¹Dwianti Westari, ²Dr. Abdul Halim,

¹,Universitas Indonesia

²M. Eng, Universitas Indonesia

The diabetes classification system is very useful in the health sector. This paper discusses the classification system for diabetes using the K-Means algorithm. The Pima Indian Diabetes (PID) dataset is used to train and evaluate this algorithm. The unbalanced value range in the attributes affects the quality of the classification result, so it is necessary to preprocess the data which is expected to improve the accuracy of the PID dataset classification result. Two types of preprocessing methods are used that are min-max normalization and z-score normalization. These two normalization methods are used and the classification accuracies are compared. Before the data classification process is carried out, the data is divided into training data and test data. The result of the classification test using the K-Means algorithm has shown that the best accuracy lies in the PID dataset which has been normalized using the min-max normalization method, which 79% compared to z-score normalization.

diabetes, k-means, min-max normalization, z-score normalization, Pima Indian Diabetes (PID)

1) American Diabetes Association, Diagnosis and classification of diabetes mellitus, Diabetes Care 32 (Supplement1) (2009) S62–S67

2) "About diabetes". World Health Organization. Retrieved 4 April 2014

3) Yilmaz N., Inan O., Uzer M.S., " A new data preparation method based on clustering algorithms for diagnosis systems of heart and diabetes diseases," J Med Syst, vol. 38, no. 5 2014.

4) Lowongtraool C., Hiransakolwong N., "Noise filtering in unsupervised clustering using computation intelligence," International Journal of Math, vol. 6, no. 59,pp. 2911-2920,2012

5) Nirmala Devi M.,Appavu alias Balamurugan S.,Swathi U.V., 2013.", An amalgam KNN to predict Diabetes Mellitus", IEEE International Conference on Emerging Trends in Computing, Communication and Nanotechnology(ICECCN), pp 691- 695.

6) Panwar, Madhuri, et al. "K-nearest neighbor based methodology for accurate diagnosis of diabetes mellitus." 2016 Sixth International Symposium on Embedded Computing and System Design (ISED). IEEE, 2016.

7) Malley B, Ramazzotti D, Wu J T-y. Data pre-processing. Secondary analysis of electronic health records. Springer; 2016. p. 115–41.

8) Fikriya, Arina Ashfa, and Sanny Hikmawati. "Support Vector Machine Predictive Analysis Implementation: Case Study of Tax Revenue in Government of South Lampung." Proceeding International Conference on Science and Engineering. Vol. 3. 2020.

9) T. T. Hanifa, S. Al-faraby, F. Informatika, and U. Telkom,“Analisis Churn Prediction pada Data Pelanggan PT . Telekomunikasi dengan Logistic Regression dan Underbagging,” vol. 4, no. 2, pp. 3210–3225, 2017.

10) Azzahra, Darnisa Nasution dkk. Perbandingan Normalisasi Data Untuk KlasifikasiWine Menggunakan Algoritma K-NN. Journal of Caomputer Engineering System and Science Vol. 4 No. 1. Januari 2019.

11) Noor Fitriana, Perbandingan Kinerja Metode Lingkage, Metode Average Lingkage, dan Metode K-Means Dalam menentukan hasil analisis cluster, (Jogyakarta: UNY, 2014), h.22

12) Praja, Abdi, Chairisni Lubis, and Dyah Erny Herwindiati. "Deteksi Penyakit Diabetes dengan Metode Fuzzy C-means Clustering dan K-means Clustering." Computatio: Journal of Computer Science and Information Systems 1.1 (2017): 15- 24.

13) Garcia-Carretero, Rafael, et all. 2020. Use of a K-Nearest Neighbors Model to Predict The Development of Type 2 Diabetes Within 2 Years in An Obese, Hypertensesive Population. International Federation for Medical and Biological Engineering.

14) N. Syafitri. Perbandingan metode KNearestNeighbor (KNN) dan Meode Nearest Cluster Classifier (NCC) Dalam Pengklasifikasian kualitas batik tulis. Teknologi Informasi & pendidikan, Vol 2, no. 1, pp. 45-46, 2010

15) B. A. Muktamar.Implemenasi dengan Naive Bayes Classifier untuk mendukung Strategi pemasaran di Bagian Humas STMIK AMIKOM Yogyakarta [Laporan Penelitian], Yogyakarta, 2013.

VOLUME 04 ISSUE 01 JANUARY 2021