Salim Lahmiri

Automated pathologies detection in retina digital images based on complex continuous wavelet transform phase angles

An automated diagnosis system that uses complex continuous wavelet transform (CWT) to process retina digital images and support vector machines (SVMs) for classification purposes is presented. In particular, each retina image is transformed into two one-dimensional signals by concatenating image rows and columns separately. The mathematical norm of phase angles found in each one-dimensional signal at each level of CWT decomposition are relied on to characterise the texture of normal images against abnormal images affected by exudates, drusen and microaneurysms. The leave-one-out cross-validation method was adopted to conduct experiments and the results from the SVM show that the proposed approach gives better results than those obtained by other methods based on the correct classification rate, sensitivity and specificity.

Image denoising in bidimensional empirical mode decomposition domain: the role of Student's probability distribution function.

Hybridisation of the bi-dimensional empirical mode decomposition (BEMD) with denoising techniques has been proposed in the literature as an effective approach for image denoising. In this Letter, the Students probability density function is introduced in the computation of the mean envelope of the data during the BEMD sifting process to make it robust to values that are far from the mean. The resulting BEMD is denoted tBEMD. In order to show the effectiveness of the tBEMD, several image denoising techniques in tBEMD domain are employed; namely, fourth order partial differential equation (PDE), linear complex diffusion process (LCDP), non-linear complex diffusion process (NLCDP), and the discrete wavelet transform (DWT). Two biomedical images and a standard digital image were considered for experiments. The original images were corrupted with additive Gaussian noise with three different levels. Based on peak-signal-to-noise ratio, the experimental results show that PDE, LCDP, NLCDP, and DWT all perform better in the tBEMD than in the classical BEMD domain. It is also found that tBEMD is faster than classical BEMD when the noise level is low. When it is high, the computational cost in terms of processing time is similar. The effectiveness of the presented approach makes it promising for clinical applications.

Denoising techniques in adaptive multi-resolution domains with applications to biomedical images

Variational mode decomposition (VMD) is a new adaptive multi-resolution technique suitable for signal denoising purpose. The main focus of this work has been to study the feasibility of several image denoising techniques in empirical mode decomposition (EMD) and VMD domains. A comparative study is made using 11 techniques widely used in the literature, including Wiener filter, first-order local statistics, fourth partial differential equation, nonlinear complex diffusion process, linear complex diffusion process (LCDP), probabilistic non-local means, non-local Euclidean medians, non-local means, non-local patch regression, discrete wavelet transform and wavelet packet transform. On the basis of comparison of 396 denoising based on peak signal-to-noise ratio, it is found that the best performances are obtained in VMD domain when appropriate denoising techniques are applied. Particularly, it is found that LCDP in combination with VMD performs the best and that VMD is faster than EMD.

Combined partial differential equation filtering and particle swarm optimization for noisy biomedical image segmentation

This paper presents a sequential system to jointly denoise and segment an image contaminated with Gaussian noise. A fourth-order partial differential equation (PDE) filter is used for noise cancelling and particle swarm optimization (PSO) is used for segmentation. The system was tested on a chest X-ray image corrupted with different levels of Gaussian noise and, based on the Jaccard and Dice statistics, the proposed system outperformed nine other hybrid models that denoise and then segment the filtered image.

Pathology grading in retina digital images using student-adjusted empirical mode decomposition and power law statistics

We present a modified two-dimensional empirical mode decomposition method (2D-EMD) for biomedical images using Students probability density function to reduce outlier effects in the envelope estimation step. An application is made for retina pathology grading of high versus low density blot hemorrhage, and high versus low subretinal exudate. Power law regression estimates of image fractal properties in the Fourier domain are used to characterize each pathology grade, and support vector machines (SVM) are employed for classification. On both grading problems, the experimental results indicated that the proposed method outperforms classical 2D-EMD.

Information fusion and S&P500 trend prediction

The purpose of this study is the prediction of Standard & Poors (S&P500) trends (ups and downs) with macroeconomic variables, technical indicators, and investor moods using k-NN algorithm and probabilistic neural networks. More precisely, eleven economic factors, twelve technical indicators and four measures of investors mood were selected as potential predictive variables. Then, the Granger causality test was performed to identify among them the predictive variables that show a strong relationship with the stock market. Finally, the identified inputs are fed to k-NN and PNN separately and the correct detection of stock market ups (+0.5%)-aggressive investment strategy - is computed using the obtained hit ratios. The simulations results from 10-fold experiments show that the average detection rate of k-NN and PNN are respectively 93.45% (±0.0019, standard deviation) and 92.4% (±0.006, standard deviation). The results suggest that aggregating the three categories of information (economic, technical, and psychological information) along with k-NN as classifier leads to high detection accuracy of future stock market ups and downs.

An EMD-SVM screening system for retina digital images: The effect of kernels and parameters

The discrete wavelet transform (DWT) and empirical mode decomposition (EMD) are employed to analyze retina digital images in the frequency domain. In particular, statistical features are extracted from high frequency components of the analyzed images. The purpose is to classify normal versus abnormal images. Three different pathologies are considered including, circinates, drusens, and microaneurysms (MA). Support vector machines (SVM) with polynomial and radial basis function kernel are used to classify retina digital images. The simulation results from leave-one-out method (LOOM) show the effectiveness of the EMD-based features over the DWT-based ones. In addition, the polynomial kernel performs better than the radial basis function kernel.

Statistical features selection from intrinsic mode functions for pathologies detection in retina digital images

The empirical mode decomposition (EMD) is employed to analyze retina digital images in the frequency domain and statistical features are extracted from high frequency components of the analyzed images. The purpose is to classify normal versus abnormal images. Three different pathologies are considered including, circinates, drusens, and microaneurysms (MA). The most informative and non redundant features are ranked and selected by use of statistical features selection techniques; namely t-statistic, entropy, Battacharrayia statistic, the area between the receiver operating characteristic (ROC) and principal component analysis (PCA). Finally, support vector machines (SVM) with polynomial and radial basis function (RBF) kernels are used to classify retina digital images based on the selected features. The simulation results from leave-one-out method (LOOM) show the effectiveness of the EMD-Battacharrayia-SVM achieves 96.54%±0.0293 correct classification rate. Thus, features selection helps improving the accuracy of our system designed for pathologies detection in retina.

An empirical mode decomposition approach for automatic diagnosis of retina digital images

In this study six statistical textural features are extracted from retina digital images processed with the empirical mode decomposition (EMD). They are the mean, standard deviation, smoothness, third moment, uniformity, and entropy. The purpose is to classify normal and abnormal images. Five different pathologies are considered. They are artery sheath, blot hemorrhage, circinates, age-related macular drusens, and microaneurysms. Support vector machines are employed as classifier. Ten random folds are generated to perform cross-validation tests. The average and standard deviation of the correct recognition rate, sensitivity and specificity are computed for each simulation to assess the performance of the classifier. The obtained results generally outperform those given by using the discrete wavelet transform (DWT) instead of the EMD.

The Informational Dynamics of Mean‒Variance Relationships in Fertilizer Markets: An Entropic Investigation

The risk‒return trade-off is a fundamental relationship that has received a large amount of attention in financial and economic analysis. Indeed, it has important implications for understanding linear dynamics in price returns and active quantitative portfolio optimization. The main contributions of this work include, firstly, examining such a relationship in five major fertilizer markets through different time periods: a period of low variability in returns and a period of high variability such as that during which the recent global financial crisis occurred. Secondly, we explore how entropy in those markets varies during the investigated time periods. This requires us to assess their inherent informational dynamics. The empirical results show that higher volatility is associated with a larger return in diammonium phosphate, potassium chloride, triple super phosphate, and urea market, but not rock phosphate. In addition, the magnitude of this relationship is low during a period of high variability. It is concluded that key statistical patterns of return and the relationship between return and volatility are affected during high variability periods. Our findings indicate that entropy in return and volatility series of each fertilizer market increase significantly during time periods of high variability.