Claim Missing Document
Check
Articles

Found 3 Documents
Search

Radial Basis Function Model for Obesity Classification Based on Lifestyle and Physical Condition Razak, Farhan Radhiansyah; Biddinika, Muhammad Kunta; Yuliansyah, Herman
Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Vol. 8 No. 2 (2024)
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/eltikom.v8i2.1347

Abstract

Obesity is a chronic condition affecting millions worldwide, influenced by genetic predispositions, environmental factors, lifestyle habits, and excessive caloric intake surpassing energy expenditure. widespread prevalence, existing studies lack a comprehensive exploration of classification models that effectively address the complex interplay between lifestyle and physical attributes. This study tackles the absence of an optimal machine learning model for accurately classifying obesity based on these multifaceted factors. To address this gap, the study evaluates the performance of three machine learning algorithms: Support Vector Machine (SVM) with a Radial Basis Function (RBF) kernel, Naïve Bayes, and K-Nearest Neighbor (KNN). The primary objectives are to identify the most accurate classification approach, analyze the strengths of these algorithms, and highlight the importance of lifestyle and physical attributes in obesity prediction. Experimental findings show that SVM with RBF kernel achieves the highest accuracy at 89%, surpassing the performance of the other models. This study advances the field of obesity classification by offering a detailed comparative analysis of machine learning algorithms and underscoring the critical role of integrating lifestyle and physical factors into predictive modeling.
MEMBANGUN JEJAK DIGITAL POSITIF: CARA MEMANFAATKAN MEDIA SOSIAL SECARA PRODUKTIF Muammar; Razak, Farhan Radhiansyah; Fadlil, Abdul; Herman
Jurnal Pengabdian Informatika Vol. 2 No. 4 (2024): JUPITA Volume 2 Nomor 4, Agustus 2024
Publisher : Jurusan Informatika, Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Penelitian ini mengeksplorasi pentingnya membangun jejak digital positif dan pemanfaatan media sosial secara produktif di kalangan siswa SMK 1 Al-Hikmah 1 Bumiayu. Dengan semakin meningkatnya penggunaan media sosial di Indonesia, siswa seringkali tidak menyadari dampak jangka panjang dari aktivitas mereka di dunia maya. Penelitian ini dilakukan melalui Program Pemberdaya Umat (Prodamat) yang bertujuan untuk meningkatkan kesadaran dan kewaspadaan terhadap jejak digital. Metode penelitian meliputi sosialisasi, pre-test dan post-test kuisioner, penyuluhan edukatif, pelatihan, observasi, serta wawancara. Hasil penelitian menunjukkan peningkatan pemahaman siswa mengenai pentingnya jejak digital dan cara memanfaatkan media sosial secara produktif. Edukasi yang diberikan melalui program ini terbukti efektif dalam meningkatkan pengetahuan siswa tentang jejak digital dan membantu mereka membangun reputasi online yang positif.
SMOTE-SVM for Handling Imbalanced Data in Obesity Classification Biddinika, Muhammad Kunta; Yuliansyah, Herman; Soyusiawaty, Dewi; Razak, Farhan Radhiansyah
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 19, No 2 (2025): April
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.103994

Abstract

 Obesity is a significant health issue associated with various chronic diseases, making its early classification critical for effective interventions. This study investigates the performance of Support Vector Machine (SVM) models with Radial Basis Function (RBF) and Linear kernels on imbalanced obesity datasets. To address data imbalance, Synthetic Minority Over-sampling Technique (SMOTE) and Random Undersampling (RUS) were applied. The results reveal that balancing techniques significantly enhance classification performance, with the Linear model achieving the highest accuracy of 96.54% when balanced using SMOTE. However, limitations include reduced recall for minority classes and potential overfitting risks. These findings underscore the importance of balancing techniques in health data classification and offer insights for further optimizing model performance. The study highlights the need for advanced data balancing strategies to improve predictive accuracy and equity across all classes.