Akademik Veri Yönetim Sistemi
ACTA POLYTECHNICA HUNGARICA, cilt.23, sa.5, ss.165-181, 2026 (SCI-Expanded, Scopus)
Classification is a fundamental task in machine learning that involves assigning data instances to one or more predefined categories or classes. Among the various classification algorithms available is the Core Classification Algorithm (CCA). However, CCA has limitations, particularly when dealing with high-dimensional data, which can negatively affect its classification performance. To address these limitations, this study proposes a new algorithm called the Improved Core Classification Algorithm (ICCA), which enhances the performance of CCA by incorporating novel features and techniques. In this article, the principles and design of ICCA were described and its performance was compared to that of CCA and other state-of-the-art classification methods on four datasets from the healthcare and phishing URLs domains. Experimental results on four datasets demonstrate that ICCA consistently outperforms the original CCA, achieves the highest accuracy on the high-dimensional phishing and cardiovascular datasets, and remains competitive on imbalanced medical data. Overall, this work contributes to the advancement of classification algorithms and provides a valuable tool for various real-world applications.