Melola Discovery

← Melola Discovery

Jurnal SINTA 2

Unsupervised Detection of Anomalous Sound for Machine Condition Monitoring using Fully Connected U-Net

Journal of ICT Research and Applications (JICTRA) · Vol. 15 No. 1 (2021) · hlm. 41–55

DOI
10.5614/itbj.ict.res.appl.2021.15.1.3
ISSN
2338-5499, 2337-5787
Terbit
2021-06-29
Penerbit
DRI - ITB
Bahasa
eng

Abstrak

Anomaly detection in the sound from machines is an important task in machine monitoring. An autoencoder architecture based on the reconstruction error using a log-Mel spectrogram feature is a conventional approach for this domain. However, because of the non-stationary nature of some sounds from the target machine, such a conventional approach does not perform well in those circumstances. In this paper, we propose a novel approach regarding the choice of used features and a new auto-encoder architecture. We created the Mixed Feature, which is a mixture of different sound representations, and a new deep learning method called Fully-Connected U-Net, a form of autoencoder architecture. With experiments on the same dataset as the baseline system, using the same architecture for all types of machines, the experimental results showed that our methods outperformed the baseline system in terms of the AUC and pAUC evaluation metrics. The optimized model achieved 83.38% AUC and 64.51% pAUC on average overall machine types on the developed dataset and outperformed the published baseline by 13.43% AUC and 8.13% pAUC.

Kata kunci

Jaringan kolaborasi para penulis

4 penulis · 6 tautan kepenulisan bersama

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

  • 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

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://journals.itb.ac.id/index.php/jictra/oai, pertama di-harvest 26 Okt 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">Unsupervised Detection of Anomalous Sound for Machine Condition Monitoring using Fully Connected U-Net</dc:title>
	<dc:creator>Van Truong, Hoang</dc:creator>
	<dc:creator>Chi Hieu, Nguyen</dc:creator>
	<dc:creator>Ngoc Giao, Pham</dc:creator>
	<dc:creator>Xuan Phong, Nguyen</dc:creator>
	<dc:subject xml:lang="en-US">anomaly detection</dc:subject>
	<dc:subject xml:lang="en-US">anomalous sound</dc:subject>
	<dc:subject xml:lang="en-US">auto-encoder</dc:subject>
	<dc:subject xml:lang="en-US">spectrogram</dc:subject>
	<dc:subject xml:lang="en-US">U-Net</dc:subject>
	<dc:description xml:lang="en-US">Anomaly detection in the sound from machines is an important task in machine monitoring. An autoencoder architecture based on the reconstruction error using a log-Mel spectrogram feature is a conventional approach for this domain. However, because of the non-stationary nature of some sounds from the target machine, such a conventional approach does not perform well in those circumstances. In this paper, we propose a novel approach regarding the choice of used features and a new auto-encoder architecture. We created the Mixed Feature, which is a mixture of different sound representations, and a new deep learning method called Fully-Connected U-Net, a form of autoencoder architecture. With experiments on the same dataset as the baseline system, using the same architecture for all types of machines, the experimental results showed that our methods outperformed the baseline system in terms of the AUC and pAUC evaluation metrics. The optimized model achieved 83.38% AUC and 64.51% pAUC on average overall machine types on the developed dataset and outperformed the published baseline by 13.43% AUC and 8.13% pAUC.</dc:description>
	<dc:publisher xml:lang="en-US">DRI - ITB</dc:publisher>
	<dc:date>2021-06-29</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en-US">Peer-reviewed Article</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journals.itb.ac.id/index.php/jictra/article/view/15353</dc:identifier>
	<dc:identifier>10.5614/itbj.ict.res.appl.2021.15.1.3</dc:identifier>
	<dc:source xml:lang="en-US">Journal of ICT Research and Applications; Vol. 15 No. 1 (2021); 41-55</dc:source>
	<dc:source>2338-5499</dc:source>
	<dc:source>2337-5787</dc:source>
	<dc:source>10.5614/itbj.ict.res.appl.2021.15.1</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://journals.itb.ac.id/index.php/jictra/article/view/15353/5267</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2021 Journal of ICT Research and Applications</dc:rights>
</oai_dc:dc>