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

Truong, Hoang Van; Hieu, Nguyen Chi; Giao, Pham Ngoc; Phong, Nguyen Xuan

doi:10.5614/itbj.ict.res.appl.2021.15.1.3

Cited by 10 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our further research are to deeply analyse roles of input features and focus on different sound representations such as Chroma Feature, Spectral Contrast, Tonnetz, etc [24], as well as to explore breathing, speech sounds provided by the Second 2021 DiCOVA Challenge.…”

Section: Discussionmentioning

confidence: 99%

A Cough-based deep learning framework for detecting COVID-19

Truong¹,

Pham²

2022

2022 44th Annual International Conference of the IEEE Engineering in Medicine &Amp; Biology Society (EMBC)

View full text Add to dashboard Cite

This paper presents a deep learning framework for detecting COVID-19 positive subjects from their cough sounds. In particular, the proposed approach comprises two main steps. In the first step, we generate a feature representing the cough sound by combining an embedding extracted from a pre-trained model and handcrafted features extracted from draw audio recording, referred to as the front-end feature extraction. Then, the combined features are fed into different back-end classification models for detecting COVID-19 positive subjects in the second step. Our experiments on the Track-2 dataset of the Second 2021 DiCOVA Challenge achieved the second top ranking with an AUC score of 81.21 and the top F1 score of 53.21 on a Blind Test set, improving the challenge baseline by 8.43% and 23.4% respectively and showing deployability, robustness and competitiveness with the state-of-the-art systems.

show abstract

Section: Discussionmentioning

confidence: 99%

A Cough-based deep learning framework for detecting COVID-19

Truong¹,

Pham²

2022

2022 44th Annual International Conference of the IEEE Engineering in Medicine &Amp; Biology Society (EMBC)

View full text Add to dashboard Cite

show abstract

“…As illustrated in Table 2, Ref. [13] represents the official baseline model provided by DCASE2020 Task 2, while [15,17,28] are the detection methods with x-vectors, the log-Mel spectrogram, and spectral-temporal information fusion as input features, respectively. Additionally, other researchers have proposed machine anomalous sound detection networks [19,20,24,32].…”

Section: Comparison Of Different Detection Methodsmentioning

confidence: 99%

“…In order to devise a more stable approach for extracting acoustic features from machines, some researchers have undertaken experimental investigations into the effectiveness of the log-Mel spectrogram feature [17,18]. This feature extraction method is founded on the Mel filter bank, designed to emulate the auditory perception of the human ear.…”

Section: Introductionmentioning

confidence: 99%

A Machine Anomalous Sound Detection Method Using the lMS Spectrogram and ES-MobileNetV3 Network

Wang,

Mei,

Song

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Unsupervised anomalous sound detection by machines holds significant importance within the realm of industrial automation. Currently, the task of machine-based anomalous sound detection in complex industrial settings is faced with issues such as the challenge of extracting acoustic feature information and an insufficient feature extraction capability within the detection network. To address these challenges, this study proposes a machine anomalous sound detection method using the lMS spectrogram and ES-MobileNetV3 network. Firstly, the log-Mel spectrogram feature and the SincNet spectrogram feature are extracted from the raw wave, and the new lMS spectrogram is formed after fusion, serving as network input features. Subsequently, based on the MobileNetV3 network, an improved detection network, ES-MobileNetV3, is proposed in this paper. This network incorporates the Efficient Channel Attention module and the SoftPool method, which collectively reduces the loss of feature information and enhances the feature extraction capability of the detection network. Finally, experiments are conducted on the dataset provided by DCASE 2020 Task 2. Our proposed method attained an averaged area under the receiver operating characteristic curve (AUC) of 96.67% and an averaged partial AUC (pAUC) of 92.38%, demonstrating superior detection performance compared to other advanced methods.

show abstract

“…Low-cost equipment like microphones simplifies sound data capture. Several recent studies, such as Koizumi et al [16], Suefusa et al [27], and van der et al [28], propose adequate methods for monitoring industrial machines with SAD. Koizumi et al [16] introduced an unsupervised approach within the detection and classification of acoustic scenes and events (DCASE) 2 challenge, primarily providing a baseline for malfunctioning industrial machine investigation and inspection (MIMII) dataset evaluation.…”

Section: Sound-based Anomly Detection (Sad)mentioning

confidence: 99%

SADIS: Real-Time Sound-Based Anomaly Detection for Industrial Systems

Meraneh,

Autrel,

Bouder

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Industrial cyber-physical systems are critical infrastructures vulnerable to cyber-attacks. Anomaly and intrusion detection are widely used approaches to enhance the security of these systems. Existing detection methods can be categorized into two families. The first family detects only known attacks. The second family overcomes this limitation but often has a high false positive rate and a long detection time. This paper investigates the second family using side-channel leakages, particularly sound, for high-accuracy detection of intrusions and anomalies in various industrial systems. Despite sound signal's advantages, such as low-cost equipment, minimal computational requirements, and noninvasive measurement. Current sound-based anomaly detection (SAD) methods face challenges such as sensitivity to background noise, unbalanced sound data, computational costs, and detection accuracy. To tackle these issues, we introduce robot-arm sound dataset (RASD) and present a real-time sound-based anomaly detection for industrial systems (SADIS) approach that uses a simple and efficient method to fingerprint expected sound data with reduced dimensions. It employs an autoencoder (AE) for data classification and utilizes the Mahalanobis distance (MD) as an anomaly-scoring function, enhancing detection performance. Our experiments demonstrate that the SADIS approach achieves an average attack detection rate of over 96%, with a detection time of less than 1 second and low computational costs.

show abstract

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

Cited by 10 publications

References 12 publications

A Cough-based deep learning framework for detecting COVID-19

A Cough-based deep learning framework for detecting COVID-19

A Machine Anomalous Sound Detection Method Using the lMS Spectrogram and ES-MobileNetV3 Network

SADIS: Real-Time Sound-Based Anomaly Detection for Industrial Systems

Contact Info

Product

Resources

About