scholarly journals Time-frequency transforms in analysis of non-stationary quasi-periodic biomedical signal patterns for acoustic anomaly detection

2020 ◽  
pp. 15-23
Author(s):  
Anastasia Iskhakova ◽  
Maxim Alekhin ◽  
Alexey Bogomolov
Keyword(s):  
Pattern Recognition ◽  
Anomaly Detection ◽  
Wavelet Transforms ◽  
Audio Signal ◽  
Digital Processing ◽  
Detection Algorithm ◽  
Inverse Transformation ◽  
Real Time Processing ◽  
Time Frequency ◽  
Acoustic Anomaly

Introduction: New approaches to efficient compression and digital processing of audio signals are relevant today. Thereis a lot of interest to new pattern recognition methods which can improve the quality of acoustic anomaly detection. Purpose:Comparative analysis of methods for time-frequency transformation of audio signal patterns, including non-stationary quasiperiodicbiomedical signals in the problem of acoustic anomaly detection. Results: The study compared different time-frequencytransforms (such as windowed Fourier, Gabor, Wigner, pseudo Wigner, smoothed pseudo Wigner, Choi — Williams, Bertrand, pseudoBertrand, smoothed pseudo Bertrand, and wavelet transforms) based on systematization of their functional characteristics(such as the existence and limitedness of basis functions, presence of zero moments and biorthogonal form, opportunity oftwo-dimensional representation and inverse transformation, real time processing, time-frequency transform quality, controlof time-frequency definition, time and frequency interference suppression, relative computational complexity, fast algorithmimplementation) for the problem of biomedial signal pattern recognition. A comparative table is presented with estimates ofinformation capacity for the considered time-frequency transforms. Practical relevance: The proposed approach can solve someacoustic anomaly detection algorithm implementation problems common in non-stationary quasi-periodic processes, in order tostudy disruptive effects causing a change in the functional state of ergatic system operators.

scholarly journals SELF-SUPERVISED ACOUSTIC ANOMALY DETECTION VIA CONTRASTIVE LEARNING

2021 ◽  
Author(s):  
Hadi Hojjati ◽  
Narges Armanfard
Keyword(s):  
Anomaly Detection ◽  
Detection Algorithm ◽  
Learning Approaches ◽  
Data Transformations ◽  
Specific Data ◽  
Latent Space ◽  
Sound Detection ◽  
Acoustic Anomaly ◽  
Abnormal Points ◽  
First Time

We propose an acoustic anomaly detection algorithm based on the framework of contrastive learning. Contrastive learning is a recently proposed self-supervised approach that has shown promising results in image classification and speech recognition. However, its application in anomaly detection is underexplored. Earlier studies have demonstrated that it can achieve state-of-the-art performance in image anomaly detection, but its capability in anomalous sound detection is yet to be investigated. For the first time, we propose a contrastive learning-based framework that is suitable for acoustic anomaly detection. Since most existing contrastive learning approaches are targeted toward images, the effect of other data transformations on the performance of the algorithm is unknown. Our framework learns a representation from unlabeled data by applying audio-specific data augmentations. We show that in the resulting latent space, normal and abnormal points are distinguishable. Experiments conducted on the MIMII dataset confirm that our approach can outperform competing methods in detecting anomalies.

scholarly journals SELF-SUPERVISED ACOUSTIC ANOMALY DETECTION VIA CONTRASTIVE LEARNING

2021 ◽  
Author(s):  
Hadi Hojjati
Keyword(s):  
Anomaly Detection ◽  
Detection Algorithm ◽  
Learning Approaches ◽  
Data Transformations ◽  
Specific Data ◽  
Latent Space ◽  
Sound Detection ◽  
Acoustic Anomaly ◽  
Abnormal Points ◽  
First Time

We propose an acoustic anomaly detection algorithm based on the framework of contrastive learning. Contrastive learning is a recently proposed self-supervised approach that has shown promising results in image classification and speech recognition. However, its application in anomaly detection is underexplored. Earlier studies have demonstrated that it can achieve state-of-the-art performance in image anomaly detection, but its capability in anomalous sound detection is yet to be investigated. For the first time, we propose a contrastive learning-based framework that is suitable for acoustic anomaly detection. Since most existing contrastive learning approaches are targeted toward images, the effect of other data transformations on the performance of the algorithm is unknown. Our framework learns a representation from unlabeled data by applying audio-specific data augmentations. We show that in the resulting latent space, normal and abnormal points are distinguishable. Experiments conducted on the MIMII dataset confirm that our approach can outperform competing methods in detecting anomalies.

scholarly journals Cyber-Physical Anomaly Detection in Microgrids Using Time-Frequency Logic Formalism

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 20012-20021
Author(s):  
Omar Ali Beg ◽  
Luan Viet Nguyen ◽  
Taylor T. Johnson ◽  
Ali Davoudi
Keyword(s):  
Anomaly Detection ◽  
Time Frequency

scholarly journals OutlierNets: Highly Compact Deep Autoencoder Network Architectures for On-Device Acoustic Anomaly Detection

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4805
Author(s):  
Saad Abbasi ◽  
Mahmoud Famouri ◽  
Mohammad Javad Shafiee ◽  
Alexander Wong
Keyword(s):  
Machine Learning ◽  
Anomaly Detection ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Network Architectures ◽  
Design Exploration ◽  
Convolutional Autoencoder ◽  
Acoustic Anomaly ◽  
Human Operators ◽  
Computational Resources

Human operators often diagnose industrial machinery via anomalous sounds. Given the new advances in the field of machine learning, automated acoustic anomaly detection can lead to reliable maintenance of machinery. However, deep learning-driven anomaly detection methods often require an extensive amount of computational resources prohibiting their deployment in factories. Here we explore a machine-driven design exploration strategy to create OutlierNets, a family of highly compact deep convolutional autoencoder network architectures featuring as few as 686 parameters, model sizes as small as 2.7 KB, and as low as 2.8 million FLOPs, with a detection accuracy matching or exceeding published architectures with as many as 4 million parameters. The architectures are deployed on an Intel Core i5 as well as a ARM Cortex A72 to assess performance on hardware that is likely to be used in industry. Experimental results on the model’s latency show that the OutlierNet architectures can achieve as much as 30x lower latency than published networks.

scholarly journals Detection of Ventricular Fibrillation Based on Ballistocardiography by Constructing an Effective Feature Set

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3524
Author(s):  
Rongru Wan ◽  
Yanqi Huang ◽  
Xiaomei Wu
Keyword(s):  
Ventricular Fibrillation ◽  
Cross Validation ◽  
Rhythmic Activity ◽  
Detection Algorithm ◽  
Motion Artifacts ◽  
Cardiac Monitoring ◽  
Mechanical Activity ◽  
Time Frequency ◽  
S Transform ◽  
Fatal Arrhythmia

Ventricular fibrillation (VF) is a type of fatal arrhythmia that can cause sudden death within minutes. The study of a VF detection algorithm has important clinical significance. This study aimed to develop an algorithm for the automatic detection of VF based on the acquisition of cardiac mechanical activity-related signals, namely ballistocardiography (BCG), by non-contact sensors. BCG signals, including VF, sinus rhythm, and motion artifacts, were collected through electric defibrillation experiments in pigs. Through autocorrelation and S transform, the time-frequency graph with obvious information of cardiac rhythmic activity was obtained, and a feature set of 13 elements was constructed for each 7 s segment after statistical analysis and hierarchical clustering. Then, the random forest classifier was used to classify VF and non-VF, and two paradigms of intra-patient and inter-patient were used to evaluate the performance. The results showed that the sensitivity and specificity were 0.965 and 0.958 under 10-fold cross-validation, and they were 0.947 and 0.946 under leave-one-subject-out cross-validation. In conclusion, the proposed algorithm combining feature extraction and machine learning can effectively detect VF in BCG, laying a foundation for the development of long-term self-cardiac monitoring at home and a VF real-time detection and alarm system.

scholarly journals Influence of Features on Accuracy of Anomaly Detection for an Energy Trading System

Sensors ◽  
2021 ◽  
Vol 21 (12) ◽  
pp. 4237
Author(s):  
Hoon Ko ◽  
Kwangcheol Rim ◽  
Isabel Praça
Keyword(s):  
Anomaly Detection ◽  
Real Time ◽  
Feature Detection ◽  
Trading System ◽  
Judgment Accuracy ◽  
Energy Trading ◽  
Real Time Processing ◽  
Detection Model ◽  
Time Required ◽  
The Relationship

The biggest problem with conventional anomaly signal detection using features was that it was difficult to use it in real time and it requires processing of network signals. Furthermore, analyzing network signals in real-time required vast amounts of processing for each signal, as each protocol contained various pieces of information. This paper suggests anomaly detection by analyzing the relationship among each feature to the anomaly detection model. The model analyzes the anomaly of network signals based on anomaly feature detection. The selected feature for anomaly detection does not require constant network signal updates and real-time processing of these signals. When the selected features are found in the received signal, the signal is registered as a potential anomaly signal and is then steadily monitored until it is determined as either an anomaly or normal signal. In terms of the results, it determined the anomaly with 99.7% (0.997) accuracy in f(4)(S0) and in case f(4)(REJ) received 11,233 signals with a normal or 171anomaly judgment accuracy of 98.7% (0.987).

scholarly journals Interpolation in wavelet spaces and the HRT-conjecture

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Eirik Berge
Keyword(s):  
Compact Group ◽  
Wavelet Transforms ◽  
Reproducing Kernel ◽  
Reproducing Kernel Hilbert Space ◽  
Space Structure ◽  
Locally Compact Group ◽  
Locally Compact ◽  
Positive Type ◽  
Time Frequency ◽  
Hrt Conjecture

AbstractWe investigate the wavelet spaces $$\mathcal {W}_{g}(\mathcal {H}_{\pi })\subset L^{2}(G)$$ W g ( H π ) ⊂ L 2 ( G ) arising from square integrable representations $$\pi :G \rightarrow \mathcal {U}(\mathcal {H}_{\pi })$$ π : G → U ( H π ) of a locally compact group G. We show that the wavelet spaces are rigid in the sense that non-trivial intersection between them imposes strong restrictions. Moreover, we use this to derive consequences for wavelet transforms related to convexity and functions of positive type. Motivated by the reproducing kernel Hilbert space structure of wavelet spaces we examine an interpolation problem. In the setting of time–frequency analysis, this problem turns out to be equivalent to the HRT-conjecture. Finally, we consider the problem of whether all the wavelet spaces $$\mathcal {W}_{g}(\mathcal {H}_{\pi })$$ W g ( H π ) of a locally compact group G collectively exhaust the ambient space $$L^{2}(G)$$ L 2 ( G ) . We show that the answer is affirmative for compact groups, while negative for the reduced Heisenberg group.

Sign in / Sign up

Export Citation Format

Share Document