Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 3

A GENETIC ALGORITHM–PARTICLE SWARM OPTIMIZATION OPTIMIZED DOFCM APPROACH TO ENHANCE CLUSTERING AND OUTLIER DETECTION

BAREKENG: Jurnal Ilmu Matematika dan Terapan · Vol. 20 No. 2 (2026) · hlm. 1453–1472

DOI
10.30598/barekengvol20iss2pp1453-1472
ISSN
2615-3017, 1978-7227
Terbit
2026-01-26
Penerbit
PATTIMURA UNIVERSITY
Bahasa
eng
Lisensi
creativecommons.org/licenses/by-sa/4.0

Abstrak

In the era of Industry 4.0, Big Data from the IoT demands advanced analysis techniques. Outlier detection is vital as anomalies may indicate sensor failures, fraud, or abnormal medical records. Fuzzy clustering methods such as DOFCM are often applied, yet their performance depends on accurate cluster center placement, which remains challenging. While several Fuzzy C-Means extensions address outlier sensitivity, most rely on single optimization strategies. The integration of PSO and GA into DOFCM has been rarely explored, making this study novel in evaluating how different evolutionary algorithms enhance clustering robustness and anomaly detection. This research introduces DOFCM-PSO and DOFCM-GA, tested on five benchmark datasets with outliers: Iris, Wine, Sonar, Diabetes, and Ionosphere. The Silhouette Coefficient (SC) was used as the evaluation metric. Results show that GA consistently outperforms PSO, with SC values improving by approximately 0.02–0.03 (equivalent to an increase of 8–12%) across datasets. For instance, the Iris dataset improved from 0.6029 (PSO) to 0.6291 (GA), while the Wine dataset increased from 0.2759 to 0.2958. In addition, evaluation of computational time and outlier detection further supports these findings. Although GA required slightly longer runtime than PSO, it substantially reduced the number of outliers while still achieving higher SC values. A similar pattern was observed in the Diabetes dataset, where GA decreased outliers from 20 to 7 with a modest SC improvement. These results indicate that PSO is more efficient in runtime, but GA provides more robust clustering by minimizing anomalies and producing better separation quality. Despite promising results, this study is limited by the relatively small dataset sizes and sensitivity to parameter settings, which may influence outcomes. Future work should apply the method to larger datasets and include additional clustering indices. Overall, DOFCM-GA can be considered a robust approach for fuzzy clustering in the presence of anomalies.

Jaringan kolaborasi para penulis

6 penulis · 8 tautan kepenulisan bersama

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Islamic University of Indonesia
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Asmawi GunawanAfiliasi tidak diketahui1
M Albarra BimakasaIslamic University of Indonesia1
Siti Nirmala UntariIslamic University of Indonesia1
Yoel Christopher TjenIslamic University of Indonesia1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OAI-PMH (metadata jurnal) https://ojs3.unpatti.ac.id/index.php/barekeng/oai, pertama di-harvest 5 Nov 2026, terakhir terlihat 15 Nov 2026.
Metadata asli (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="en-US">A GENETIC ALGORITHM–PARTICLE SWARM OPTIMIZATION OPTIMIZED DOFCM APPROACH TO ENHANCE CLUSTERING AND OUTLIER DETECTION</dc:title>
	<dc:creator>Afriyani, Sintia</dc:creator>
	<dc:creator>Fajriyah, Rohmatul</dc:creator>
	<dc:description xml:lang="en-US">In the era of Industry 4.0, Big Data from the IoT demands advanced analysis techniques. Outlier detection is vital as anomalies may indicate sensor failures, fraud, or abnormal medical records. Fuzzy clustering methods such as DOFCM are often applied, yet their performance depends on accurate cluster center placement, which remains challenging. While several Fuzzy C-Means extensions address outlier sensitivity, most rely on single optimization strategies. The integration of PSO and GA into DOFCM has been rarely explored, making this study novel in evaluating how different evolutionary algorithms enhance clustering robustness and anomaly detection. This research introduces DOFCM-PSO and DOFCM-GA, tested on five benchmark datasets with outliers: Iris, Wine, Sonar, Diabetes, and Ionosphere. The Silhouette Coefficient (SC) was used as the evaluation metric. Results show that GA consistently outperforms PSO, with SC values improving by approximately 0.02–0.03 (equivalent to an increase of 8–12%) across datasets. For instance, the Iris dataset improved from 0.6029 (PSO) to 0.6291 (GA), while the Wine dataset increased from 0.2759 to 0.2958. In addition, evaluation of computational time and outlier detection further supports these findings. Although GA required slightly longer runtime than PSO, it substantially reduced the number of outliers while still achieving higher SC values. A similar pattern was observed in the Diabetes dataset, where GA decreased outliers from 20 to 7 with a modest SC improvement. These results indicate that PSO is more efficient in runtime, but GA provides more robust clustering by minimizing anomalies and producing better separation quality. Despite promising results, this study is limited by the relatively small dataset sizes and sensitivity to parameter settings, which may influence outcomes. Future work should apply the method to larger datasets and include additional clustering indices. Overall, DOFCM-GA can be considered a robust approach for fuzzy clustering in the presence of anomalies.</dc:description>
	<dc:publisher xml:lang="en-US">PATTIMURA UNIVERSITY</dc:publisher>
	<dc:date>2026-01-26</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://ojs3.unpatti.ac.id/index.php/barekeng/article/view/19653</dc:identifier>
	<dc:identifier>10.30598/barekengvol20iss2pp1453-1472</dc:identifier>
	<dc:source xml:lang="en-US">BAREKENG: Jurnal Ilmu Matematika dan Terapan; Vol 20 No 2 (2026): BAREKENG: Journal of Mathematics and Its Application; 1453-1472</dc:source>
	<dc:source>2615-3017</dc:source>
	<dc:source>1978-7227</dc:source>
	<dc:source>10.30598/barekengvol20iss2year2026</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://ojs3.unpatti.ac.id/index.php/barekeng/article/view/19653/12410</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2026 Sintia Afriyani, Rohmatul Fajriyah</dc:rights>
	<dc:rights xml:lang="en-US">http://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>