Sedigheh Ghofrani
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sedigheh Ghofrani has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Ahmad Ayatollahi
Iran University of Science and Technology
2 shared publications - Des McLernon
School of Electronic and Electrical Engineering, University of Leeds, Leeds, U.K.
2 shared publications - Abdulkadir Sengur
Department of Electrical-Electronic Engineering, Faculty of Technology, Firat University, 23000 Elazig, Turkey
1 shared publication - Ali Nikseresht
School of Computer Science, Georgia Institute of Technology, Atlanta, USA
1 shared publication Amiri Parian Mahnaz
Electrical Engineering Department Islamic Azad University South Tehran Branch Tehran Iran
1 shared publicationD.C. McLernnon
1 shared publication
Latest Publications
- 16 November 2025
- Published by Springer Nature in Annals of Biomedical Engineering
- Vol. 54 (2) , 531-548
EFD in Comparison with EWT for Synthetic and EEG Signal Decomposition and Classification of Alzheimer’s Disease and Mild Cognitive Impairment
Purpose This paper investigates the well-known Empirical Wavelet Transform (EWT) and the recently introduced Empirical Fourier Decomposition (EFD) for the early diagnosis of Alzheimer's disease (AD). Both synthetic signals and real EEG data are decomposed and reconstructed, particularly under noisy conditions. Methods EWT and EFD were applied to decompose non-stationary EEG signals into five sub-bands (Delta, Theta, Alpha, Beta, and Gamma). From each sub-band, eight features were extracted and used to classify subjects into AD and Mild Cognitive Impairment (MCI) groups. Among the five classifiers tested, Random Forest (RF) yielded the best performance for both EWT and EFD. In addition to conventional evaluation metrics, Dynamic Time Warping (DTW) and the Kolmogorov–Smirnov (KS) statistic were used for algorithm assessment. Results The results show that EFD outperforms EWT and achieves competitive performance compared to state-of-the-art approaches. Conclusion EFD is a novel decomposition method that demonstrates robust performance on both synthetic and real EEG signals, supporting its potential use in the early diagnosis of Alzheimer's disease.
- 16 November 2025
- Published by Springer Nature in Annals of Biomedical Engineering
- Vol. 54 (2) , 531-548
EFD in Comparison with EWT for Synthetic and EEG Signal Decomposition and Classification of Alzheimer’s Disease and Mild Cognitive Impairment
Purpose This paper investigates the well-known Empirical Wavelet Transform (EWT) and the recently introduced Empirical Fourier Decomposition (EFD) for the early diagnosis of Alzheimer's disease (AD). Both synthetic signals and real EEG data are decomposed and reconstructed, particularly under noisy conditions. Methods EWT and EFD were applied to decompose non-stationary EEG signals into five sub-bands (Delta, Theta, Alpha, Beta, and Gamma). From each sub-band, eight features were extracted and used to classify subjects into AD and Mild Cognitive Impairment (MCI) groups. Among the five classifiers tested, Random Forest (RF) yielded the best performance for both EWT and EFD. In addition to conventional evaluation metrics, Dynamic Time Warping (DTW) and the Kolmogorov–Smirnov (KS) statistic were used for algorithm assessment. Results The results show that EFD outperforms EWT and achieves competitive performance compared to state-of-the-art approaches. Conclusion EFD is a novel decomposition method that demonstrates robust performance on both synthetic and real EEG signals, supporting its potential use in the early diagnosis of Alzheimer's disease.
- 10 January 2023
- Published by Elsevier in Applied Soft Computing
- Vol. 135
Using empirical wavelet transform and high-order fuzzy cognitive maps for time series forecasting
- 10 January 2023
- Published by Elsevier in Applied Soft Computing
- Vol. 135
Using empirical wavelet transform and high-order fuzzy cognitive maps for time series forecasting
- Open Access
- 8 December 2018
- Published by MECS Publisher in International Journal of Image, Graphics and Signal Processing
- Vol. 10 (12) , 11-20
Sparse Representation and Face Recognition
Now a days application of sparse representation are widely spreading in many fields such as face recognition. For this usage, defining a dictionary and choosing a proper recovery algorithm plays an important role for the method accuracy. In this paper, two type of dictionaries based on input face images, the method named SRC, and input extracted features, the method named MKD-SRC, are constructed. SRC fails for partial face recognition whereas MKD-SRC overcomes the problem. Three extension of MKD-SRC are introduced and their performance for comparison are presented. For recommending proper recovery algorithm, in this paper, we focus on three greedy algorithms, called MP, OMP, CoSaMP and another called Homotopy. Three standard data sets named AR, Extended Yale-B and Essex University are used to asses which recovery algorithm has an efficient response for proposed methods. The preferred recovery algorithm was chosen based on achieved accuracy and run time.
- 8 December 2018
- Published by MECS Publisher in International Journal of Image, Graphics and Signal Processing
- Vol. 10 (12) , 11-20
Open AccessSparse Representation and Face Recognition
Now a days application of sparse representation are widely spreading in many fields such as face recognition. For this usage, defining a dictionary and choosing a proper recovery algorithm plays an important role for the method accuracy. In this paper, two type of dictionaries based on input face images, the method named SRC, and input extracted features, the method named MKD-SRC, are constructed. SRC fails for partial face recognition whereas MKD-SRC overcomes the problem. Three extension of MKD-SRC are introduced and their performance for comparison are presented. For recommending proper recovery algorithm, in this paper, we focus on three greedy algorithms, called MP, OMP, CoSaMP and another called Homotopy. Three standard data sets named AR, Extended Yale-B and Essex University are used to asses which recovery algorithm has an efficient response for proposed methods. The preferred recovery algorithm was chosen based on achieved accuracy and run time.
- Open Access
- 18 January 2018
- Published by Springer Nature in EURASIP Journal on Image and Video Processing
- Vol. 2018 (1) , 4
Using BayesShrink, BiShrink, Weighted BayesShrink, and Weighted BiShrink in NSST and SWT for Despeckling SAR Images
- 18 January 2018
- Published by Springer Nature in EURASIP Journal on Image and Video Processing
- Vol. 2018 (1) , 4
Open AccessUsing BayesShrink, BiShrink, Weighted BayesShrink, and Weighted BiShrink in NSST and SWT for Despeckling SAR Images
- Open Access
- 1 June 2017
- Published by Institution of Engineering and Technology (IET) in IET Signal Processing
- Vol. 11 (4) , 429-436
Mℓ 1,2 ‐MUSIC algorithm for DOA estimation of coherent sources
Recasting the direction of arrival (DOA) estimation problem into sparse model is a subject of many researches, which has been carried out by different methods. Using the compressive sensing (CS) multiple measurement vector recovery algorithms have improved the resolution of DOA estimation in comparison with conventional methods such as multiple signal classification (MUSIC). In addition, a recently introduced hybrid method using CS and array processing named as ℓ 1,2 ‐MUSIC exhibits high resolution as well as capability of resolving coherent sources. However, with recent advances in technology and employing higher order polynomial sources due to non‐linear frequency characteristic, the performance of conventional methods is poor when the size of the array is small or the noise level is high. A novel hybrid method is presented based on matching pursuit (MP) signal decomposition and the ℓ 1,2 ‐MUSIC algorithm. The new approach named Mℓ 1,2 ‐MUSIC takes MP decomposition coefficients of the signal into account and applies the ℓ 1,2 ‐MUSIC to achieve DOA estimation. Along with improving the resolvability of closely located non‐stationary sources (high ordered polynomial phase) with small‐sized sensor array, the main advantage of the proposed method is robustness to source coherency.
- 1 June 2017
- Published by Institution of Engineering and Technology (IET) in IET Signal Processing
- Vol. 11 (4) , 429-436
Open AccessMℓ 1,2 ‐MUSIC algorithm for DOA estimation of coherent sources
Recasting the direction of arrival (DOA) estimation problem into sparse model is a subject of many researches, which has been carried out by different methods. Using the compressive sensing (CS) multiple measurement vector recovery algorithms have improved the resolution of DOA estimation in comparison with conventional methods such as multiple signal classification (MUSIC). In addition, a recently introduced hybrid method using CS and array processing named as ℓ 1,2 ‐MUSIC exhibits high resolution as well as capability of resolving coherent sources. However, with recent advances in technology and employing higher order polynomial sources due to non‐linear frequency characteristic, the performance of conventional methods is poor when the size of the array is small or the noise level is high. A novel hybrid method is presented based on matching pursuit (MP) signal decomposition and the ℓ 1,2 ‐MUSIC algorithm. The new approach named Mℓ 1,2 ‐MUSIC takes MP decomposition coefficients of the signal into account and applies the ℓ 1,2 ‐MUSIC to achieve DOA estimation. Along with improving the resolvability of closely located non‐stationary sources (high ordered polynomial phase) with small‐sized sensor array, the main advantage of the proposed method is robustness to source coherency.
- Open Access
- 8 January 2015
- Published by MECS Publisher in International Journal of Image, Graphics and Signal Processing
- Vol. 7 (2) , 15-22
Comparing Nonsubsampled Wavelet, Contourlet and Shearlet Transforms for Ultrasound Image Despeckling
Ultrasound images suffer of multiplicative noise named speckle. Bayesian shrinkage in transform domain is a well-known method based on finding threshold value to suppress the speckle noise. The main problem of applying Bayesian shrinkage is finding the optimum threshold value in appropriate transform domain. In this paper, we compare the performance of adaptive Bayesian thresholding when nonsubsampled Wavelet, Contourlet and Shearlet transforms are used. We processed two synthetic test images and three original ultrasound images as well to demonstrate the efficiency of the designed filters. In order to compare the performance of Bayesian shrinkage when employing the three mentioned transform domain, we used peak signal to noise ratio (PSNR), mean square error (MSE), and structural similarity (SSIM) as the full-reference (FR) objective criteria parameters and noise variance (NV), mean square difference (MSD), and equivalent number of looks (ENL) as the no-reference (NR) objective criteria parameters
- 8 January 2015
- Published by MECS Publisher in International Journal of Image, Graphics and Signal Processing
- Vol. 7 (2) , 15-22
Open AccessComparing Nonsubsampled Wavelet, Contourlet and Shearlet Transforms for Ultrasound Image Despeckling
Ultrasound images suffer of multiplicative noise named speckle. Bayesian shrinkage in transform domain is a well-known method based on finding threshold value to suppress the speckle noise. The main problem of applying Bayesian shrinkage is finding the optimum threshold value in appropriate transform domain. In this paper, we compare the performance of adaptive Bayesian thresholding when nonsubsampled Wavelet, Contourlet and Shearlet transforms are used. We processed two synthetic test images and three original ultrasound images as well to demonstrate the efficiency of the designed filters. In order to compare the performance of Bayesian shrinkage when employing the three mentioned transform domain, we used peak signal to noise ratio (PSNR), mean square error (MSE), and structural similarity (SSIM) as the full-reference (FR) objective criteria parameters and noise variance (NV), mean square difference (MSD), and equivalent number of looks (ENL) as the no-reference (NR) objective criteria parameters
- 1 September 2014
- Published by Elsevier in Measurement
- Vol. 55, 126-132
GA-SELM: Greedy algorithms for sparse extreme learning machine
- 1 September 2014
- Published by Elsevier in Measurement
- Vol. 55, 126-132
GA-SELM: Greedy algorithms for sparse extreme learning machine
- Open Access
- 1 July 2014
- Published by Institution of Engineering and Technology (IET) in IET Signal Processing
- Vol. 8 (5) , 540-551
Matching pursuit for direction of arrival estimation in the presence of Gaussian noise and impulsive noise
Two high‐resolution direction of arrival (DOA) estimation approaches of non‐stationary narrowband signals based on matching pursuit (MP) are developed. The first sensor output is considered as the reference and decomposed by MP. As the MP is a linear decomposition, the obtained MP coefficients contain the steering vector information. So, the MP coefficients corresponding to the leading decomposition atoms are used to develop the MP‐MUSIC algorithm for the DOA estimation. In addition, the chosen MP atoms are used to implement the modified spatial time–frequency distribution (STFD) based on Wigner Ville (WV) distribution as well, and this method named MP‐WV. It has been demonstrated that these two methods can be applied for underdetermined problems and are robust against Gaussian and impulsive noises. The authors show that using either coefficients or chosen atoms to estimate the DOA in array processing by considering the source discriminative capability outperforms the conventional MUSIC and STFD. Some simulation results showing the performance of the two proposed approaches based on MP, conventional MUSIC and STFD are presented.
- 1 July 2014
- Published by Institution of Engineering and Technology (IET) in IET Signal Processing
- Vol. 8 (5) , 540-551
Open AccessMatching pursuit for direction of arrival estimation in the presence of Gaussian noise and impulsive noise
Two high‐resolution direction of arrival (DOA) estimation approaches of non‐stationary narrowband signals based on matching pursuit (MP) are developed. The first sensor output is considered as the reference and decomposed by MP. As the MP is a linear decomposition, the obtained MP coefficients contain the steering vector information. So, the MP coefficients corresponding to the leading decomposition atoms are used to develop the MP‐MUSIC algorithm for the DOA estimation. In addition, the chosen MP atoms are used to implement the modified spatial time–frequency distribution (STFD) based on Wigner Ville (WV) distribution as well, and this method named MP‐WV. It has been demonstrated that these two methods can be applied for underdetermined problems and are robust against Gaussian and impulsive noises. The authors show that using either coefficients or chosen atoms to estimate the DOA in array processing by considering the source discriminative capability outperforms the conventional MUSIC and STFD. Some simulation results showing the performance of the two proposed approaches based on MP, conventional MUSIC and STFD are presented.
- 7 December 2013
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 8 (4) , 687-697
Using Curvelet transform for watermarking based on amplitude modulation
- 7 December 2013
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 8 (4) , 687-697
Using Curvelet transform for watermarking based on amplitude modulation
- 27 March 2013
- Published by Elsevier in Signal Processing
- Vol. 93 (12) , 3466-3478
High-resolution direction finding of non-stationary signals using matching pursuit
- 27 March 2013
- Published by Elsevier in Signal Processing
- Vol. 93 (12) , 3466-3478
High-resolution direction finding of non-stationary signals using matching pursuit