Machine Learning Approach for an Adaptive E-Learning System Based on Kolb Learning Styles

This research focuses on designing a learning experience platform using xAPI and incorporating design thinking principles to foster innovation. The study focused on two main areas: a) analyzing and synthesizing the conceptual framework for a learning experience platform using xAPI with design thinking learning to promote innovation; and b) evaluating the suitability of a learning management model design for the learning experience platform using xAPI with design thinking learning to promote innovation. The evaluation was conducted by nine experts and the model consists of five parts: 1) the student module, 2) the teacher module, 3) the learning module, 4) the analytical module, and 5) the portfolio module. These modules were derived from an assessment of the suitability of the learning style, which indicated the highest level. The result regarding the suitability of the components of the LEP-DT learning model was at the highest level ( x = 4.79, S.D). The value is 0.39. According to the assessment results, the model can be applied to learning management.

Section: Revolution In E-learningmentioning

confidence: 99%

The Design of a Learning Experience Platform using xAPI with Design Thinking Learning to Promote Innovation

Nilmanee,

Sintanakul,

Sakulviriyakitkul

2024

“…Automatic speech recognition is a subfield of artificial intelligence [17] that converts audio signals into text transcription for speech. It can accurately count the words spoken by humans into the voice receiver and understand each one almost perfectly.…”

Section: Automatic Speech Recognitionmentioning

confidence: 99%

Distributed Communicative Language Training Platform Using Automatic Speech Recognition Technology for Smart University

Phuengrod,

Wannapiroon,

Nilsook

2023

The purpose of this research is to achieve the following objectives: 1) Synthesize documents and international research on the characteristics of a smart university. 2) Synthesize the processes of distributed communicative language training (DCLT). 3) Design the system architecture of a DCLT platform that utilizes automatic speech recognition (ASR) technology for a smart university. 4) Evaluate the appropriateness of a DCLT platform that utilizes ASR technology for a smart university. Nine experts were selected for this research. They were required to have more than five years of relevant experience in the field, including expertise in system architecture, distributed enterprise, language teaching, and ASR. The research instruments included a suitable assessment form for evaluating the system architecture of a DCLT platform that utilizes ASR technology for a smart university. The results of this research indicate that the DCLT platform, which utilizes ASR technology, was considered suitable for a smart university.

“…This process has been widely studied in various scientific areas, giving rise to a wide range of theories and models that point to different ways of learning among individuals [14]. We highlight the models that point to the need to take into account the reciprocity between the modes of learning and the modes of teaching, which gives special emphasis to the identification of learning styles [15,16]. This identification allows the teacher to know himself and his students better [17,18], allowing him to design different classroom practices to improve performance.…”

Section: Literature Reviewmentioning

confidence: 99%

The Contextual Environment as a Catalyst for Change in the Learning Process and Learning Styles of Students

Sousa,

Mendonça,

Fontão

2023

This study aims to assess whether students’ learning styles have changed due to the environmental context changes caused by the COVID-19 pandemic outbreak. This analysis is important because learning styles, in addition to predicting vocational outcomes, must inform the design of pedagogical practices and supports used in the teaching environment. To achieve this objective, a cross-sectional analysis was conducted on three cohorts of students who enrolled in an engineering course. Students in group 2 have been under confinement conditions during the previous year, while students in group 3 have been under confinement conditions for the previous two years. Group 1 consists of students who did not experience any confinement. The obtained results lead to the following conclusions: (i) The pandemic outbreak has led to environmental changes, pedagogical practices, and changes in the personality profiles of students, which can significantly impact the learning styles of students entering an engineering degree. (ii) While some learning styles are more susceptible to change, others remain resilient. (iii) The duration of exposure to the environmental changes caused by the pandemic outbreak has a greater impact on the changes in these learning styles.