Claim Missing Document
Check
Articles

Found 2 Documents
Search

Implementasi Logika Fuzzy Mamdani Dalam Klasifikasi Kategori Berat Badan Berbasis IMT Ambon, Matelda Yunanta; Lili, Juniver Veronika; Bandhaso, Victor; Wati, Masna; Septiarini, Anindita
Infotek: Jurnal Informatika dan Teknologi Vol. 8 No. 2 (2025): Infotek : Jurnal Informatika dan Teknologi
Publisher : Fakultas Teknik Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/jit.v8i2.30637

Abstract

Body Mass Index (BMI) is a common method used to classify body weight based on the ratio of weight to height. However, its accuracy is often questioned because it does not account for age and gender, which also influence body composition. This study implements the Mamdani fuzzy logic approach to classify body weight based on BMI while considering age and gender. The system utilizes fuzzy membership functions to dynamically determine categories such as Underweight, Normal, Overweight, and Obese, and is developed using the Python programming language with interactive visualizations. Testing results show that the system can provide more adaptive and personalized classifications. Defuzzification values, such as 59.48 for a BMI of 24.22, indicate a classification consistent with WHO standards—namely, the Normal category. The system also demonstrates that classification results may vary for the same BMI when age or gender differs, as illustrated in multi-demographic visualizations. The centroid defuzzification method produces stable and representative outputs. Evaluation results show high accuracy, consistency in rule base, and an ability to handle data uncertainty. Thus, this system serves as a more flexible alternative to conventional methods in body weight classification.
IDENTIFIKASI POLA KECELAKAAN LALU LINTAS DENGAN K-MEANS CLUSTERING Bandhaso, Victor; Wati, Masna; uddin, Havil
Jurnal Teknologi Informasi dan Komunikasi (TIKomSiN) Vol 14, No 1 (2026): Jurnal Tikomsin, Vol 14, No.1, April 2026
Publisher : STMIK Sinar Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30646/tikomsin.v14i1.1037

Abstract

Traffic accidents represent a complex issue with significant social and economic impacts. This study aims to identify temporal patterns of traffic accidents based on temporal and demographic attributes using the K-Means Clustering algorithm applied to 9,659 accident records in Central Java Province in 2024. Time attributes were converted to decimal format, while occupational data for the involved parties were transformed into numerical codes to enable clustering analysis. The K-Means Clustering algorithm was then employed to generate cluster models. Cluster 0 is characterized by an afternoon peak in incident time around 18.10, with the closest encoded occupational category corresponding to TNI–POLRI personnel. Cluster 1 consists of an average incident occurring at 06.26, predominantly involving homemakers. Cluster 2 is dominated by homemakers, with incidents generally occurring around 17.03. Cluster 3 shows the dominance of TNI–POLRI personnel, with incidents most frequently occurring at 07.19. These findings indicate that the most frequently involved occupational groups are military/police personnel and homemakers, both of which exhibit high mobility during peak hours and also threaten officers who are supposed to maintain traffic order.