ايمان عبدالعزيز غني الظاهر

Recently, Botnets have become a common tool for implementing and transferring various malicious codes over the Internet. These codes can be used to execute many malicious activities including DDOS attack, send spam, click fraud, and steal data. Therefore, it is necessary to use Modern technologies to reduce this phenomenon and avoid them in advance in order to differentiate the Botnets traffic from normal network traffic. In this work, ensemble classifier algorithms to identify such damaging botnet traffic. We experimented with different ensemble algorithms to compare and analyze their ability to classify the botnet traffic from the normal traffic by selecting distinguishing features of the network traffic. Botnet Detection offers a reliable and cheap style for ensuring transferring integrity and warning the risks before its occurrence.

Recently, the most user-friendly systems in the biometric world are face recognition systems. In addition, they are one of the active research fields while the researchers work to ameliorate the effectiveness and competence of biometric implementations. The major challenge to be in these implementations is to extract the useful features sets which are not disturbed caused by number of factors, including person movement, illuminations, camera’s differences and other ecological and physical changes. Thus, AMM (Active Appearance Model) is one of the good population solutions which it can be used as a features extraction technique by accurate modeling under different physical and environmental situations. In this research, an AAM based face recognition system is proposed. Then, three different data sets YALEB, FERET and CASIA V5 which have been utilized for the first time in the evaluation. The experimental results showed that the performance of AAM is very powerful with face recognition.

Hybrid intelligent system means a software system that utilizes a combination of different approaches and techniques from artificial intelligence subfields in order to optimize the target system. Field orient system FOS is a nonlinear device due to the saturation phenomenon, conventional FOS methods provide poor performance, and limited disturbance rejection capability and longer convergence time delay.to optimize the FOS. This paper describes a simple hybrid intelligent design of a “Fuzzy Inference system (FIS)” with PD (FIS-PD) intelligent that is suitable for real-time applications and uses novel output membership functions, which do not include overlap. This increases optimization of rate response convergence, allows for a significant reduction in computational problem, and lowers the execution time. Application of FIS-PD intelligent increases the quality factor of field orient system as results to optimize field oriented system FOS for saturated nonlinear drive in order to achieve high dynamic performance and wide operating range. The performance of the proposed optimization is validated via simulation and the simulation investigation has been carried out for the FOS in this paper. A relative comparison between the FOS and the proposed FIS-PD intelligent indicates that the proposed optimization method yields superior performance. Comparative tests with a conventional system are provided to confirm the effectiveness of the proposed technique.

Digital retinal images are more appropriate for automatic screening of diabetic retinopathy systems. Unfortunately, a significant percentage of these images are poor quality that hiders further analysis due to many factors (such as patient movement, inadequate or non-uniform illumination, acquisition angle and retinal pigmentation). The retinal images of poor quality need to be enhanced before the extraction of features and abnormalities. So, the segmentation of retinal image is essential for this purpose, the segmentation is employed to smooth and strengthen image by separating the background and damaged areas from the overall image thus resulting in retinal image enhancement and less processing time. In this paper, methods for segmenting colored retinal image are proposed to improve the quality of retinal image diagnosis. The methods generates two segmentation masks; i.e., background segmentation mask for extracting the background area and poor quality mask for removing the noisy areas from retinal image. The standard retinal image databases DIARETDB0, DIARETDB1, STARE, DRIVE and some images obtained from ophthalmologists have been used to test the validation of the proposed segmentation technique. Experimental results indicate the introduced methods are effective and can lead to high segmentation accuracy