China
Africa
Explore chapters and articles related to this topic
A connected e-learning framework for engineering education
Published in Ataur Rahman, Vojislav Ilic, Blended Learning in Engineering Education, 2018
For many years, researchers in the field of cognitive science have dedicated much effort to developing technologies that monitor learners’ progress and uses these learning data to modify instruction at any time (O’Connell, 2016). This pedagogical approach is referred to as adaptive learning and is enabled by research in artificial intelligence, particularly machine learning. According to Pugliese (2016), adaptive learning systems can be used to dynamically adjust the type of content in accordance with learner’s ability attainment. This content brokering aspect of adaptive learning systems allows for both automated and teacher interventions, with timely feedback that may accelerate learners’ performance. Adaptive learning systems have been criticized by their instruction-centric aspect; however, recent research conducted by VanLEHN (2011) suggests that within their limited area of expertise, currently available adaptive learning systems seem to be just as good as human tutors or instructors. According to Moore (2016), adaptive learning is one of Gartner’s top strategic technologies for higher education with the potential to actualize the promise of scalable personalized learning and granular predictive learning analytics. In this regard, National University, a private institution of higher education in California (Fain, 2017), is the latest higher education institution combining adaptive learning, predictive analytics and competency-based learning to support the personal learning needs and interests of their students.
Framework for Instructional Technology
Published in Vincent G. Duffy, Advances in Applied Human Modeling and Simulation, 2012
Paula J. Durlach, Randall D. Spain
Vanderwaetere, Desmet, and Clarebout (2011) defined adaptive learning environments as those that accommodate different learning needs and abilities of learners by providing individualized instruction. There are various ways in which an adaptive learning environment could adapt to the learner-both in terms of the student data used to make instructional decisions and in the types of instructional decisions that are made. This paper describes a framework for instructional technology (FIT), aimed at delineating four types of instructional decisions that a technology-based learning environment can make: corrective feedback, support, micro-sequencing, and macro-sequencing. Corrective feedback addresses ways that explicit feedback concerning errors could be given. Support addresses how the technology supports the student within a task with hints or prompts. Microsequencing addresses how a technology-based instructional environment determines what content or task to present next within a module. Macro-sequencing addresses how a technology-based instructional environment determines what module to present next. For each decision, FIT lays out a continuum of complexity, which roughly maps to levels of adaptation, and the corresponding sophistication of the student model required to support those decisions. Within any particular instructional system, the level can be different for corrective feedback, macrosequencing, micro-sequencing, and support decisions.
Automation in Educational Services
Published in Edward Y. Uechi, Business Automation and Its Effect on the Labor Force, 2023
An adaptive learning system is designed to adapt a course to a student’s progress, ability, and behavior. The conventional way of teaching teaches all students in the same manner without regard to any particular student’s learning style. Adaptive learning learns about an individual student and changes the pacing of the course and the sequence of the lessons to be a better fit for the individual student. The next lesson the student sees will be based on how well she did on the previous lesson. The computer software program applies a mathematical model to analyze multiple variables indicating the student’s knowledge and behavior. The results of the analysis will then instruct the software to alter the course’s design.
Variable incremental adaptive learning model based on knowledge graph and its application in online learning system
Published in International Journal of Computers and Applications, 2022
With the development of Internet technology, online learning has been widely used, which brings convenience to learners, and also has some problems. Most online learning systems still adopt the traditional teaching method. Although they provide simple data statistics and analysis functions, it is difficult to provide learners with adaptive learning resources according to their learning status and cognitive level. Although there are a large number of learning resources in the system, most of them exist as independent individuals, or they are simply classified. In the process of learning, learners need to spend a lot of time and energy to screen learning resources, which is easy to cause ‘network confusion’ and ‘cognitive overload’ of learners. Although online learning system can enable learners to learn anytime and anywhere, breaking the time and space limitations of traditional teaching, long-term fragmented learning is difficult for learners to master the knowledge structure of the system, affecting the learning effect of learners.
Artificial Neural Networks for Educational Data Mining in Higher Education: A Systematic Literature Review
Published in Applied Artificial Intelligence, 2021
Emmanuel Okewu, Phillip Adewole, Sanjay Misra, Rytis Maskeliunas, Robertas Damasevicius
Bernard et al. (Bernard et al. 2015) used ANN to identify learning styles with a view to customizing learning for high performance, learning satisfaction, and reducing the time required for learning. They opined that adaptive learning systems offer personalized content to students taking into cognizance their learning styles. Though questionnaires can be used to identify students’ learning styles, the authors hinted that the approach has several demerits. To overcome these challenges, research has been carried out on automatic approaches that can identify learning styles. Since this line of research is still at infancy coupled with the fact that current approaches need significant improvement before their effective use in adaptive systems, the authors succumbed to using ANN to identify students’ learning styles. The study evaluated the ANN approach using data from 75 students and it was discovered that it outperformed other approaches in terms of accuracy of identify learning styles. With accurate learning style identification, quality academic advice could be offered students by way of adaptive systems or by informed teachers who know precisely their students’ learning styles. The authors concluded that such informed academic advising leads to greater learning satisfaction, higher performance, and reduced learning time. Despite focusing on enriching learning experience using ANN, the focus was not primarily to identify gaps and challenges confronting the growth of ANN-based EDM. Also, the study is not an SLR.
Benefits of adaptive lessons for pre-class preparation in a flipped numerical methods course
Published in International Journal of Mathematical Education in Science and Technology, 2020
Adaptive learning offers individualized and personalized learning and feedback to students. Today's students are used to customization as well as having interaction and control when searching for knowledge and information [1]. Given this, as well as individual preferences, needs, and aptitudes, a ‘one-size-fits-all’ approach is not optimal. However, adaptive courseware has the goal of analyzing students’ performance using algorithms while they interact with the online environment to learn and practice. The adaptive software is then able to determine recommended content or activities for the student and provide personalized feedback, displaying real-time progress for both the student and instructor via dashboards. In prior flipped classroom research, the lack of a personalized approach with the pre-class preparation that students were asked to complete was identified as a challenge [2]. This served as a motivation for the use of adaptive lessons with the numerical methods flipped classroom. Numerical methods is a broadly-applicable topic taken by students from various engineering disciplines.