Melola Discovery

← Melola Discovery

Open access Jurnal SINTA 5

ANALISIS KOMPARASI KESTABILAN ALGORITMA DECISION TREE DAN RANDOM FOREST UNTUK KLASIFIKASI GANGGUAN TIDUR

AnoaTIK: Jurnal Teknologi Informasi dan Komputer · Vol. 3 No. 2 (2026) · pp. 93–98

DOI
10.33772/anoatik.v3i2.126
ISSN
2987-7652
Published
2026-01-18
Publisher
Program Studi Ilmu Komputer FMIPA-UHO
Language
ind
License
creativecommons.org/licenses/by-sa/4.0

Abstract

English

Sleep disorders are serious health conditions that are closely associated with an increased risk of hypertension and cardiovascular disease. Considering the high cost of conventional clinical diagnostic procedures, data mining techniques for early detection offer an effective alternative. This study aims to conduct a comparative performance analysis between the Decision Tree (C4.5) and Random Forest algorithms in classifying sleep disorders (None, Insomnia, and Sleep Apnea). To address class imbalance issues, this research utilizes the secondary Sleep Health and Lifestyle dataset. To evaluate model stability, a rigorous validation method, Stratified 10-Fold Cross-Validation, is employed. The experimental results indicate that the Random Forest algorithm outperforms the Decision Tree, achieving an average accuracy of 91.41% and a Kappa value of 0.8473. The primary advantage of the Random Forest algorithm lies in its ability to significantly improve the detection sensitivity of the Insomnia class to 88.31%. Based on feature importance analysis, diastolic blood pressure and the BMI category (Overweight) are identified as the most influential features in the diagnostic process. Random Forest is therefore considered a more accurate and stable model for medical decision support systems.

Bahasa Indonesia

Sleep disorders, juga dikenal sebagai gangguan tidur, merupakan masalah kesehatan serius yang berkorelasi erat dengan risiko hipertensi dan penyakit kardiovaskular. Mengingat mahalnya biaya diagnosis klinis konvensional, teknik data mining untuk deteksi dini menjadi alternatif yang efektif. Tujuan dari penelitian ini adalah untuk melakukan analisis perbandingan kinerja antara algoritma Decision Tree (C4.5) dan Random Forest untuk mengklasifikasikan gangguan tidur (None, Insomnia, dan Sleep Apnea). Untuk mengatasi ketidakseimbangan kelas, penelitian ini menggunakan dataset sekunder Sleep Health and Lifestyle. Untuk menguji stabilitas, metode validasi yang ketat, Stratified 10-Fold Cross-validation, digunakan. Hasil pengujian menunjukkan bahwa algoritma Random Forest mengalahkan Decision Tree dengan akurasi rata-rata 91,41% dan nilai Kappa 0,8473. Keunggulan utama algoritma Random Forest adalah kemampuan untuk meningkatkan sensitivitas deteksi kelas Insomnia secara signifikan menjadi 88,31%. Menurut analisis nilai fitur, tekanan darah diastolik dan kategori BMI (Overweight) adalah fitur yang paling umum dalam diagnosis. Random Forest dianggap lebih akurat dan stabil untuk digunakan sebagai model sistem pendukung keputusan medis

Keywords

Collaboration network of the authors

8 authors · 11 co-authorship links

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • Universitas Halu Oleo
  • Affiliation unknown
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Natalis RansiUniversitas Halu Oleo2
AsnaniAffiliation unknown1
Umu KhabibahUniversitas Halu Oleo1
Andi TenriawaruUniversitas Halu Oleo1
Auni TiftazaniUniversitas Halu Oleo1
Amal AnugraUniversitas Halu Oleo1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OAI-PMH (metadata jurnal) https://anoatik.uho.ac.id/index.php/atik/oai, first harvested 26 Okt 2026, last seen 26 Okt 2026.
Original metadata (oai_dc) 
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="id-ID">ANALISIS KOMPARASI KESTABILAN ALGORITMA DECISION TREE DAN RANDOM FOREST UNTUK KLASIFIKASI GANGGUAN TIDUR</dc:title>
	<dc:creator>Soleh, Almunajat Amirul</dc:creator>
	<dc:creator>Rahman, Gusti Arviana</dc:creator>
	<dc:subject xml:lang="id-ID">Klasifikasi</dc:subject>
	<dc:subject xml:lang="id-ID">Random Forest</dc:subject>
	<dc:subject xml:lang="id-ID">decision tree</dc:subject>
	<dc:subject xml:lang="id-ID">gangguan tidur</dc:subject>
	<dc:subject xml:lang="id-ID">stratified cross-validation</dc:subject>
	<dc:subject xml:lang="id-ID">Data Mining</dc:subject>
	<dc:subject xml:lang="en-US">sleep disorder</dc:subject>
	<dc:subject xml:lang="en-US">classification</dc:subject>
	<dc:subject xml:lang="en-US">random forest</dc:subject>
	<dc:subject xml:lang="en-US">decision tree</dc:subject>
	<dc:subject xml:lang="en-US">data mining</dc:subject>
	<dc:subject xml:lang="en-US">stratified cross-validation</dc:subject>
	<dc:description xml:lang="en-US">Sleep disorders are serious health conditions that are closely associated with an increased risk of hypertension and cardiovascular disease. Considering the high cost of conventional clinical diagnostic procedures, data mining techniques for early detection offer an effective alternative. This study aims to conduct a comparative performance analysis between the Decision Tree (C4.5) and Random Forest algorithms in classifying sleep disorders (None, Insomnia, and Sleep Apnea). To address class imbalance issues, this research utilizes the secondary Sleep Health and Lifestyle dataset. To evaluate model stability, a rigorous validation method, Stratified 10-Fold Cross-Validation, is employed. The experimental results indicate that the Random Forest algorithm outperforms the Decision Tree, achieving an average accuracy of 91.41% and a Kappa value of 0.8473. The primary advantage of the Random Forest algorithm lies in its ability to significantly improve the detection sensitivity of the Insomnia class to 88.31%. Based on feature importance analysis, diastolic blood pressure and the BMI category (Overweight) are identified as the most influential features in the diagnostic process. Random Forest is therefore considered a more accurate and stable model for medical decision support systems.</dc:description>
	<dc:description xml:lang="id-ID">Sleep disorders, juga dikenal sebagai gangguan tidur, merupakan masalah kesehatan serius yang berkorelasi erat dengan risiko hipertensi dan penyakit kardiovaskular. Mengingat mahalnya biaya diagnosis klinis konvensional, teknik data mining untuk deteksi dini menjadi alternatif yang efektif. Tujuan dari penelitian ini adalah untuk melakukan analisis perbandingan kinerja antara algoritma Decision Tree (C4.5) dan Random Forest untuk mengklasifikasikan gangguan tidur (None, Insomnia, dan Sleep Apnea). Untuk mengatasi ketidakseimbangan kelas, penelitian ini menggunakan dataset sekunder Sleep Health and Lifestyle. Untuk menguji stabilitas, metode validasi yang ketat, Stratified 10-Fold Cross-validation, digunakan. Hasil pengujian menunjukkan bahwa algoritma Random Forest mengalahkan Decision Tree dengan akurasi rata-rata 91,41% dan nilai Kappa 0,8473. Keunggulan utama algoritma Random Forest adalah kemampuan untuk meningkatkan sensitivitas deteksi kelas Insomnia secara signifikan menjadi 88,31%. Menurut analisis nilai fitur, tekanan darah diastolik dan kategori BMI (Overweight) adalah fitur yang paling umum dalam diagnosis. Random Forest dianggap lebih akurat dan stabil untuk digunakan sebagai model sistem pendukung keputusan medis</dc:description>
	<dc:publisher xml:lang="id-ID">Program Studi Ilmu Komputer FMIPA-UHO</dc:publisher>
	<dc:date>2026-01-18</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://anoatik.uho.ac.id/index.php/atik/article/view/126</dc:identifier>
	<dc:identifier>10.33772/anoatik.v3i2.126</dc:identifier>
	<dc:source xml:lang="en-US">AnoaTIK: Jurnal Teknologi Informasi &amp; Komputer; Vol. 3 No. 2 (2025): Desember 2025; 93-98</dc:source>
	<dc:source xml:lang="id-ID">AnoaTIK: Jurnal Teknologi Informasi dan Komputer; Vol 3 No 2 (2025): Desember 2025; 93-98</dc:source>
	<dc:source>2987-7652</dc:source>
	<dc:source>10.33772/anoatik.v3i2</dc:source>
	<dc:language>ind</dc:language>
	<dc:relation>https://anoatik.uho.ac.id/index.php/atik/article/view/126/44</dc:relation>
	<dc:rights xml:lang="id-ID">Hak Cipta (c) 2026 Almunajat Amirul Soleh, Gusti Arviana Rahman</dc:rights>
	<dc:rights xml:lang="id-ID">https://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>