Faiz Hilmawan Masyfa, Daniel Siahaan, Umi Laili Yuhana, Pitoyo Hartono
Assessing students' cognitive profiles is crucial for educators to personalize learning and adapt to individual needs. However, achieving accurate evaluation remains a significant challenge. This study aims to address this challenge by identifying the most effective method to classify cognitive profiles using machine learning techniques. This research uses a hybrid clustering-classification approach to increase the accuracy of cognitive profiling. This study involved a comparative analysis of four clustering methods and seven classification methods to assess their efficacy in cognitive profiling tasks. Through experiments and analysis, this research identified the most effective hybrid approach, combining DBSCAN and Multilayer Perceptron classification, thereby achieving impressive and reliable accuracy. These findings provide important insights into the strengths and limitations of various approaches and provide educators with more accurate tools to personalize learning and improve student outcomes. © 2024 IEEE.
Institut Teknologi Sepuluh Nopember, Department of Informatics, Surabaya, Indonesia; Universitas Negeri Malang, Department of Electrical Engineering and Informatics, Malang, Indonesia; School of Engineering, Chukyo University, Nagoya, Japan