DATA MINING DALAM CLUSTERISASI RISIKO TINGGI OBESITAS MENGGUNAKAN METODE K-MEANS CLUSTERING

ANZILA HASBY, NPM 2109500149 (2025) DATA MINING DALAM CLUSTERISASI RISIKO TINGGI OBESITAS MENGGUNAKAN METODE K-MEANS CLUSTERING. Tugas_Akhir(Artikel) Building of Informatics, Technology and Science (BITS), 7 (1). pp. 863-872. ISSN 2685-331 (e-ISSN) 2684-8910(p-ISSN)

	Text COVER.pdf Download (1MB)
	Text ARTIKEL.pdf Download (848kB)

Abstract

Obesitas adalah kondisi kelebihan lemak tubuh akibat ketidakseimbangan antara asupan dan penggunaan kalori. Masalah ini telah menjadi epidemi global, termasuk di Indonesia, dengan dampak serius pada kesehatan fisik, mental, dan sosial. Perempuan lebih rentan mengalami obesitas karena faktor biologis dan gaya hidup, seperti terlihat dalam data sebuah puskesmas di mana 76,6% penderita obesitas sentral adalah perempuan. sehingga penelitian ini mengembangkan model segmentasi risiko obesitas pada perempuan menggunakan algoritma K-Means Clustering berbasis data sekunder dari Kaggle (n=898) dengan variabel usia, riwayat keluarga, pola konsumsi, aktivitas fisik, hingga mode transportasi yang digunakan. Hasil preprocessing dan normalisasi StandardScaler menunjukkan 2 cluster optimal (Silhouette Score: 0.267), di mana Cluster 1 (usia muda 24.53 tahun, riwayat keluarga obesitas 1.91, konsumsi fast food 1.84, aktivitas fisik rendah 2.71) berisiko lebih tinggi dibandingkan Cluster 0 (usia 41.41 tahun dengan pola hidup lebih sehat), mengungkap interaksi signifikan antara faktor genetik dan gaya hidup sebagai pemicu utama. Temuan ini menyediakan dasar ilmiah untuk intervensi berbasis kelompok, seperti program edukasi gizi terfokus bagi populasi usia muda, sekaligus mendemonstrasikan efektivitas pendekatan data mining dalam kesehatan masyarakat untuk klasifikasi risiko penyakit tidak menular. Kata Kunci: Obesitas; K-Means Clustering; Analisis Cluster; Perempuan; Faktor Risiko =================================================================================================== Obesity is a condition of excess body fat due to an imbalance between calorie intake and expenditure. This problem has become a global epidemic, including in Indonesia, with serious impacts on physical, mental, and social health. Women are more susceptible to obesity due to biological factors and lifestyle choices, as evidenced by data from a community health centre where 76.6% of central obesity patients were women. This study developed an obesity risk segmentation model for women using the K Means Clustering algorithm based on secondary data from Kaggle (n=898), incorporating variables such as age, family history, dietary patterns, physical activity levels, and mode of transportation used. The results of preprocessing and StandardScaler normalisation showed two optimal clusters (Silhouette Score: 0.267), where Cluster 1 (young age 24.53 years, family history of obesity 1.91, fast food consumption 1.84, low physical activity 2.71) has a higher risk compared to Cluster 0 (age 41.41 years with a healthier lifestyle), revealing a significant interaction between genetic factors and lifestyle as the main triggers. These findings provide a scientific basis for group-based interventions, such as targeted nutrition education programmes for the young population, while demonstrating the effectiveness of data mining approaches in public health for classifying the risk of non-communicable diseases. Keywords: Obesity; K-Means Clustering; Cluster Analysis; Women; Risk Factors

Item Type:	Article
Uncontrolled Keywords:	Obesitas, K-Means Clustering, Analisis Cluster, Perempuan, Faktor Risiko ================== Obesity, K-Means Clustering, Cluster Analysis, Women, Risk Factors
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software Z Bibliography. Library Science. Information Resources > Z665 Library Science. Information Science Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4050 Electronic information resources
Divisions:	Fakultas Sains Dan Teknologi > Sistem Informasi
Depositing User:	Unnamed user with email repository@ulb.ac.id
Date Deposited:	09 Oct 2025 04:48
Last Modified:	09 Oct 2025 04:48
URI:	http://repository.ulb.ac.id/id/eprint/1781

Actions (login required)

View Item