Self-organizing map clustering method for the analysis of e-learning activities

Bara, Musa Wakil; Ahmad, Nor Bahiah; Modu, Mohammed Maina; Ali, Hamisu Alhaji

doi:10.1109/mintc.2018.8363155

Cited by 14 publications

(15 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…a rectangular or hexagonal topology), through 'fitting' a grid of nodes to the data over a fixed number of iterations. The resulting map allows a graphical presentation of the data that can be easily interpreted by map-readers, which can be further classified by the machine learning techniques designed for low dimensionality (Bara et al, 2018;Spielman and Folch, 2015;Natita et al, 2016). Numerous studies have highlighted the utility of SOM for visualising complex, nonlinear statistical relationships within high-dimensional data (Yin, 2008;Bação and Lobo, 2010;Das et al, 2016;Miljković, 2017).…”

Section: 2: Contextualising Todmentioning

confidence: 99%

Considering context and dynamics: A classification of transit-orientated development for New York City

Liu

Singleton

Arribas‐Bel

2020

Journal of Transport Geography

View full text Add to dashboard Cite

Section: 2: Contextualising Todmentioning

confidence: 99%

Considering context and dynamics: A classification of transit-orientated development for New York City

Liu

Singleton

Arribas‐Bel

2020

Journal of Transport Geography

View full text Add to dashboard Cite

“…A considerable amount of literature target predicting learners' performance in completing academic courses, solving quizzes, and reducing dropout rates. Many machines and deep learning techniques such as trained neural networks [18], feed-forward neural networks [19], self-organizing maps [20], recurrent neural networks [21], matrix factorization [22], and probabilistic graphical models [23] have been practiced to develop prediction algorithms in finding the right learning behavior. M-learning systems were developed under the influence of studies in the area of E-learning, intelligent tutoring systems, adaptive learning, and computer-aided learning [24].…”

Section: Related Studies (Learner Modeling Approaches)mentioning

confidence: 99%

Deep neural network based m-learning model for predicting mobile learners’ performance

Adnan¹,

Habib²,

Ashraf³

et al. 2020

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

The use of deep learning (DL) techniques for mobile learning is an emerging field aimed at developing methods for finding mobile learners' learning behavior and exploring important learning features. The learning features (learning time, learning location, repetition rate, content types, learning performance, learning time duration, and so on) act as fuel to DL algorithms based on which DL algorithms can classify mobile learners into different learning groups. In this study, a powerful and efficient m-learning model is proposed based on DL techniques to model the learning process of m-learners. The proposed m-learning model determines the impact of independent learning features on the dependent feature i.e. learners' performance. The m-learning model dynamically and intuitively explores the weights of optimum learning features on learning performance for different learners in their learning environment. Then it split learners into different groups based on features differences, weights, and interrelationships. Because of the high accuracy of the DL technique, it was used to classify learners into five different groups whereas random forest (RF) ensemble method was used in determining each feature importance in making adaptive m-learning model. Our experimental study also revealed that the m-learning model was successful in helping m-learners in increasing their performance and taking the right decision during the learning flow.

show abstract

“…Foi utilizada uma nova abordagem chamada "Frequent Sequential Traversal Pattern Mining" ou FSTSOM, para tratamento de problemas ordenados. Em [Bara et al 2018], foi utilizado o SOM para agrupar alunos de acordo com suas similaridades na interação com a plataforma e foi realizada análises sobre a correlação entre os comportamentos de aprendizagem dos alunos e o grau de sucesso que cada um alcançou.…”

Section: Clusterizaçãounclassified

Identificação de gargalos em e-learnings gamificados e indicação dos erros mais frequentes para viabilizar e priorizar melhorias

Hazin¹,

Leite²,

Macêdo³

et al. 2019

Anais Do XXX Simpósio Brasileiro De Informática Na Educação (SBIE 2019)

View full text Add to dashboard Cite

Due to the growth of e-learning and the recent changes on student learning preferences and behavior, the scientific community has proposed new approaches to support the application of active learning strategies and gamification. This work presents a solution to identify "bottlenecks" in courses, with the purpose of reducing effort of professors and students on the learning process. The solution includes data mining and clustering using Self-Organizing Map (SOM) to verify the course tasks with the highest error rates and then to group its errors by similarity. Thus it was possible to prioritize interventions at the points that most hinder students' progress. The approach was successfully applied in an industrial automation e-learning.Resumo. Diante do novo perfil dos estudantes e do crescimento do e-learning, a comunidade científica vem propondo métodos para produção de cursos gamificados e que utilizam metodologias ativas. Nesse contexto, este trabalho oferece uma contribuição para identificar "gargalos" em cursos gamificados, com propósito de reduzir o esforço de professores e alunos no processo de ensino e aprendizagem. A solução contemplou mineração de dados e clusterização através do Self-Organizing Map (SOM) para identificar as atividades com maior incidência de erros e agrupar os tipos de erros por similaridade. Assim, foi possível priorizar intervenções nos pontos que mais atrapalham o progresso dos estudantes. A abordagem foi aplicada com sucesso em um e-learning de automação industrial.O resultado dessas mudançasé que o processo tradicional de ensino e aprendizagem, orientado em conteúdos e centrado no professor, vem se tornando cada vez mais

show abstract

Self-organizing map clustering method for the analysis of e-learning activities

Cited by 14 publications

References 12 publications

Considering context and dynamics: A classification of transit-orientated development for New York City

Considering context and dynamics: A classification of transit-orientated development for New York City

Deep neural network based m-learning model for predicting mobile learners’ performance

Identificação de gargalos em e-learnings gamificados e indicação dos erros mais frequentes para viabilizar e priorizar melhorias

Contact Info

Product

Resources

About