PENERAPAN METODE EXTREME LEARNING MACHINE UNTUK MENINGKATKAN AKURASI ALGORITMA K-NEAREST NEIGHBORS DALAM KLASIFIKASI PENYAKIT KANKER PAYUDARA

Paulus Arman Pora (Universitas PGRI Kanjuruhan Malang)
Danang Aditya Nugraha (Universitas PGRI Kanjuruhan Malang)
Heri Santoso (Universitas PGRI Kanjuruhan Malang)

BIMASAKTI
Vol 9 No 1 (2026): BIMASAKTI

Breast cancer is a major health concern that poses a significant threat to women across the globe. While early detection plays a vital role in improving survival rates, achieving high diagnostic accuracy continues to be a challenge. In this study, the K-Nearest Neighbors (KNN) algorithm is employed as a fundamental classification technique, which is further enhanced using the Extreme Learning Machine (ELM) to boost the accuracy of breast cancer classification. The dataset utilized in this research was obtained from Kaggle, comprising 569 samples with 32 features. The research methodology involves data preprocessing, dividing the dataset into training and testing sets with different ratios, and assessing the model’s performance through a confusion matrix.The results show that integrating ELM into KNN increases the average accuracy from 70.86% to 95.44%, achieving the highest accuracy of 96.50% at a 75% training and 25% testing ratio. These findings confirm that the ELM–KNN combination produces a more accurate and efficient model for breast cancer diagnosis.