Characterization of microembolic behavior, as solid or gaseous, guides to an efficient treatment protocol. In this study a new methodology to classify microembolic signals by Deep Convolutional Neural Networks (CNN) is implemented. The experimental system is made up of a flow phantom (ATSLaB) with a cylinder of 6 mm in width. Contrast agents composed of bubbles are employed in this investigational study to imitate the ultrasonic characteristics of gaseous emboli. A Doppler liquid which contains particles, have scatter proprieties analogous to red blood cells, is exploited to mimic the ultrasonic characteristics of the solid emboli. In order to optimize the CNN topology in the training phase, an adaptive learning Root Mean Square (RMSProp) algorithm is used. A classification rate of 99.9% is achieved in this experimental study. These results demonstrate that the CNN optimized model can be adequately exploited for microemboli classification using radio frequency (RF) signals compared to artificial neural networks (ANN) models.

This paper presents a hybrid strategy combining compact analytical models of short channel Gate-All-Around Junctionless (GAAJ) MOSFET and metaheuristic-based approach for parameters optimization. The proposed GAAJ MOSFET design includes highly extension regions doping. The aim is to investigate the impact of this design on the RF and analog performances systematically and to show the immunity behavior against the short channel effects (SCEs) degradation. In this context, an analytical model via the meticulous solution of 2D Poisson equation, incorporating source/drain (S/D) extensions effect, has been developed and verified by comparing it with TCAD simulation results. A comparative evaluation between the proposed GAAJ MOSFET structure and the classical device in terms of RF/Analog performances is also investigated. The proposed design provides RF/Analog performances improvement. Furthermore, based on the presented analytical models, Genetic Algorithms (GA) optimization approach is used to optimize the design of S/D parameters. The optimized structure exhibits better performances, i.e., cut-off frequency and drive current are improved. Besides, it shows superior immunity behavior against the RF/Analog degradation due to the unwanted SCEs. The insights offered by the proposed paradigm will help to enlighten designer in future challenges facing the GAAJ MOSFET technology for high RF/analog applications.

The security of multimedia documents becomes an urgent need, especially with the increasing image falsifications provided by the easy access and use of image manipulation tools. Hence, usage of image authentication techniques fulfills this need. In this paper, we propose an effective self-embedding fragile watermarking scheme for color images tamper detection and restoration. To decrease the capacity of insertion, a Bayer pattern is used to reduce the color host image into a gray-level watermark, to further improve the security Torus Automorphism permutation is used to scramble the gray-level watermark. In our algorithm, three copies of the watermark are inserted over three components (R, G, and B channels) of the color host image, providing a high probability of detection accuracy and recovery if one copy is destroyed. In the tamper detection process, a majority voting technique is used to determine the legitimacy of the image and recover the tampered regions after interpolating the extracted gray-level watermark. Using our proposed method, tampering rate can achieve 25% with a high visual quality of recovered image and PSNR values greater than 34 (dB). Experimental results demonstrate that the proposed method affords three major properties: the high quality of watermarked image, the sensitive tamper detection and high localization accuracy besides the high-quality of recovered image.

The high suppleness of Bayesian networks has led to their wide application in a variety of dependability modeling and analysis problems. The main objective of this paper is to extend the use of such powerful tool to estimate the occurrence frequency of failures and consequences in a straightforward way. Such extension is based on the employment of a transformation operator to substitute the original terms with matrices that hold the full dependability description of the corresponding element. Two simple case studies in reliability and safety contexts are treated using the suggested method whose results are validated through their comparison to the corresponding results of other classical dependability techniques.

In this study, an optimized extended Kalman filter (EKF), and an interval type-2 fuzzy sliding mode control (IT2FSMC) in presence of uncertainties and disturbances are presented for robotic manipulators. The main contribution is the proposal of a novel application of Biogeography-Based Optimization (BBO) to optimize the EKF in order to achieve high performance estimation of states. The parameters to be optimized are the covariance matrices Q and R, which play an important role in the performances of EKF. The interval type-2 fuzzy logic system is used to avoid chattering phenomenon in the sliding mode control (SMC). Lyapunov theorem is used to prove the stability of control system. The suggested control approach is demonstrated using a computer simulation of two-link manipulator. Finally, simulations results show the robustness and effectiveness of the proposed scheme, and exhibit a more superior performance than its conventional counterpart.

Automatic Speech Recognition can be considered as a transcription of spoken utterances into text which can be used to monitor/command a specific system. In this paper, we propose a general end-to-end approach to sequence learning that uses Long Short-Term Memory (LSTM) to deal with the non-uniform sequence length of the speech utterances. The neural architecture can recognize the Arabic spoken digit spelling of an isolated Arabic word using a classification methodology, with the aim to enable natural human-machine interaction. The proposed system consists to, first, extract the relevant features from the input speech signal using Mel Frequency Cepstral Coefficients (MFCC) and then these features are processed by a deep neural network able to deal with the non uniformity of the sequences length. A recurrent LSTM or GRU architecture is used to encode sequences of MFCC features as a fixed size vector that will feed a multilayer perceptron network to perform the classification. The whole neural network classifier is trained in an end-to-end manner. The proposed system outperforms by a large gap the previous published results on the same database.

The emergence of new data handling technologies and analytics enabled the organization of big data in processes as an innovative aspect in wireless sensor networks (WSNs). Big data paradigm, combined with WSN technology, involves new challenges that are necessary to resolve in parallel. Data aggregation is a rapidly emerging research area. It represents one of the processing challenges of big sensor networks. This paper introduces the big data paradigm, its main dimensions that represent one of the most challenging concepts, and its principle analytic tools which are more and more introduced in the WSNs technology. The paper also presents the big data challenges that must be overcome to efficiently manipulate the voluminous data, and proposes a new classification of these challenges based on the necessities and the challenges of WSNs. As the big data aggregation challenge represents the center of our interest, this paper surveys its proposed strategies in WSNs.