Automatic Detection of Epileptiform EEG Discharges based on the Semi-Classical Signal Analysis (SCSA) method

Li, Peihao; Piliouras, Evangelos; Poghosyan, Vahe; Alhameed, Majed; Laleg‐Kirati, Taous‐Meriem

doi:10.1109/embc46164.2021.9631028

Cited by 2 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An appropriate h interval has been proposed in (Piliouras, 2020) for 1D-signals, where a minimum value for h based on the sampling theorem is introduced. This value had been successfully used in (Piliouras, 2020;Li et al, 2021), providing good accuracy for signal representation. This minimum value is defined as:…”

Section: Parameters Selectionmentioning

confidence: 99%

“…We also considered other features as described in (Li et al, 2021) and which consists of the ratio between the first κ of the eigenvalues matrix and ĥ min (R h ) and the ratio between the median of the κ of all eigenvalues (MR h ), as following:…”

Section: Scsa-based Featuresmentioning

confidence: 99%

“…The mean number of eigenvalues M h obtained in each eigenvalue matrices was used as a feature since this value gives valuable information on signal shape (Li et al, 2021), helping to identify changes in the morphology. Finally, the mean and standard deviation of the κ were used as descriptors of the pixel distribution of the eigenvalues matrices.…”

Section: Scsa-based Featuresmentioning

confidence: 99%

“…This makes these features robust against noisy signals Li and Laleg-Kirati (2021b), Li et al (2021), Garcia et al (2022). Ṫhe limitation of this feature extraction method is the computational complexity causing high running times.…”

Section: Energy-based Featuresmentioning

confidence: 99%

“…Ratio between the median of the κ of all eigenvalues and h Li et al (2021). Lȧw's mask has shown robustness against noise and morphological changes in the images Rachidi et al (2008), Wang (2014), Dash and Jena (2017).…”

Section: Hmentioning

confidence: 99%

See 4 more Smart Citations

A learning-based image processing approach for pulse wave velocity estimation using spectrogram from peripheral pulse wave signals: An in silico study

Vargas

Bahloul²,

Laleg‐Kirati³

2023

Front. Physiol.

View full text Add to dashboard Cite

Carotid-to-femoral pulse wave velocity (cf-PWV) is considered a critical index to evaluate arterial stiffness. For this reason, estimating Carotid-to-femoral pulse wave velocity (cf-PWV) is essential for diagnosing and analyzing different cardiovascular diseases. Despite its broader adoption in the clinical routine, the measurement process of carotid-to-femoral pulse wave velocity is considered a demanding task for clinicians and patients making it prone to inaccuracies and errors in the estimation. A smart non-invasive, and peripheral measurement of carotid-to-femoral pulse wave velocity could overcome the challenges of the classical assessment process and improve the quality of patient care. This paper proposes a novel methodology for the carotid-to-femoral pulse wave velocity estimation based on the use of the spectrogram representation from single non-invasive peripheral pulse wave signals [photoplethysmography (PPG) or blood pressure (BP)]. This methodology was tested using three feature extraction methods based on the semi-classical signal analysis (SCSA) method, the Law’s mask for texture energy extraction, and the central statistical moments. Finally, each feature method was fed into different machine learning models for the carotid-to-femoral pulse wave velocity estimation. The proposed methodology obtained an $R2\geq0.90$ for all the peripheral signals for the noise-free case using the MLP model, and for the different noise levels added to the original signal, the SCSA-based features with the MLP model presented an $R2\geq0.91$ for all the peripheral signals at the level of noise. These results provide evidence of the capacity of spectrogram representation for efficiently assessing the carotid-to-femoral pulse wave velocity estimation using different feature methods. Future work will be done toward testing the proposed methodology for in-vivo signals.

show abstract

Section: Parameters Selectionmentioning

confidence: 99%

Section: Scsa-based Featuresmentioning

confidence: 99%

Section: Scsa-based Featuresmentioning

confidence: 99%

Section: Energy-based Featuresmentioning

confidence: 99%