Fully learnable deep wavelet transform for unsupervised monitoring of high-frequency time series

@article{Michau2022FullyLD,
  title={Fully learnable deep wavelet transform for unsupervised monitoring of high-frequency time series},
  author={Gabriel Michau and Ga{\"e}tan Frusque and Olga Fink},
  journal={Proceedings of the National Academy of Sciences of the United States of America},
  year={2022},
  volume={119}
}
Significance Monitoring of industrial assets often relies on high-frequency (HF) signal measurements. One difficulty of dealing with such measurements in the industrial context is the conciliation between the high-frequency sampling and low-dimensional decision states (e.g., healthy/unhealthy), in a context where, very often, labels are not available. Here, we propose a fully unsupervised deep-learning framework for high-frequency time series that is able to extract meaningful and sparse… 

Figures and Tables from this paper

Slab Track Condition Monitoring Based on Learned Sparse Features from Acoustic and Acceleration Signals
TLDR
A deep learning framework based on the recently proposed Denoising Sparse Wavelet Network (DeSpaWN) is used to automatically learn meaningful and sparse representations of raw high-frequency signals and it is found that the classification accuracy using acceleration signals can reach almost 100%, irrespective of which feature learning / extraction method is adopted.
AN INTELLIGENT MODEL BASED ON DEEP TRANSFER LEARNING FOR DETECTING ANOMALIES IN CYBER-PHYSICAL SYSTEMS
  • L. Sukhostat
  • Computer Science
    Radio Electronics, Computer Science, Control
  • 2021
TLDR
An approach based on transfer learning and the extreme gradient boosting algorithm, developed for detecting anomalies in acoustic signals of cyber-physical systems, is proposed and recommended for practical use in diagnosing the state of industrial equipment.
Robust Time Series Denoising with Learnable Wavelet Packet Transform
TLDR
This paper proposes to apply a deep learning denoising model inspired by a signal processing, a learnable version of wavelet packet transform that has signficant learning capabilities with few interpretable parameters and has an intuitive initialisation.
Learnable Wavelet Packet Transform for Data-Adapted Spectrograms
TLDR
A deep learning framework for learnable wavelet packet transforms is proposed, enabling to learn features automatically from data and optimise them with respect to the defined objective function.
TCCT: Tightly-Coupled Convolutional Transformer on Time Series Forecasting

References

SHOWING 1-10 OF 50 REFERENCES
MIMII Dataset: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection
TLDR
A new dataset of industrial machine sounds that is called a sound dataset for malfunctioning industrial machine investigation and inspection (MIMII dataset) is presented to assist the machine-learning and signal-processing community with their development of automated facility maintenance.
Learning Sparse Orthogonal Wavelet Filters
TLDR
A method for learning wavelet functions directly from data and imposes an orthogonality constraint on the functions so that the learned wavelets can be used to perform both analysis and synthesis, and extends the framework to multidimensional signals.
A Wavelet Tour of Signal Processing - The Sparse Way, 3rd Edition
TLDR
The central concept of sparsity is explained and applied to signal compression, noise reduction, and inverse problems, while coverage is given to sparse representations in redundant dictionaries, super-resolution and compressive sensing applications.
Feature learning for fault detection in high-dimensional condition monitoring signals
TLDR
An integrated automatic unsupervised feature learning and one-class classification for fault detection that uses data on healthy conditions only for its training, demonstrating a better performance in cases where condition monitoring data contain several non-informative signals.
Deep Scattering Spectrum
A scattering transform defines a locally translation invariant representation which is stable to time-warping deformation. It extends MFCC representations by computing modulation spectrum
An End-to-End Multi-Level Wavelet Convolutional Neural Networks for heart diseases diagnosis
Wavelet Scattering Transform and Ensemble Methods for Side-Channel Analysis
TLDR
This paper proposes to use the Wavelet Scattering Transform, recently proposed by Mallat, for mapping traces into a time-frequency space which is stable under small translation and diffeomorphism and successfully increases the performance of Template Attacks on artificially desynchronized traces and signals from a jitter-protected implementation.
...
...