Cut Aulia Safira Rahman
Sekolah Vokasi, Universitas Gadjah Mada

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Application of the K-Nearest Neighbors (KNN) Algorithm for Diabetes Mellitus Classification: Evidence from Aceh Province, Indonesia Cut Aulia Safira Rahman; Rizky Wahyu Aulia; Azhar Azhar; Rahmad Hidayat
Jurnal Teknologi Rekayasa Informasi dan Komputer Vol 9, No 1 (2026): JURNAL TRIK - POLITEKNIK NEGERI LHOKSEUMAWE
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jtrik.v9i1.8721

Abstract

Diabetes mellitus is a non-communicable disease with a steadily increasing prevalence in Indonesia, including Aceh Province. Early detection using data-driven approaches is essential to minimize the risk of severe complications. This study aims to classify diabetes mellitus by implementing the K-Nearest Neighbors (KNN) algorithm. The dataset comprises 1,500 instances from the Pima Indians Diabetes Dataset obtained from Kaggle and an additional 100 instances collected from hospitals across Aceh Province. Data preprocessing involved normalization and label encoding, followed by data partitioning into training and testing sets using a 90:10 ratio. The KNN model was configured with a parameter value of K=5. Experimental results indicate that the proposed model achieved an accuracy of 85%, precision of 87%, recall of 82%, and an F1-score of 85% on the Kaggle dataset. For the hospital dataset, the model attained an accuracy of 76%, precision of 80.95%, recall of 68%, and an F1-score of 73.91%. These findings suggest that the KNN algorithm demonstrates adequate performance in classifying diabetes mellitus and may serve as a basis for the development of data-driven medical decision support systems.
Facial Skin Color Classification Using Hybrid Features With The K-Nearest Neighbor (KNN) Method Nurul Agustina; Radhiyatammardhiyyah; Cut Aulia Safira Rahman
International Journal of Applied Artificial Intelligence and Robotics Vol. 2 No. 2 (2026): Vol 2 No 2 (November 2026)
Publisher : PT. Literasi Teknologi Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.67745/ijaic.v2i2.26

Abstract

Facial skin color classification can still be affected by differences in lighting, cameras, and image conditions, causing visual assessment to potentially produce inconsistent results. This study aims to develop a facial skin color classification system using a combination of color and texture features and the K-Nearest Neighbor (KNN) algorithm. The research data consist of primary and secondary datasets. The research stages include data collection, preprocessing, color feature extraction using Color Moments in the YCbCr color space, texture feature extraction using Gray Level Co-occurrence Matrix (GLCM), hybrid feature construction, KNN classification, and performance evaluation. The color and texture features are combined into a hybrid feature representation, which is then used as the input for KNN. K-value testing was conducted using several configurations to determine the optimal parameter. The results show that K = 3 achieved the highest performance in both dataset scenarios. The primary dataset achieved an accuracy of 90.61%, while the secondary dataset achieved an accuracy of 87.43%. Class-wise evaluation indicates that the model can recognize all three skin color categories with good performance. The results demonstrate that combining color and texture information can be an effective approach for facial skin color classification.