Mazhar B. Tayel

ECG images classification using artificial neural network based on several feature extraction methods

This paper, presents an intelligent diagnosis system for electrocardiogram (ECG) intensity images using artificial neural network (ANN). Features are extracted from many preprocess such as wavelet decomposition (WD), Edge detection (ED), gray level histogram (GLH), Fast Fourier transform (FFT), and Mean-variance (M-V). The ANN supervised feed-forward back propagation using adaptive learning rate with momentum term algorithm used as a classifier. The input data to the classifier is very large so, ECG images data are grouped in batches that introduced to ANN classifier. The objective of this paper is to introduce an expert system for ECG diagnosis, more suitable preprocess for the used 63 ECG intensity images, and simplest ANN architecture classifier, depending on the higher accuracy of the classifier related to the extracted input features.

A bio-sensory system for increase implant longevity for occlusal analysis

Definition of individual bite force (BF) has been widely used in dentistry domain. In this study, a vivo sensory setup is introduced to simulate and analyze dental implant stress, in order to check out implant quality. Two different proposed sensors are introduced. First is a simple mechanical sensor for hard BF measurements. The second is a kind of new material compound suitable for flexible tactile sensor. It had been reported that excessive occlusal forces applied to the implant prostheses. The proposed biosensors reduce the number of patients and dentist exposure to radiation and avoiding alteration of patient bites that may result in consequential malfunctions and side effects like bone loss, screw loosening, and mastication system failure.

Breast boarder boundaries extraction using statistical properties of Mammogram

Many image processing techniques developed over the past two decades to help radiologists in diagnosing breast cancer. At the same time, many studies proven that an early diagnosis of breast cancer can increase five year survival rate from 60% to 80+% [1]. That made screening programs a mandatory step for females. Therefore, radiologists have to examine a large number of images, which may lead to missed breast lesions at early stage due to work load. Computer-Aided-Diagnosis (CAD) systems can be a powerful tool to overcome this problem by highlighting suspected lesions. However, this task is challenging also from CAD systems point of view due to difficulties in articulating and modeling patterns of abnormalities in a computational way as many pre-porcessing steps need to be done to identify region of interest before pattern recognition algorithms can be applied. In this paper a new proposed thresholding algorithm is introduced for breast boundaries and pectoral muscle determination in Mammograms using statistical properties.

An Introduced Neural Network-Differential Evolution Model for Small Signal Modeling of PHEMTs

Since neural network algorithms are able to model nonlinear relations between different data sets, an introduced neural network model (INN) based on a generalized differential evolution training algorithm (INN-DE) is presented for pseudomorphic high electron mobility transistor (PHEMT). This global optimization algorithm is applied to avoid the local minima problem in the gradient descent-training algorithm and to achieve acceptable solution. The main advantage of this technique is its validation in wide range of frequencies and high accuracy for the small signal characteristics. The proposed (INN-DE) model is used to predict the scattering parameter values for various bias values different from the ones in the data set used for training. This model has been verified by comparing predicted and measured values of a PHEMT for a certain data set of S-parameters at different frequencies and bias points

A proposed implementation method of an audio steganography technique

Steganography is the art of science dealing with hiding secret data inside image, audio, video or text files. In audio steganography; secret message is embedded in the digital sound by slightly altering the binary sequence of the sound file. Existing audio steganography software deal with WAV, AU, and even MP3 sound files. Embedding secret messages in the digital sound is usually a more difficult process than embedding messages in other forms, such as digital images. Audio steganography uses different algorithms, but (LSB) least significant bit is applied in this paper. The quality of sound is depended on the size of the audio which the user selects and length of the message.

A novel design of a MEMS solar cell based on microcantilever-photoinduced bending

Solar energy is one of the major sources of green renewable energy. Photovoltaic (PV) cells have the focus in researches for long time to improve its efficiency and reducing cost. This paper introduces a novel design of a micro solar cell based on MEMS device harvesting thermal and quantum components of solar energy converted into mechanical energy that converted into electrical energy. Even it is a double energy conversion process, the micro solar cell has simple design structure and less expensive compared to the conventional micro PV cell. This device can be used to power wireless micro sensors or as micro battery charger, while arrays of this device can be used for small scale generation.

A self-consistent modeling of 4H-SiC Schottky barrier diodes

The present state of SiC power Schottky barrier diode (SBR) is presented in this paper. 4H-SiC SBD is modeled using a self-consistent model. The model is based on the solution of semiconductor transport equations from the surface to the bulk region. The model includes the effect of oxide thickness at the metal semiconductor interface SiO2/SiC; effective oxide charge at the interfacial layer included the fixed and mobile charges, and the effect of interface state charge density. A very good agreement between the simulated forward characteristics using the present model and published experimental data. The model is used to characterize the barrier height change due to effect of oxide thickness, effective oxide charge, and interface state charge density.

Preparation and characterization of a pseudocapacitor electrode by spraying a conducting polymer onto a flexible substrate

Abstract In this paper, polyaniline is deposited using a spraying technique onto a flexible current collector for pseudocapacitor applications. The polyaniline is characterized using Fourier transform infrared spectroscopy (FTIR), scanning electron microscopy (SEM), and optical absorption studies. The energy density of a pseudocapacitor is higher than that of double-layer supercapacitors due to Faradaic reactions. A high specific capacitance of 594.92 F/g is obtained at a scan rate of 5 mV/s with a scanning potential window of (−0.8 to 0.8 V). The results show an increase in the energy density of 82.63 W h/kg at a potential difference of 1 V using a 4 M potassium hydroxide aqueous electrolyte.

A new hybrid security allocation steganography algorithm

Security, authentication, and identification are essential requirement for confidential data transmission. The will known methods of data encryption attain certain security levels, they make the encrypted data unreadable and unnatural this attracts some unintended observer attention. To search for a higher security approach, Steganography and Cryptography are two popular ways of sending vital information in a secret way. One hides the existence of the message and the other converts the message into an unreadable format. This paper, describes a method for integrating the advantages of Cryptography and Steganography together through image processing. The paper introduces a New Hybrid Security message Allocation Algorithm (NHSA) to achieve a higher level of security. The statistical evaluation of this system shows that, a higher PSNR and MSE are achieved comparing with the other systems.

A new hybrid fuzzy-decomposed full capacity Stego-system

The aim of this paper is to introduce a new hybrid fuzzy-decomposed Stego-system for embedding secret messages into gray scale image. Experiments and evaluation metric parameters show that the Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), Correlation (COR) and Entropy computed by the proposed system are better than those generated by the previous existing system. Thus, a high level of imperceptibility and high level of overall security had been attained.