Second-order Time-Reassigned Synchrosqueezing Transform: Application to Draupner Wave Analysis

Fourer, Dominique; Auger, François

doi:10.23919/eusipco.2019.8902342

Cited by 27 publications

(17 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2019, He et al proposed, in [ 24 ], a new variant of the synchrosqueezing technique which overcomes the problem of non reversibility by moving the transform values along the time axis instead of the frequency axis. Hence, the time-reassigned synchrosqueezed STFT (also called first-order horizontal synchrosqueezing) can be defined as [ 25 ]:

where

corresponds to the time reassignment operator which is classically computed using Equation ( 5 ). The marginalization over time of the resulting transform leads to:

…”

Section: Stft-based Time–frequency Analysismentioning

confidence: 99%

See 1 more Smart Citation

On the Use of Concentrated Time–Frequency Representations as Input to a Deep Convolutional Neural Network: Application to Non Intrusive Load Monitoring

Houidi

Fourer

Auger

2020

Entropy

Self Cite

View full text Add to dashboard Cite

Since decades past, time–frequency (TF) analysis has demonstrated its capability to efficiently handle non-stationary multi-component signals which are ubiquitous in a large number of applications. TF analysis us allows to estimate physics-related meaningful parameters (e.g., F0, group delay, etc.) and can provide sparse signal representations when a suitable tuning of the method parameters is used. On another hand, deep learning with Convolutional Neural Networks (CNN) is the current state-of-the-art approach for pattern recognition and allows us to automatically extract relevant signal features despite the fact that the trained models can suffer from a lack of interpretability. Hence, this paper proposes to combine together these two approaches to take benefit of their respective advantages and addresses non-intrusive load monitoring (NILM) which consists of identifying a home electrical appliance (HEA) from its measured energy consumption signal as a “toy” problem. This study investigates the role of the TF representation when synchrosqueezed or not, used as the input of a 2D CNN applied to a pattern recognition task. We also propose a solution for interpreting the information conveyed by the trained CNN through different neural architecture by establishing a link with our previously proposed “handcrafted” interpretable features thanks to the layer-wise relevant propagation (LRP) method. Our experiments on the publicly available PLAID dataset show excellent appliance recognition results (accuracy above 97%) using the suitable TF representation and allow an interpretation of the trained model.

show abstract

where

corresponds to the time reassignment operator which is classically computed using Equation ( 5 ). The marginalization over time of the resulting transform leads to:

…”

Section: Stft-based Time–frequency Analysismentioning

confidence: 99%

“…Hence, an exact signal reconstruction can be obtained using the inverse Fourier transform as [ 25 ]:

…”

Section: Stft-based Time–frequency Analysismentioning

confidence: 99%

On the Use of Concentrated Time–Frequency Representations as Input to a Deep Convolutional Neural Network: Application to Non Intrusive Load Monitoring

Houidi

Fourer

Auger

2020

Entropy

Self Cite

View full text Add to dashboard Cite

show abstract

“…STFT converts the signals into a 2D time-frequency domain by performing Fourier Transform in a fixed window traversing the time domain. Considering a signal f (t), the STFT of f (t) with a window g(t) in Schwartz class, is defined as [16][17][18]:…”

Section: Synchrosqueezing Transformmentioning

confidence: 99%

Specific Emitter Identification Based on Synchrosqueezing Transform for Civil Radar

et al. 2020

View full text Add to dashboard Cite

Time-frequency (TF) signal features are widely used in specific emitter identification (SEI) which commonly arises in many applications, especially for radar signals. Due to data scale and algorithm complexity, it is difficult to obtain an informative representation for SEI with existing TF features. In this paper, a feature extraction method is proposed based on synchrosqueezing transform (SST). The SST feature has an equivalent dimension to Fourier transform, and retains the most relevant information of the signal, leading to on average approximately 20 percent improvement in SEI for complex frequency modulation signals compared with existing handcrafted features. Numerous results demonstrate that the synchrosqueezing TF feature can offer a better recognition accuracy, especially for the signals with intricate time-varying information. Moreover, a linear relevance propagation algorithm is employed to attest to the SST feature importance from the perspective of deep learning.

show abstract

“…This can be utilized in security systems, in which the authors' plan for further work. A promising concept is to use a synchrosqueezing method, which instead of relocating the energy along both time and frequency directions, performs energy concentration in one direction [14], [20] to allow signal enhancement and component extraction. This approach is also one of the plans for further research in this matter.…”

Section: B Computational Complexity Analysismentioning

confidence: 99%

A Comparison of the Recursive and FFT-based Reassignment Methods in Micro-Doppler Analysis

Abratkiewicz

Samczyński

Fourer

2020

2020 IEEE Radar Conference (RadarConf20)

Self Cite

View full text Add to dashboard Cite

Second-order Time-Reassigned Synchrosqueezing Transform: Application to Draupner Wave Analysis

Cited by 27 publications

References 22 publications

On the Use of Concentrated Time–Frequency Representations as Input to a Deep Convolutional Neural Network: Application to Non Intrusive Load Monitoring

On the Use of Concentrated Time–Frequency Representations as Input to a Deep Convolutional Neural Network: Application to Non Intrusive Load Monitoring

Specific Emitter Identification Based on Synchrosqueezing Transform for Civil Radar

A Comparison of the Recursive and FFT-based Reassignment Methods in Micro-Doppler Analysis

Contact Info

Product

Resources

About