Designing high-resolution time–frequency and time–scale distributions for the analysis and classification of non-stationary signals: a tutorial review with a comparison of features performance

Boashash, Boualem; Ouelha, Samir

doi:10.1016/j.dsp.2017.07.015

Cited by 63 publications

(26 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result of the wavelet transformation, spatial distributions called scalograms were obtained. However, in the case of using the STFT transformation, spectral density distributions were obtained, called spectrograms [19]. Examples of distribution results obtained for the s3 sample using sinusoidal excitation are shown in figures 2 and 3.…”

Section: Resultsmentioning

confidence: 99%

“…The scales presented in figure 2 illustrate changes in the areas of greatest activity for the selected sample when the excitation frequency changes. Calculations of TS distributions were carried out using Morlet wavelet (Gabor), which is characterized by the same variance in time and frequency domain [19]. It can be seen that as the frequency increases, the area of greatest activity changes.…”

Section: Resultsmentioning

confidence: 99%

“…However, due to the stochastic nature of the measured MBN signals, analysis procedures have been developed using the combined representation of time and frequency, which allows obtaining holistic information about changes in the material [15÷18]. This article uses two transformations to obtain time-frequency representations of MBN signals defining characteristics in time-frequency (TF) and time-scale (TS) space [19]. First, tests were carried out for a set of magnetic samples subjected to mechanical processes and representing different states of material properties, and, as a consequence, different magnetic properties.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Analysis of measurement conditions influence on the magnetic Barkhausen noise phenomenon

Maciusowicz

Psuj

2020

Weld.Tech.Rev.

View full text Add to dashboard Cite

The effectiveness of the magnetic Barkhausen noise method (MBN), used for non-destructive testing of ferromagnetic materials, depends to a large extent on a number of factors determining the measurement conditions. The use of conditions allowing the highest possible level of discrimination between the various states of the materials state is of highest importance. Therefore, this paper presents an analysis of the impact of measurement conditions on Barkhausen noise signals observed for various states of the material conditions. Taking into consideration the stochastic nature of MBN and the complex characterization of its changes, the analysis was based on the time-frequency representation of the MBN signal. The paper presents selected distributions achieved using two transformation methods. In addi- tion, the extraction methods of features allowing the quantification of complex information were given. Finally, the discrimination ability for a number of parameters and features of MBN signals were deter- mined and the obtained results were discussed.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of measurement conditions influence on the magnetic Barkhausen noise phenomenon

Maciusowicz

Psuj

2020

Weld.Tech.Rev.

View full text Add to dashboard Cite

show abstract

“…These aspects are affected by changes in magnetic properties forced by material changes that occur as a result of several different factors, such as change in the stress state and depth of hardening. There are many features used in audio signal recognition and classification or biomedical applications [56,57,58,59,60]. Those can be useful for BN signal analysis; however, they have not found much interest in previous research.…”

Section: Time-frequency Domain Analysis Of Mbnmentioning

confidence: 99%

“…Those can be useful for BN signal analysis; however, they have not found much interest in previous research. Generally, the spectrogram features are defined by extending T and F domain features definition over the common 2D TF spatial representation [56,57,58,59,60]. This allows obtaining additional information which would not be available under single domain representation regime.…”

Section: Time-frequency Domain Analysis Of Mbnmentioning

confidence: 99%

Use of Time-Dependent Multispectral Representation of Magnetic Barkhausen Noise Signals for the Needs of Non-Destructive Evaluation of Steel Materials

Maciusowicz

Psuj

2019

Sensors

View full text Add to dashboard Cite

Due to the existing relationship between microstructural properties and magnetic ones of the ferromagnetic materials, the application potential of the magnetic Barkhausen noise (BN) method to non-destructive testing is constantly growing. However, the stochastic nature of the Barkhausen effect requires the use of advanced signal processing methods. Recently, the need to apply time-frequency (TF) transformations to the processing of BN signals arose. However, various TF methods have been used in the majority of cases for qualitative signal conditioning and no extensive analysis of TF-based information has been conducted so far. Therefore, in this paper, the wide analysis of BN TF representation was carried out. Considering the properties of TF transformations, the Short-Time Fourier Transform (STFT) was used. A procedure for definition of the envelopes of the TF characteristic was proposed. To verify the quality of extracted features, an analysis was performed on the basis of BN signals acquired during stress loading experiments of steel elements. First, the preliminary experiments were processed for various parameters of the measuring system and calculation procedures. The feature extraction procedure was performed for different modes of TF representations. Finally, the distributions of TF features over the loading stages are presented and their information content was validated using commonly used features derived from time T and frequency F domains.

show abstract

FPGA‐Based Implementation of Real‐Time Cardiologist‐Level Arrhythmia Detection and Classification in Electrocardiograms Using Novel Deep Learning

Chandrasekaran,

Chandran,

Selvam

2024

Circuit Theory & Apps

View full text Add to dashboard Cite

Cardiac arrhythmia refers to irregular heartbeats caused by anomalies in electrical transmission in the heart muscle, and it is an important threat to cardiovascular health. Conventional monitoring and diagnosis still depend on the laborious visual examination of electrocardiogram (ECG) devices, even though ECG signals are dynamic and complex. This paper discusses the need for an automated system to assist clinicians in efficiently recognizing arrhythmias. The existing machine‐learning (ML) algorithms have extensive training cycles and require manual feature selection; to eliminate this, we present a novel deep learning (DL) architecture. Our research introduces a novel approach to ECG classification by combining the vision transformer (ViT) and the capsule network (CapsNet) into a hybrid model named ViT‐Cap. We conduct necessary preprocessing operations, including noise removal and signal‐to‐image conversion using short‐time Fourier transform (SIFT) and continuous wavelet transform (CWT) algorithms, on both normal and abnormal ECG data obtained from the MIT‐BIH database. The proposed model intelligently focuses on crucial features by leveraging global and local attention to explore spectrogram and scalogram image data. Initially, the model divides the images into smaller patches and linearly embeds each patch. Features are then extracted using a transformer encoder, followed by classification using the capsule module with feature vectors from the ViT module. Comparisons with existing conventional models show that our proposed model outperforms the original ViT and CapsNet in terms of classification accuracy for both binary and multi‐class ECG classification. The experimental findings demonstrate an accuracy of 99% on both scalogram and spectrogram images. Comparative analysis with state‐of‐the‐art methodologies confirms the superiority of our framework. Additionally, we configure a field‐programmable gate array (FPGA) to implement the proposed model for real‐time arrhythmia classification, aiming to enhance user‐friendliness and speed. Despite numerous suggestions for high‐performance FPGA accelerators in the literature, our FPGA‐based accelerator utilizes optimization of loop parallelization, FP data, and multiply accumulation (MAC) unit. Our accelerator architecture achieves a 57% reduction in processing time and utilizes fewer resources compared to a floating‐point (FlP) design.

show abstract

Designing high-resolution time–frequency and time–scale distributions for the analysis and classification of non-stationary signals: a tutorial review with a comparison of features performance

Cited by 63 publications

References 58 publications

Analysis of measurement conditions influence on the magnetic Barkhausen noise phenomenon

Analysis of measurement conditions influence on the magnetic Barkhausen noise phenomenon

Use of Time-Dependent Multispectral Representation of Magnetic Barkhausen Noise Signals for the Needs of Non-Destructive Evaluation of Steel Materials

FPGA‐Based Implementation of Real‐Time Cardiologist‐Level Arrhythmia Detection and Classification in Electrocardiograms Using Novel Deep Learning

Contact Info

Product

Resources

About