Claim Missing Document
Check
Articles

Found 2 Documents
Search

Comparison of Support Vector Machine and K-Nearest Neighbors in Breast Cancer Classification Anita Desiani; Adinda Ayu Lestari; M Al-Ariq; Ali Amran; Yuli Andriani
Pattimura International Journal of Mathematics (PIJMath) Vol 1 No 1 (2022): Pattimura International Journal of Mathematics (PIJMath)
Publisher : Pattimura University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (470.745 KB) | DOI: 10.30598/pijmathvol1iss1pp33-42

Abstract

Cancer is one of the leading causes of death, and breast cancer is the second leading cause of cancer death in women. One method to realize the level of malignancy of breast cancer from an early age is by classifying the cancer malignancy using data mining. One of the widely used data mining methods with a good level of accuracy is the Support Vector Machine (SVM) and K-Nearest Neighbors (KNN). Evaluation techniques of percentage split and cross-validation were used to evaluate and compare the SVM and KNN classification models. The result was that the accuracy level of the SVM classification method was better than the KNN classification method when using the cross-validation technique, which is 95,7081%. Meanwhile, the KNN classification method was better than the SVM classification method when using the percentage split technique, which is 95,4220%. From the comparison results, it can be seen that the KNN and SVM methods work well in the classification of breast cancer.
Pengembangan Local Density-Aware Adaptive Distance Weighted K-Nearest Neighbor untuk Klasifikasi Stroke Pada Data Tidak Seimbang Ahyar Supani; Yuli Andriani; Indarto; Ariansyah Saputra
JUPITER (Jurnal Penelitian Ilmu dan Teknologi Komputer) Vol 18 No 3 (2026): Jurnal Penelitian Ilmu dan Teknologi Komputer (JUPITER)
Publisher : Teknik Komputer Politeknik Negeri Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36257/jupiter.v18i3.12520

Abstract

Stroke merupakan salah satu penyebab utama kematian dan disabilitas di dunia sehingga memerlukan deteksi dini untuk meningkatkan keberhasilan penanganan. Penerapan machine learning dalam prediksi risiko stroke masih menghadapi kendala akibat karakteristik dataset yang sangat tidak seimbang (highly imbalanced), sehingga algoritma klasifikasi cenderung bias terhadap kelas mayoritas dan kurang mampu mengidentifikasi kasus stroke sebagai kelas minoritas. Penelitian ini mengusulkan Local Density-Aware Adaptive Distance-Weighted K-Nearest Neighbor (LDADW-KNN) dengan mengintegrasikan informasi local density dan adaptive distance weighting ke dalam mekanisme pembobotan tetangga agar proses weighted voting lebih adaptif terhadap data takseimbang. Pengujian dilakukan menggunakan Stroke Prediction Dataset yang terdiri atas 5.110 sampel dengan rasio ketidakseimbangan kelas sebesar 19,52:1. Tahapan penelitian meliputi preprocessing, normalisasi standar scaler, perhitungan jarak Euclidean, estimasi local density, pembobotan adaptif, dan proses klasifikasi. Hasil pengujian menunjukkan bahwa LDADW-KNN memperoleh accuracy 0,94, recall 0,02, precision 0,11, F1-score 0,03, G-Mean 0,14, Balanced Accuracy 0,51, dan AUC 0,61, dengan kinerja yang kompetitif dibandingkan lima varian KNN pembanding. Meskipun peningkatan deteksi kelas minoritas masih terbatas, metode ini berpotensi menjadi alternatif pengembangan algoritma klasifikasi untuk data medis tidak seimbang dan mendukung pengembangan sistem pendukung keputusan klinis berbasis kecerdasan buatan.