A deep stacked wavelet auto-encoders to supervised feature extraction to pattern classification

The major issue in pattern classification is in the extraction of features in the training phase. The focus of this work is on combining the ability of wavelet networks and the deep learning techniques to propose a new supervised feature extraction method to pattern classification. This new approach allows the classification of all classes of the dataset by the reconstruction of a Deep Stacked wavelet Auto-Encoder. This Network is obtained after a series of wavelet Auto-Encoders followed by a Softmax classifier at the last layer. Finally, a fine-tuning is applied for the improvement of our result using a back propagation algorithm. Our approach is tested with different image datasets which are the COIL-100, the APTI and the ImageNet datasets and is also tested with two other audio corpuses that contain Arabic words and French words. The experimental test demonstrates the efficiency of our network for image and audio classification compared to other methods.     

State estimation for nonlinear conformable fractional‐order systems: A healthy operating case and a faulty operating case

The issue of estimating states for classical integer‐order nonlinear systems has been widely addressed in the literature. Yet, generalization of existing results to the fractional‐order framework represents a fertile area of research. Note that, recently, a new and advantageous type of fractional derivative, the conformable derivative, was defined. So far, the general query of designing observers for conformable fractional‐order systems has not been investigated. In addition, it has been proved in the literature that some important tools for stability analysis of fractional‐order systems are valid using the conformable derivative concept, but invalid using other fractional derivative concepts. Motivated by the cited facts, this paper presents a first‐state estimation scheme for fractional‐order systems under the conformable derivative concept. A healthy operating case and a faulty operating case are treated. In this paper, a version of Barbalat's lemma, which is invalid using the well‐known Caputo derivative, is exploited to prove the convergence of the estimation errors. In order to validate the theoretical results, a numerical example is studied in the simulation section.     

BicFinder: a biclustering algorithm for microarray data analysis

In the context of microarray data analysis, biclustering allows the simultaneous identification of a maximum group of genes that show highly correlated expression patterns through a maximum group of experimental conditions (samples). This paper introduces a heuristic algorithm called BicFinder (The BicFinder software is available at: ) for extracting biclusters from microarray data. BicFinder relies on a new evaluation function called Average Correspondence Similarity Index (ACSI) to assess the coherence of a given bicluster and utilizes a directed acyclic graph to construct its biclusters. The performance of BicFinder is evaluated on synthetic and three DNA microarray datasets. We test the biological significance using a gene annotation web-tool to show that our proposed algorithm is able to produce biologically relevant biclusters. Experimental results show that BicFinder is able to identify coherent and overlapping biclusters.     

Maximizing the bandwidth of coherent,mid-IR supercontinuum using highly nonlinear aperiodic nanofibers

We describe in detail a new procedure of maximizing the bandwidth of mid-infrared (mid-IR) supercontinuum (SC) in highly nonlinear microstructured As₂Se₃ and tellurite aperiodic nanofibers. By introducing aperiodic rings of first and secondary air holes into the cross-sections of our microstructured fiber designs, we achieve flattened and all-normal dispersion profiles over much broader bandwidths than would be possible with simple periodic designs. These fiber designs are optimized for efficient, broadband, and coherent SC generation in the mid-IR spectral region. Numerical simulations show that these designs enable the generation of a SC spanning over 2290?nm extending from 1140 to 3430?nm in 8?cm length of tellurite nanofiber with input energy of E?=?200?pJ and a SC bandwidth of over 4700?nm extending from 1795 to 6525?nm generated in only 8?mm-length of As₂Se₃-based nanofiber with input energy as low as E?=?100?pJ. This work provides a new type of broadband mid-IR SC source with flat spectral shape as well as excellent coherence and temporal properties by using aperiodic nanofibers with all-normal dispersion suitable for applications in ultrafast science, metrology, coherent control, non-destructive testing, spectroscopy, and optical coherence tomography in the mid-IR region.     

Lack of association between renin-angiotensin system, gene polymorphisms, and wall thickness of the radial and carotid arteries

To investigate the relationship between polymorphisms of the angiotensin-converting enzyme (ACE) and the angiotensin II type 1 receptor (AT1R) genes and structural phenotypes of arteries, we studied a cohort of 340 subjects (aged 49+/-12 years) without evidence of cardiovascular disease and who had never been treated previously with any cardiovascular treatments. Structural phenotypes (wall thickness and internal diameter) were evaluated for the common carotid and the radial arteries using high-resolution echo-tracking devices (NIUS-02 and Wall Track System). The influence of ACE insertion/deletion (I/D) and AT1R A/C1166 polymorphism genotypes on structural parameters was tested by ANOVA and logistic regression analysis. For the radial artery, mean wall thickness among subjects according to the ACE I/D or AT1R A/C1166 genotypes was not different. This lack of association persisted in a logistic regression analysis or when the comparison was restricted to a subgroup of subjects potentially at high genetic risk (DD and CC or AC) compared with subjects at low genetic risk (AA and II or ID). Also, no association was observed between the carotid artery intima-media thickness and the 2 polymorphisms. In conclusion, the ACE I/D and the AT1R A/C1166 gene polymorphisms are not markers of vascular hypertrophy in subjects with no evidence of cardiovascular disease. These results suggest that these gene polymorphisms have an undetectable role in the geometry of the radial and carotid arteries compared with usual determinants such as blood pressure and age.     

Ambiguity attacks on SVD audio watermarking approach using chaotic encrypted images

In this paper, we study the robustness of the proposed watermarking algorithm by Al-Nuaimy et al. (Digit Signal Process 21(6):764–779 2011) for audio signals which is based on singular value decomposition (SVD). It has been concluded that it is fundamentally flawed in its design, in that it falls to two ambiguity attacks where the extracted watermark is not the embedded one but determined by the reference watermark. In the first attack, when a watermarked audio signal is rewatermarked by an attacker’s watermark, this one can be easily extracted to claim ownership of the original audio signal. In the second attack, during the extracting process when an attacker uses the singular vectors of his watermark, he can extract the attacker’s watermark. Therefore, he can claim ownership of the watermarked audio signal. The experimental results prove that the proposed attacks create a false positive detection in watermark extraction. Therefore, Al-Nuaimy et al. algorithm cannot be used for security systems, data hiding and copyright protection.

     

Data Association in Multi-target Tracking Using Belief Function

In this paper, we present a new method for data association in multi-target tracking. The representation and the fusion of the information in our method are based on the use of belief function. The proposal generates the basic belief mass assignment using a modified Mahalanobis distance. While the decision making process is based on the extension of the frame of hypotheses. Our method has been tested for a nearly constant velocity target and compared with both the nearest neighbor filter and the joint probabilistic data associations filter in highly ambiguous cases. The results demonstrate the feasibility of the proposal and show improved performance compared to the aforementioned alternative commonly used methods.     

Robust H ∞ output feedback control with pole placement constraints for uncertain discrete-time fuzzy systems

This paper investigates the problem of multi-objective control for a class of uncertain discrete-time fuzzy systems. The state-space Takagi–Sugeno T–S fuzzy model with linear fractional parameter uncertainties is adopted. Based on a linear matrix inequality approach and via so-called dynamic parallel distributed compensation, a fuzzy full-order dynamic output feedback controller is developed such that the L ₂ gain performance from the exogenous input signals to the controlled output is less than or equal to some prescribed value and, for all admissible uncertainties, the closed-loop poles of each local system are within a pre-specified sub-region of complex plane. Two numerical examples are provided to illustrate the effectiveness of the proposed design method.     

Optimal Natural Convection Heat Transfer Improvement by Combining Periodic Heating Temperature,Cavity Inclination,and Nanofluid

Natural convection within a square inclined cavity filled with Al₂O₃–water nanofluid is investigated numerically. The temperature of the cooled surface is maintained constant, while that of the opposite surface (heating temperature) is varied sinusoidally in time. The remaining walls are considered adiabatic. The parameters governing the problem are the amplitude and the period of the variable temperature, the Rayleigh number, the inclination of the cavity, and the solid volume fraction. A substantial enhancement of heat transfer is obtained by combining the beneficial effects of the variable heating temperature (via its period and amplitude), the inclination of the cavity, and the nanoparticles fraction. In comparison with the constant heating conditions, it is found that both the variable heating temperature and the inclination of the cavity may lead to drastic changes in the flow structure and the corresponding heat transfer. The resonance phenomenon, observed for critical periods of the exciting temperature, is amplified by adding Al₂O₃ nanoparticles to the base fluid.