The Application of Multi Layer Feed Forward Artificial Neural Network for Learning Style Identification

Traditional online learning environments generally use a one-size-fits-all approach, neglecting individual learner needs, goals, and cognitive abilities. Adaptive Educational Hypermedia (AEH) systems emerged to address this by personalizing learning content based on user profiles. The Adaptive Learning System is a computerized system developed to enhance digital interactive educational content teaching and learning. The system’s Adaptive algorithm automatically detects learners’ strengths and weaknesses through the adaptation process and provides personalized learning materials, feedback, and guidance during their learning. Adaptive content allows learners to learn the material at their own pace while providing additional support, evaluation, and resources tailored to each learner. In traditional educational systems, every student is given access to the same learning content regardless of their individual learning needs. Higher education institutions face various challenges when testing and implementing adaptive learning systems for their domain of knowledge. Issues related to technical challenges include processing real-time data, difficulties consolidating learning concepts and solutions into existing learning management systems, and the complexity, ease of use, and usability of adaptive learning systems. However, despite the advancement and technical sophistication in adaptive algorithms, most AEH systems still face significant usability challenges. Learners often struggle with complex interfaces, limited system responsiveness, and poor adaptation to diverse demographics and subject backgrounds. Consequently, the current adaptive systems are underutilized in higher education, with limited empirical evidence on their effectiveness in enhancing student engagement, engagement, quality of experience (QoE), and academic performance. While foundational research work (Brusilovsky, 2001; De Bra et al., 2013) and recent studies (Liu & Lim, 2020; colMOOC project) have shown the importance of adaptive educational hypermedia, yet ongoing issues persist regarding usability, learner control (Paramythis & Loidl-Reisinger, 2004), and empirical validation across varied higher education settings (Latham et al., 2004; Educause, 2018). Systematic investigations into user-controllable personalization and its effects on inclusivity and academic achievement remain limited (Xie et al., 2019; Lundqvist; Warburton, 2019). Furthermore, Li et al. (2021) highlighted that existing systems lack comprehensive cognitive modelling and fail to adequately adapt to individual learner dispositions, which restricts their intelligence and adaptability. This complexity in adaptive systems continues to pose challenges for education overall, as emphasized by Fengying Li, Yifeng He, and Qingshui Xue (2021). Addressing these issues, Dubiel et al. (2022) propose a framework for adaptive user interfaces that integrates the interaction environment to enhance system responsiveness. Therefore, there remains a significant gap in the literature regarding the lack of empirical evaluation of user-controlled personalization, particularly in real-world, multi-disciplinary higher education contexts. Existing research has focused mainly on adaptive algorithmic and technical development, but has not given sufficient attention to practical usability (the lack of effective, usable AEH systems, learner diversity, and actual learner-centered outcomes). Moreover, there is a lack of comprehensive frameworks for evaluating the usability of adaptive educational hypermedia (AEH), and there is limited research on how these adaptive systems can foster inclusivity and fairness among diverse learner populations. Therefore, there is an urgent need to address the usability and complexity problems in AEH systems and to suggest the creation of usable, effective, personalised, learner-centric, and user-controllable AEH systems for higher education environments. This research study addresses these gaps by introducing a personalized, user-controllable Adaptive Educational Hypermedia (AEH) framework specially designed for a Higher Education setting. It evaluates multiple versions of adaptive learning systems across multiple disciplines (English, Malay, Computer Science) revealing significant enhancements in both student achievement and satisfaction. The study not only evaluates multiple versions of adaptive systems but also offers practical recommendations for software developers and educators seeking to implement effective, more intuitive, and learner-centric adaptive systems within real higher educational environments. By exploring the relationships between learner demographics, usability, and academic outcomes, the study promotes inclusivity and equity in digital education. More specifically, it introduces a novel user-controllable personalization feature that empowers learners to customize the learning content to improve their adaptive learning experience, addressing a major limitation found in existing systems. The findings demonstrate significant improvements in student performance and satisfaction with the system’s interface, thereby enhancing subject retention, confirming that adaptive learning systems can effectively improve the academic experience in higher education environments.

Improving online education through automatic learning style identification using a multi-step architecture with ant colony system and artificial neural networks

A multi-layer feed forward neural network model for accurate prediction of flue gas sulfuric acid dew points in process industries

E-learning systems have rapidly evolved from generation to another throughout the recent years. Adaptive Educational Hypermedia System (AEHS) provides capabilities to personalize the web-based system according to student's model such as user's interests, needs, preferences, knowledge, and background, which are personal characteristics gathered explicitly or implicitly. The goal of developing AEHS is to achieve an effective and affective learning performance, as well as to get positive impacts on the student through gaining skills and learning experiences. Most AEHS are technologically-driven to transfer knowledge rather than pedagogically-driven focusing on gaining cognitive skills and other experiences. To overcome this gap many researchers considered Cognitive style (CS) as the most important factor for reasoning and predicting individual traits, learning strategies and other preferences. Furthermore many researchers proposed new cognitive factors- rational, intuitive, and interpersonal as the most innate, brain-based, fixed stable preferences to build a robust adaptive student model dynamically and to get positive influence on the affective and effective AEHS. Based on the literature review, we have identified a number of theoretical and technical issues related to the AEHS architecture in relation to the whole brain cognitive style model to achieve an effective learning outcomes. The findings will be used for designing a user model for AEHS.

Learning style based individualized adaptive e-learning environments: Content analysis of the articles published from 2005 to 2014

The purpose of adaptive educational hypermedia systems (AEHS) is to provide each learner with learning experiences that have been specially tailored to their specific learning requirements. While the concept of AEHS appears promising, AEHS are very complex systems to design and develop. This chapter reviews a few of the challenges encountered in the design and development of these complex systems and some of the challenges encountered by educators who propose to use AEHS with their students. A number of the skills required by educators to develop positive learning experiences are discussed. In order to successfully use AEHS, educators must decide on what student characteristics to base the adaptive elements of the course. Educators may feel challenged to show the impact that AEHS can have on the learning experience. Educators may have a dilemma in deciding to allow or not to allow (1) student access to their user model and (2) students to edit their user model. Further research is required to explore why AEHS have not yet impacted education as initially expected.

Surgical resident learning styles: faculty and resident accuracy at identification of preferences and impact on ABSITE scores

Background: The benefit of online learning materials in medical education is not well defined.Aim: The study correlated certain self-identified learning styles with the use of self-selected online learning materials.Methods: First-year osteopathic medical students were given access to review and/or summary materials via an online course management system (CMS) while enrolled in a pre-clinical course. At the end of the course, students completed a self-assessment of learning style based on the Index of Learning Styles and a brief survey regarding their usage and perceived advantage of the online learning materials.Results: Students who accessed the online materials earned equivalent grades to those who did not. However, the study found that students who described their learning styles as active, intuitive, global, and/or visual were more likely to use online educational resources than those who identified their learning style as reflective, sensing, sequential, and/or verbal.Conclusions: Identification of a student's learning style can help medical educators direct students to learning resources that best suit their individual needs.

The bandsawing as a multi-point cutting operation is the preferred method for cutting off raw materials in industry. Although cutting off with bandsaw is very old process, research efforts are very limited compared to the other cutting process. Appropriate online tool condition monitoring system is essential for sophisticated and automated machine tools to achieve better tool management. Tool wear monitoring models using artificial neural network are developed to predict the tool wear during cutting off the raw materials (American Iron and Steel Institute 1020, 1040 and 4140) by bandsaw. Based on a continuous data acquisition of cutting force signals, it is possible to estimate or to classify certain wear parameters by means of neural networks thanks to reasonably quick data-processing capability. The multi-layered feed forward artificial neural network (ANN) system of a 6 × 9 × 1 structure based on cutting forces was trained using error back-propagation training algorithm to estimate tool wear in bandsawing. The data used for the training and checking of the network were derived from the experiments according to the principles of Taguchi design of experiments planned as L27. The factors considered as input in the experiment were the feed rate, the cutting speed, the engagement length and material hardness. 3D surface plots are generated using ANN model to study the interaction effects of cutting conditions on sawblade. The analysis shows that cutting length, hardness and cutting speed have significant effect on tooth wear, respectively, while feed rate has less effect. In this study, the details of experimentation and ANN application to predict tooth wear have been presented. The system shows that there is close match between the flank wear estimated and measured directly.

Adaptive education systems are considered one of the most interesting research issues in technology-based learning strategies. Since learners have different needs, abilities and learning preferences, we should fit the curriculum and teaching strategies to these different learning styles. This article investigates the impact of using LAES (Libyan Adaptive Education System) on the performance of learners. An ALSI (Arabic Learning Style Instrument) was integrated into the LAES system to consider learner preferences. Results obtained by the learners in the ALSI instrument were used to initialize their profiles. And then, an experimental study was conducted to investigate the impact of LAES system on the performance of learners. The results reveal the students who have learnt using LAES system were better than others who have learnt without the LAES in terms of the knowledge gained.

Identification of learning styles is one way of contributing to a more efficient teaching process, and it helps teachers choose an effective teaching strategy. This study reports a three-year process to explain the change in the learning styles of physical education students. It also involves an assessment of the overall academic achievement of physical education students based on their learning style preferences throughout this process. Forty-one physical education students, 41.5% of whom were female, comprised the sample. The study used a longitudinal study/panel study design to observe the time-dependent variation of learning styles. The data were collected using the Kolb Learning Style Inventory 3 and analysed using a Chi-Squared (χ2) test, Kruskal-Wallis H test, and Mann-Whitney U test. The results of the analysis showed that the curriculum of the PE teaching department did not lead to a change in the learning styles of students studying in this department. Additionally, the overall academic achievement of the physical education students did not vary for the first (Semester 3) and second measurements (Semester 5) based on their learning style preferences. However, for the third measurement (Semester 7), learning style preferences had differing effects on their academic achievement.
 Key Words: Study process, learning style, longitudinal study, teacher candidate

Various types of learners can be observed in today’s e-learning environments. Learning Analytics can offer insights on a student’s actions and behaviour. We can correlate this data with the identification of learning styles like in the Felder-Silverman Learning Styles Model (FSLSM), and use it for user modelling. Supported by visualizations on learning styles and learning behaviour students and instructors can reflect the learning process. Based on our previously published conceptual model for linking learning analytics and learning styles in e-learning environments, we present an Integrated Learning Styles Analytics system (ILSA), which supports identification of learning styles as well as analysis and visualization of activity data in the Moodle LMS. ILSA consists of a questionnaire for learning style identification derived from FSLSM and offers immediate results to its participants. Next, by utilizing various data sources in Moodle, e.g. log data or the grade book, we are able to correlate a user’s activity with their learning styles. This work offers details on the finalized concept as well as its implementation. By providing insights on data sources in Moodle and presenting various visualizations, this work allows teachers to reuse the system in their e-learning courses.

As intelligent systems demand for human–automation interaction increases, the need for learners’ cognitive traits adaptation in adaptive educational hypermedia systems (AEHS) has dramatically increased. AEHS utilize learners’ cognitive processes to attain fair human–automation interaction for their adaptive processes. However, obtaining accurate cognitive trait for the AEHS adaptation process has been a challenge due to the fact that it is difficult to determine what extent such traits can comprehend system functionalities. Hence, this study has explored correlation among learners’ pupil size dilation, learners’ reading time and endogenous blinking rate when using AEHS so as to enable cognitive load estimation in support of AEHS adaptive process. An eye-tracking sensor was used and the study found correlation among learners’ pupil size dilation, reading time and learners’ endogenous blinking rate. Thus, the results show that endogenous blinking rate, pupil size and reading time are not only AEHS reliable parameters for cognitive load measurement but can also support human–automation interaction at large.

Adaptive content selection is recognized as a challenging research issue in adaptive educational hypermedia systems (AEHS). Several efforts have been reported in literature aiming to support the Adaptation Model (AM) design by providing AEHS designers with either guidance for the direct definition of adaptation rules, or semi-automated mechanisms which generate the AM via the implicit definition of such rules. The goal of the semi-automated, decision-based approaches is to generate a continuous decision function that estimates the desired AEHS response, aiming to overcome the insufficiency and/or inconsistency problems of the defined adaptation rule sets. Although such approaches bare the potential to provide efficient AMs, they still miss a commonly accepted framework for evaluating their performance. In this paper, we propose an evaluation framework suitable for validating the performance decision-based approaches in adaptive learning objects selection in AEHS and demonstrate the use of this framework in the case of our proposed decision-based approach for estimating the desired AEHS response.

This chapter presents an adaptive predictive model for a student modeling prediction task in the context of an adaptive educational hypermedia system (AEHS). The task, that consists in determining what kind of learning resources are more appropriate to a particular learning style, presents two issues that are critical. The first is related to the uncertainty of the information about the student’s learning style acquired by psychometric instruments. The second is related to the changes over time of the student’s preferences (concept drift). To approach this task, we propose a probabilistic adaptive predictive model that includes a method to handle concept drift based on statistical quality control. We claim that our approach is able to adapt quickly to changes in the student’s preferences and that it should be successfully used in similar user modeling prediction tasks, where uncertainty and concept drift are presented.Request access from your librarian to read this chapter's full text.