Detecting Learning Patterns in Tertiary Education Using K-Means Clustering

Abstract

We are in the era where various processes need to be online. However, data from digital learning platforms are still underutilised in higher education, yet, they contain student learning patterns, whose awareness would contribute to educational development. Furthermore, the knowledge of student progress would inform educators whether they would mitigate teaching conditions for critically performing students. Less knowledge of performance patterns limits the development of adaptive teaching and learning mechanisms. In this paper, a model for data exploitation to dynamically study students progress is proposed. Variables to determine current students progress are defined and are used to group students into different clusters. A model for dynamic clustering is proposed and related cluster migration is analysed to isolate poorer or higher performing students. K-means clustering is performed on real data consisting of students from a South African tertiary institution. The proposed model for cluster migration analysis is applied and the corresponding learning patterns are revealed.

Acceso a tecnologías en el rendimiento universitario en tiempos del covid-19: análisis de asociación por clústeres

“…Además, es un modelo moderno de aprendizaje automático para agrupar individuos en función de puntajes relacionados (Tuyishimire et al, 2022). También ofrece una solución factible al problema de identificar grupos de estudiantes con actitud similar hacia el aprendizaje y el rendimiento académico a distancia (Ilieva et al, 2021;Sáiz-Manzanares et al, 2021).…”

“…La pandemia del covid-19 ha tenido un impacto significativo en la educación superior a nivel mundial, lo que ha obligado a las instituciones a reconsiderar el uso y las capacidades de las tecnologías de información (TI) (Gamage et al, 2020). En este contexto, se han tomado medidas para responder a las nuevas condiciones, aprovechando los nuevos recursos para adaptarse al confinamiento y garantizar la educación a distancia a través de ellas (Tuyishimire et al, 2022). Todo esto en consonancia con el objetivo de desarrollo sostenible número 4, que promueve la calidad y las oportunidades de aprendizaje para toda la vida (Naciones Unidas, 2020), lo que permite la movilidad social y económica.…”

Research on the strategy of locating abnormal data in internet of things management platform based on improved modified particle swarm optimization convolutional neural network algorithm

“…However, due to the power system's extraordinarily enormous size, how to properly analyze the current data swiftly necessitates the direction of matching control algorithms. Existing data processing and analysis techniques include fuzzy clustering [13], K-means clustering [14][15][16], neural networks [17][18][19][20], and others. Literature [15] proposes a fault routing method based on VMD and permutation entropy feature extraction and combined with the K-means clustering algorithm.…”