contrast to the CGs, whose educational process remained unchanged, the EGs were engaged in autonomous learning based on the developed intelligent platform. This model included the functions of students, teachers, the intelligent platform itself, and provided an algorithm for autonomous training. The students’ functions covered the registration on the platform; choice of courses, amount of study time, forms of knowledge control and self-study; processing materi- als available on the platform for each topic, module, or block; passing tests; perform- ing independent tasks; and familiarization with their study results. Functions of teachers included the development of an educational plan, learning materials for lectures or seminars, practical assignments for independent work, and means of student's control; uploading all the developed materials to the intelligent platform; communication in the platform's online chat (help students if necessary); commenting on completed tasks on the forum, and familiarization with students' learning outcomes. The intelligent platform was supposed to process and store data, generate unique logins and passwords, form individual course loads, and collect the study results. 56 http://www.i-jim.org Paper—The Intelligent Platform of Autonomous Learning in Post-Secondary Education The working algorithm was as follows: 1. Registration of a student on the autonomous learning platform: entering personal data, indicating his/her specialty, training duration, and the range of professional interests; generation of a unique login and password 2. Determination of training time and volume: students can choose the number of courses for a particular time period (for example, 3 or 4 courses per week, 5 or 6 lessons per day) 3. Students’ choice of forms of control for each course or topic: test control, an- swers to questions, creative tasks, project activities 4. Students’ choice of forms and topics for independent work (presentation, mini project, mind map, storytelling, video) 5. Generation by the platform of student’s individual schedule 6. Implementation of autonomous learning: the student works on the materials available on the intelligent platform and undergoes knowledge control 7. Calculation by the platform of the final educational result for courses/modules. At the last stage of the study, all participants were interviewed using the Method- ology section's questionnaires. The results of this examination are presented in Table 3 and Fig. 1. Table 3. Students’ survey results Readiness levels/number of respondents High Satisfactory Moderate Low Total respondents Sechenov University 1st year (EG) 4 6 10 5 25 1st year (CG) 0 2 6 14 22 2nd year (EG) 5 3 10 7 25 2nd year (CG) 2 4 12 7 25 3rd year (EG) 6 9 8 3 26 3rd year (CG) 2 5 8 10 26 4th year (EG) 6 8 7 0 21 4th year (CG) 3 4 9 6 22 Humanitarian and Technical Academy 1st year (EG) 8 8 4 5 25 1st year (CG) 3 3 6 13 25 2nd year (EG) iJIM ‒ Vol. 15, No. 10, 2021 57 Paper—The Intelligent Platform of Autonomous Learning in Post-Secondary Education 7 6 8 3 24 2nd year (CG) 4 4 4 12 24 3rd year (EG) 9 9 7 2 27 3rd year (CG) 4 4 6 12 26 4th year (EG) 5 7 6 5 23 4th year (CG) 3 4 7 10 24 As shown in Table 3, EG respondents demonstrate higher readiness for the imple- mentation of autonomous learning based on intelligent platforms than those from CGs. Thus, it was revealed that among the first-year students of Sechenov University allocated to the EG were 16% more individuals with a high level of readiness for autonomous learning than in the CG, in which such highly prepared students were not identified at all. A satisfactory level of readiness was inherent to 24% of Sechenov University newcomers, and a moderate – to 40%. Among second-year students of Sechenov University who belonged to the EG, 20%, 12%, and 40% were ready for autonomous learning at high, satisfactory, and moderate levels. Data for students of the third year of study from the EG indicate that only 24% of them were highly pre- pared for such learning mode, while 36% and 32% of third-years appeared to be ready at satisfactory and moderate levels. As of the fourth-year students of Sechenov Uni- versity distributed to the EG, 24%, 36%, and 28% were ready for autonomous learn- ing at high, satisfactory, and moderate levels. In general, among the respondents of Sechenov University EG, 21% had a high readiness for autonomous learning imple- mentation, 27% – satisfactory, 35% – moderate, and 17% – low (Fig. 1). Fig. 1. Students’ survey results (experimental group) for both universities 12 14 14 10 12 9 18 10 15 18 15 5 11 15 13 5 0 5 10 15 20 High Satisfactory Moderate Low N u m b e r o f re sp o n d e n ts ( to ta l) Readiness levels Students’ survey results (experimental group) 1st year 2nd year 3rd year 4th year 58 http://www.i-jim.org Paper—The Intelligent Platform of Autonomous Learning in Post-Secondary Education The results of CGs were somehow worse (Fig. 2). A high level was noted among 3.6% of learners, satisfactory among 7.8%, moderate among 18.2%, and low among 70.4% of enrolled students. Fig. 2. Students’ survey results (control group) for both universities Among the EG students of the first year of study at the Humanitarian and technical academy, high and satisfactory readiness levels amounted to 32% each, while moder- ate made up 16% of all freshmen. The readiness of Humanitarian and technical acad- emy EG sophomores for autonomous learning at a high level was inherent to 29% of individuals, at a satisfactory level – to 25%, and at a moderate level – 33%. Among the third-year students, only 33% were ready for autonomous learning at a high and satisfactory level, while 26% had a moderate readiness level. Among EG students of the Humanitarian and technical academy's final course, 22% were ready for autono- mous learning at a high level, 30% – at satisfactory, and 26% – at moderate. On aver- age, 29% of EG respondents had a high level of readiness for autonomous learning using intelligent platforms, 30% had a satisfactory level, 25% – moderate, and 16% – low. In parallel, only 7% of students of CGs demonstrated a high level of readiness, 7.6% had a satisfactory level, 11.6% – moderate, and 73.8% – low. Given the ob- tained data, the effectiveness of the implementation of the proposed autonomous learning model was proven. 3 5 12 27 6 8 16 19 6 9 14 22 6 8 16 16 0 5 10 15 20 25 30 High Satisfactory Moderate Low N u m b e r o f re sp o n d e n ts ( to ta l) Readiness levels Students’ survey results (control group) 1st year 2nd year 3rd year 4th year iJIM ‒ Vol. 15, No. 10, 2021 59 Paper—The Intelligent Platform of Autonomous Learning in Post-Secondary Education Fig. 3. Educators’ survey results As can be seen from Fig. 3, fifteen teachers (50%) of Sechenov University are ready to introduce autonomous learning through intelligent platforms at a high level. Five educators each (16.7%) have satisfactory and average readiness levels. None of the involved instructors from Sechenov University showed a low level of readiness. Among the teachers of Humanitarian and technical academy, sixteen people (53%) were ready to implement and practice autonomous learning at a high level, seven (24%) and six (20%) had satisfactory and average levels of readiness, respectively, and only one (3%) showed a low readiness level. In general, 51.5% of educators ap- peared to be highly prepared to introduce autonomous learning, 20.4% had a satisfac- tory level of readiness, 18.4% – moderate, and 9.7% – low. 4 Discussion Similar to the present research is the experiment on the smart classroom system - a ubiquitous network access environment, where wireless terminals can carry out group discussions and cooperative education in alignment with students' learning needs. It is a widely held view that such a system can better stimulate students' interest and par- ticipation in training and make independent learning possible [18]. However, the prin- cipal difference of this study from the present one is its narrow profile. It focuses only on learning a foreign language, whereas the current work proposes implementing autonomous learning in various disciplines and courses. Certain correlations with the conducted experiment can be noted in Indonesian re- search to study teachers' and students' perceptions concerning autonomous learning. This study argues that even though both teachers and students held positive tenets on 15 5 5 0 16 7 6 1 0 2 4 6 8 10 12 14 16 18 High Satisfactory Moderate Low N u m b e r o f re sp o n d e n ts Readiness levels Educators’ survey results Sechenov University Humanitarian and technical academy 60 http://www.i-jim.org Paper—The Intelligent Platform of Autonomous Learning in Post-Secondary Education autonomous learning, they still had an inadequate understanding of autonomous learn- ing concepts [37]. Since the proposed autonomous learning model is network-based, it is appropriate to mention a study that proves the effectiveness of the combination of web-based education and autonomous learning through the introduction of mobile and individual training methods. It is noteworthy that this research was carried out precisely in the post-secondary education system, which encourages widespread mobile and individu- al teaching methods [34]. Large-scale research conducted at one of Ecuador universities to establish a rela- tionship between the incentive to study and the attitude to learning a foreign language has revealed a strong link between motivation and frequency of occurrence of auton- omous learning activities [38]. This suggests that autonomous learning is a time re- quirement and a key priority for the educational community. Accordingly, a conclu- sion can be drawn on the advisability of applying an autonomous learning model based on an intelligent platform. As our research shows, the implementation of such systems can be fast and increases the participants' readiness in the learning process for autonomy. Most scientific works on autonomous learning emphasize that such training posi- tively affects learning, cognitive activity, students' motivation, and academic results. The present investigation confirmed the hypothesis that using an autonomous learning intelligent platform in post-secondary education contributes to an increase in the read- iness of teachers and students to work in a self-directed learning mode. Furthermore, this study contributed to the expansion of the understanding of autonomous learning possibilities. It also confirmed the assumption that all participants in the educational process should be ready to study autonomously. 5 Conclusion This research aimed to develop and test the effectiveness of the autonomous learn- ing intelligent platform in post-secondary education. The study hypothesis assumed that intelligent platforms for self-directed training in post-secondary education con- tribute to the enhancement of teachers' and students' readiness to work autonomously. The study provided the creation of the autonomous learning model implemented in the study process based on a specially developed intelligent platform. After its intro- duction, through the use of the survey method, it was revealed that 51.5% of enrolled teachers were ready for autonomous learning at a high level, 20.4% – at a satisfactory level, 18.4% – at a moderate level, and 9.7% – at a low level. Among the students of Sechenov University, 21% of respondents had a high level of readiness for autono- mous learning based on intelligent platforms, 27% of students had a sufficient level, 35% – moderate, and 17% – low. Among the Humanitarian and technical academy students, 29% appeared to be highly prepared for autonomous learning, 30% were ready at a sufficient level, 25% – at moderate, and 16% – at low. The results demon- strate a qualitative increase in the readiness for independent, autonomous work of iJIM ‒ Vol. 15, No. 10, 2021 61 Paper—The Intelligent Platform of Autonomous Learning in Post-Secondary Education both students and teachers and conclude that implementing an intelligent autonomous learning system contributes to this process. The practical significance of research findings is in using the developed question- naires and the model of autonomous learning in post-secondary education. This study's scientific value is that it lays the foundations for numerous scientific discus- sions on the feasibility of autonomous learning intelligent platforms in post-secondary education. Besides, the performed examination opens new prospects for exploring novel approaches to organizing autonomous learning and promotes the development of best teaching practices in self-directed education. 5.1 Recommendations The study results allow us to recommend at the level of post-secondary education to implement and independently create intelligent systems of autonomous learning at the level of educational institutions or to attract ready-made online learning platforms for their implementation. With the transition to autonomous learning, the willingness to use it grows for both teachers and students, and academic performance remains stable. 5.2 Research limitation The research participants' age ranged from 18 to 25 for students and from 32 to 55 for educators. The examination was conducted within the educational process and was limited in time. During the study course, the experimental group of students practiced only autonomous learning based on the created intelligent platform. The study uses descriptive statistics to demonstrate a measurable benefit in improv- ing participants' preparedness; more detailed research is required using correlation and factor analysis to elucidate the significant success factors of intelligent autonomous learning systems. The study also used data from only two universities and should be extrapolated with caution to institutions using other curricula. 6 References [1] Papadakis, S. (2020). Evaluating a game-development approach to teach introductory pro- gramming concepts in secondary education. International Journal of Technology En- hanced Learning, 12(2), 127-145. https://doi.org/10.1504/ijtel.2020.106282 [2] Qureshi, M.I., Khan, N., Gillani, S.M.A.H., Raza, H. (2020). A Systematic Review of Past Decade of Mobile Learning: What we Learned and Where to Go. International Journal of Interactive Mobile Technologies, 14(6): 67-81. https://doi.org/10.3991/ijim.v14i06.13479 [3] Chen, N. (2012). Autonomous Learning in the Context of Computer-based Multimedia College English Teaching and Learning. Theory & Practice in Language Studies, 2(12): 2541-2547. https://doi.org/10.3991/ijim.v14i06.13479 [4] Kalogiannakis, M., Papadakis, S. (2019). Evaluating pre-service kindergarten teachers' in- tention to adopt and use tablets into teaching practice for natural sciences. International 62 http://www.i-jim.org https://doi.org/10.1504/ijtel.2020.106282 https://doi.org/10.3991/ijim.v14i06.13479 https://doi.org/10.3991/ijim.v14i06.13479 Paper—The Intelligent Platform of Autonomous Learning in Post-Secondary Education Journal of Mobile Learning and Organisation, 13(1): 113-127. https://doi.org/10.1504 /ijmlo.2019.096479 [5] Papadakis, S., Trampas, A. M., Barianos, A. K., Kalogiannakis, M., & Vidakis, N. (2020). Evaluating the Learning Process: The "ThimelEdu" Educational Game Case Study. In CSEDU 2020 - Proceedings of the 12th International Conference on Computer Supported Education Volume 2, 2020, Pages 290-298.Virtual, Online; May 2020. https://doi.org/ 10.5220/0009379902900298 [6] Papadakis, S., Vaiopoulou, J., Kalogiannakis, M., Stamovlasis, D. (2020). Developing and Exploring an Evaluation Tool for Educational Apps (E.T.E.A.) Targeting Kindergarten Children. Sustainability, 12: 4201. https://doi.org/10.3390/su12104201 [7] Li, Q. (2019). Students’ Autonomous Learning in the Era of “Internet+” Big Data. In In- ternational conference on Big Data Analytics for Cyber-Physical-Systems. Springer, Sin- gapore, pp. 340-344. https://doi.org/10.1007/978-981-15-2568-1_47 [8] Bathmaker, A.M. (2017). Post-secondary education and training, new vocational and hy- brid pathways and questions of equity, inequality and social mobility: introduction to the special issue. Journal of Vocational Education & Training, 69(1): 1-9. https://doi.org/10.1080/13636820.2017.1304680 [9] Chen, Y.F., Luo, Y.Z., Fang, X., Shieh, C.J. (2018). Effects of the application of computer multimedia teaching to automobile vocational education on students’ learning satisfaction and learning outcome. EURASIA Journal of Mathematics, Science and Technology Edu- cation, 14(7): 3293-3300. https://doi.org/10.29333/ejmste/91245 [10] Voronina, G.V. (2017). Informational technologies in modern education. In Collection of articles of the International scientific and practical conference “The role of science in the development of society” On March 3, 2017, Kazan, pp. 57-59. [11] Koryakina, Ya.V., Lomteva, T.N., Kamensky. M.V. (2019). Self-regulated learning under the conditions of digitalization of education. Bulletin of the North-Caucasus Federal Uni- versity, 2(71): 141-148. [12] Zhang, J. (2018). Blended learning innovation model among college students based on In- ternet. International Journal of Emerging Technologies in Learning, 13(10): 158-170. https://doi.org/10.3991/ijet.v13i10.9454 [13] Wilkinson, K., Barter, P. (2016). Do mobile learning devices enhance learning in higher education anatomy classrooms? Journal of Pedagogic Development, 6(1): 14-23. [14] Yoon, S., Kim, S., Kang, M. (2018). Predictive power of grit, professor support for auton- omy and learning engagement on perceived achievement within the context of a flipped classroom. Active Learning in Higher Education, 21(3): 233-247. https://doi.org/10.1177/ 1469787418762463 [15] Carvalho, J.P., Rosa, H., Brogueira, G., Batista, F. (2017). MISNIS: An intelligent plat- form for twitter topic mining. Expert Systems with Applications, 89: 374-388. https://doi.org/10.1016/j.eswa.2017.08.001 [16] Dascalu, M.D., Paraschiv, I.C., Nicula, B., Dascalu, M., Trausan-Matu, S., Nuta, A. C. (2019). Intelligent Platform for the Analysis of Drug Leaflets Using NLP Techniques. In 2019 18th RoEduNet Conference: Networking in Education and Research (RoEduNet). IEEE, pp. 1-6. https://doi.org/10.1109/roedunet.2019.8909606 [17] Filimonenkova, T.N. (2018). Electronic educational resources and their role in smart- education. Problems of Modern Teacher Training, 61(2): 202-205. [18] Pingxiao, W. (2017). Research on the English teaching and autonomous learning based on multimedia platform and smart classroom system. International Journal of Multimedia and Ubiquitous Engineering, 12(1): 351-362. https://doi.org/10.14257/ijmue.2017.12.1.30 iJIM ‒ Vol. 15, No. 10, 2021 63 https://doi.org/10.1504%0b/ijmlo.2019.096479 https://doi.org/10.1504%0b/ijmlo.2019.096479 https://doi.org/10.5220/0009379902900298 https://doi.org/10.5220/0009379902900298 https://doi.org/10.3390/su12104201 https://doi.org/10.1007/978-981-15-2568-1_47 https://doi.org/10.1080/13636820.2017.1304680 https://doi.org/10.29333/ejmste/91245 https://doi.org/10.3991/ijet.v13i10.9454 https://doi.org/10.1177/1469787418762463 https://doi.org/10.1177/1469787418762463 https://doi.org/10.1016/j.eswa.2017.08.001 https://doi.org/10.1109/roedunet.2019.8909606 https://doi.org/10.14257/ijmue.2017.12.1.30 Paper—The Intelligent Platform of Autonomous Learning in Post-Secondary Education [19] Haji-Othman, N.A., Wood, K. (2016). Perceptions of learner autonomy in English lan- guage education in Brunei darussalam. In Language learner autonomy: Teachers’ beliefs and practices in Asian contexts. Phnom Penh, Cambodia, pp. 79-95. https://doi.org/10.5746/leia/la_asia [20] Takahashi, A., Kashiwaba, Y., Okumura, T., Ando, T., Yajima, K., Hayakawa, Y., Takeshige, M., Uchida, T. (2016). A3 Learning System: Advanced Active and Autono- mous Learning System. International Journal of Engineering Pedagogy, 6(2): 52-58. https://doi.org/10.3991/ijep.v6i2.5645 [21] Martín-Gutiérrez, J., Fabiani, P., Benesova, W., Meneses, M.D., Mora, C.E. (2015). Aug- mented reality to promote collaborative and autonomous learning in higher education. Computers in human behavior, 51: 752-761. https://doi.org/10.1016/j.chb.2014.11.093 [22] Yun, J.J., Lee, D., Ahn, H., Park, K., Yigitcanlar, T. (2016). Not deep learning but auton- omous learning of open innovation for sustainable artificial intelligence. Sustainability, 8(8): 797. https://doi.org/10.3390/su8080797 [23] Vidakis, N.; Barianos, A.; Trampas, A.; Papadakis, Stamatios; Kalogiannakis, M. and Vassilakis, K. (2019). Generating Education in-Game Data: The Case of an Ancient Thea- tre Serious Game.In Proceedings of the 11th International Conference on Computer Sup- ported Education - Volume 1: CSEDU, ISBN 978-989-758-367-4, pages 36-43. https://doi.org/10.5220/0007810800360043 [24] Dorouka, P., Papadakis, S., & Kalogiannakis, M. (2020). Tablets and apps for promoting robotics, mathematics, STEM education and literacy in early childhood education. Interna- tional Journal of Mobile Learning and Organisation, 14(2), 255-274. https://doi.org/10. 1504/ijmlo.2020.10026334 [25] Wang, X. (2017). The Application of Autonomous Learning in English Phonetics Teach- ing. In 2017 4th International Conference on Education, Management and Computing Technology (ICEMCT 2017). Atlantis Press, pp. 520-523. https://doi.org/10.2991/icemct- 17.2017. 115 [26] Rimale, Z., El Habib, B., Tragha, A., El Guemmat, K. (2016). Survey on the use of the mobile learning based on mobile cloud computing. International Journal of Interactive Mobile Technologies, 10(3): 35-41. https://doi.org/10.3991/ijim.v10i3.5672 [27] Karkar, A., Al Ja’am, J. (2016). An educational ontology-based m-learning system. Inter- national Journal of Interactive Mobile Technologies, 10(4): 48-56. https://doi.org/10.3991/ ijim.v10i4.6011 [28] Wilson-Lendor, D.L. (2020). An After Thought: Support Services for Distance Learners at a Post-secondary Institution. Doctoral dissertation, University of Southern California. [29] Zhang, Y.B., Ning, T.T., Xue, T. (2017). Autonomous learning ability training of college students in Tianjin from the perspective of habitus and field. Journal of Discrete Mathe- matical Sciences and Cryptography, 20(1): 323-339. https://doi.org/10.1080 /09720529.2016.1183309 [30] Hu, Y. (2016). The Role of Learner Autonomy for Learning English Out-of-class in Chi- nese Universities. A Project Submitted in Partial Fulfillment of the Requirements for the Degree of Master of Education in the Department of Curriculum and Instruction. [31] Beckers, J., Dolmans, D.H., Knapen, M.M., Van Merriënboer, J.J. (2019). Walking the tightrope with an e-portfolio: imbalance between support and autonomy hampers self- directed learning. Journal of Vocational Education & Training, 71(2): 260-288. https://doi.org/10.1080/13636820.2018.1481448 64 http://www.i-jim.org https://doi.org/10.5746/leia/la_asia https://doi.org/10.3991/ijep.v6i2.5645 https://doi.org/10.1016/j.chb.2014.11.093 https://doi.org/10.3390/su8080797 https://doi.org/10.5220/0007810800360043 https://doi.org/10.1504/ijmlo.2020.10026334 https://doi.org/10.1504/ijmlo.2020.10026334 https://doi.org/10.2991/icemct-17.2017.115 https://doi.org/10.2991/icemct-17.2017.115 https://doi.org/10.2991/icemct-17.2017.115 https://doi.org/10.3991/ijim.v10i3.5672 https://doi.org/10.3991/ijim.v10i4.6011 https://doi.org/10.3991/ijim.v10i4.6011 https://doi.org/10.1080%0b/09720529.2016.1183309 https://doi.org/10.1080%0b/09720529.2016.1183309 https://doi.org/10.1080/13636820.2018.1481448 Paper—The Intelligent Platform of Autonomous Learning in Post-Secondary Education [32] Ma, W. (2016). Study on the Influencing Factors on Network-based Autonomous Learning in Mechanical Engineering English. International Journal of Emerging Technologies in Learning, 11(3): 57-62. https://doi.org/10.3991/ijet.v11i03.5536 [33] Li, Y., Jin, D. (2020). A Model for the Influential Factors of the Autonomous Learning Ability of Japanese Majors. International Journal of Emerging Technologies in Learning, 15(12): 153-167. https://doi.org/10.3991/ijet.v15i12.14531 [34] Yao, S. (2016). Research on Web-based Autonomous English Learning of Engineering Students. International Journal of Emerging Technologies in Learning, 11(6): 4-9. [35] Kiseleva, A.V. (2017). Autonomous learning as one of directions of modern education. Advances in modern science and education, 2(6): 41-45. [36] Soboleva, E.I., Kupavskaya, A.A. (2017). Autonomous foreign language teaching and learning at non-linguistic higher education institutions. In Readings of A.I. Bulatov: Mate- rials of I International scientific and practical conference On March 31, 2017, pp. 266-268. [37] Khotimah, K., Widiati, U., Mustofa, M., Ubaidillah, M.F. (2019). Autonomous English learning: Teachers’ and students’ perceptions. Indonesian Journal of Applied Linguistics, 9: 371-381. https://doi.org/10.17509/ijal.v9i2.20234 [38] Bravo, J.C., Intriago, E.A., HolguĆn, J.V., Garzon, G.M., Arcia, L.O. (2017). Motivation and Autonomy in Learning English as Foreign Language: A Case Study of Ecuadorian College Students. English Language Teaching, 10(2): 100-113. https://doi.org/10.5539/elt. v10n2p100 7 Authors Samusenkov Vadim Olegovich is a PhD of Medical Sciences, Associate Professor of the Department of Prosthetic Dentistry, I.M. Sechenov Moscow State Medical University, Russian Federation. croc@bk.ru Klyushin Vladimir Leonidovich is a PhD in Physical and Mathematical Sciences, Doctor in Information Science, Professor of S.M. Nikolskii Institute of Mathematics, RUDN, Moscow, Russian Federation. Prasolov Valeriy Ivanovich is a PhD of Political Sciences, Associate Professor of the Department of Risk Analysis and Economic Security, Financial University under the Government of the Russian Federation, Moscow, Russian Federation. Sokolovskiy Konstantin Gennadyevich is a PhD of Juridical Sciences, Associate Professor of the Department of General Subjects, Humanitarian and Technical Academy, Kokshetau, Kazakhstan. Article submitted 2020-10-29. Resubmitted 2021-01-13. Final acceptance 2021-01-17. Final version published as submitted by the authors. iJIM ‒ Vol. 15, No. 10, 2021 65 https://doi.org/10.3991/ijet.v11i03.5536 https://doi.org/10.3991/ijet.v15i12.14531 https://doi.org/10.17509/ijal.v9i2.20234 https://doi.org/10.5539/elt.v10n2p100 https://doi.org/10.5539/elt.v10n2p100 file:///C:/Users/INSOREDS1/Desktop/SCHEDULING/iJIM%2010/Kumar%20%20Review/croc@bk.ru