K-means optimization with bat algorithm for predicting diabetes and hypertension risk in athletes - comparison with machine learning

Aug 3, 2026

This research develops an analytical classification framework for predicting diabetes and hypertension risk in athletes by integrating k-means clustering with a bat algorithm optimizer. The study compares classification performance across Random Forest, Extremely Randomized Trees, and Support Vector Classification, emphasizing method selection for sports data. A case study uses primary data from 200 respondents from Surabaya State University and the East Java National Sports Committee. Evaluation shows the best result is Random Forest combined with k-means and bat optimization, reaching 81.25% accuracy, improving predictive performance and decision support.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Abstract

Introduction

Classification and data types

K-means clustering in machine learning

Initialization sensitivity and optimization need

Bat algorithm for clustering optimization

Proposed hybrid framework overview

Experimental case study and dataset

Results and accuracy comparison

Contributions and potential adaptations

K-means optimization with bat algorithm for predicting diabetes and hypertension risk in athletes’ comparison with machine learning A’yunin Sofro a, 1,*, Danang Ariyanto a,2, Junaidi Budi Prihanto b,3, Dimas Avian Maulana a,4, Riska Wahyu Romadhonia a,5, Asri Maharani c,6, Affi Oktaviarina a,7, Ibnu Febry Kurniawan d,8, Khusnia Nurul Khikmah e,9, Muhammad Mahdy Al Akbar f, 10 a Actuarial Science Department, Universitas Negeri Surabaya, Surabaya, East Java, 60231 Indonesia b Sport Education Department, Universitas Negeri Surabaya, Surabaya, East Java, 60231 Indonesia c School of Health Sciences, Department of Nursing, Manchester Metropolitan University, Bonsall St, Manchester, M15 6GX, United Kingdom d Data Sciences Department, Universitas Negeri Surabaya, Surabaya, East Java, 60231 Indonesia e Mathematics Department, Universitas Palangka Raya, Palangka Raya, Central Kalimantan, 74874 Indonesia f Mathematics Department, Universitas Negeri Surabaya, Surabaya, East Java, 60231 Indonesia [1](1 ayuninsofro@unesa.ac.id)[ ayuninsofro@unesa.ac.id](1 ayuninsofro@unesa.ac.id); [2](2 danangariyanto@unesa.ac.id)[ danangariyanto@unesa.ac.id](2 danangariyanto@unesa.ac.id); [3](3 junaidibudi@unesa.ac.id)[ junaidibudi@unesa.ac.id](3 junaidibudi@unesa.ac.id); [4](4 dimasmaulana@unesa.ac.id)[ dimasmaulana@unesa.ac.id](4 dimasmaulana@unesa.ac.id); [5](5 riskaromadhonia@unesa.ac.id)[ riskaromadhonia@unesa.ac.id](5 riskaromadhonia@unesa.ac.id); [6](6 asri.maharani@manchester.ac.uk)[ asri.maharani@manchester.ac.uk](6 asri.maharani@manchester.ac.uk); [7](7 affiatioktaviarina@unesa.ac.id)[ affiatioktaviarina@unesa.ac.id](7 affiatioktaviarina@unesa.ac.id); [8](8 ibnufebry@unesa.ac.id)[ ibnufebry@unesa.ac.id](8 ibnufebry@unesa.ac.id); [9](9 khusnia. nurulkhikmah@mipa.upr.ac.id)[ khusnia. nurulkhikmah@mipa.upr.ac.id](9 khusnia. nurulkhikmah@mipa.upr.ac.id); [10](10 muhammad.21061@mhs.unesa.ac.id)[ muhammad.21061@mhs.unesa.ac.id](10 muhammad.21061@mhs.unesa.ac.id) * corresponding author ARTICLE INFO ABSTRACT | Article history
Received October 24, 2024
Revised August 11, 2025
Accepted September 13, 2025
Available online November 30, 2025
Keywords
Bat Optimization
Extremely Randomized Trees Machine learning Classification Support Vector Classification | This research aims to develop an analytical approach to classification statistics. The proposed approach combines machine learning with optimization. Considering the urgency of research related to exploring the best methods to apply to sports data. This study proposes a novel framework that combines the k-means clustering results with the bat algorithm to optimize performance prediction for athletes in Indonesia The proposed method aims to explore the data by comparing the classification performance of random forests, extremely randomized trees, and support vector machines. We conducted a case study using primary data from 200 respondents at Surabaya State University and the East Java National Sports Committee. The accuracy results in this study indicate that, based on the performance evaluation metric, the best approach is random forest clustering using k-means with bat algorithm optimization, achieving 81.25% accuracy, compared with other machine learning approaches. This research contributes to the field of classification statistics by introducing a novel hybrid framework that integrates machine learning, clustering, and optimization techniques to improve predictive accuracy, particularly in sports analytics. Beyond sports science, the proposed approach can be adapted to other domains that require robust performance prediction and decision support, such as health analytics, educational assessment, and human resource selection.

© 2025 The Author(s) .
This is an open access article under the CC–BY-SA license
| | --- | --- | 1. Introduction Classification is a fundamental branch of statistics whose main task is to place data points into predefined c

FAQs

What dataset is used for the case study?

The case study uses primary data collected from 200 respondents from Surabaya State University and the East Java National Sports Committee.

Aug 3, 2026

Upload by Theodora