ملخص البحث :

Steganography is the science of hiding information that involves all the techniques used to exchange the secret message with low distortion of the cover medium. Many different cover medium formats such as (image, audio, video, and text) can be used to hide the secret message. Image files are mostly used because of their frequency on the Internet. Some of the old techniques used schemes to hide information are: invisible ink, null ciphers, micro-codes, and pink-pricks. Modern Steganography has gained a lot of attention for the last two decades because of the rapid growth of communication technologies such as Internet and the need of a secure channel to transmit the important information. In this paper, a concept of image steganography is explained and a review of recent image steganography methods and its applications is presented.

ملخص البحث :

In this paper, the receivers of three-dimensional optical code division multiple access (3-D OCDMA) systems based on a 3-D perfect difference (3-D PD) code and a 3-D Diluted Perfect Difference/Multi-Diagonal (3-D DPD/MD) code are investigated. The main problem of using 3-D PD code in OCDMA system is the complexity of the receiver where the required number of the Fiber Brag gratings (FBGs) increases with the spectral code length. Also, the number of optical delay lines (ODLs) rises based on temporal code length. The 3-D DPD/MD code which was proposed by the author, to reduce the receiver complexity. The comparison results prove that the 3-D DPD/MD code has lower receiver complexity than the 3-D PD code. The required number of FBGs and ODLs of a 3-D DPD/MD code is constant with the code length because it depends on the basic code length not on the extended length. While it is proportional with the code length for a 3-D PD code. Hence, the 3-D DPD/MD code can reduce the receiver complexity to less than 25% of the 3-D PD system receiver according to the code length.

ملخص البحث :

In this paper, we conducted a comparison of a number of deep learning networks in detecting Covid-19 disease based on X-ray and CT-scan images. An eight different deep learning network types (ResNet50, Mobilenetv2, Densnet201, SqueezeNet, Efficientb0, Googlenet, VGG19, and Alexnet25) are investigated to detect the COVID-19 based on the X-ray and CT-scan images. A transfer-learning technique is adopted in the training phase for all networks with different datasets. The networks are trained and tested on 70% and 30% of the dataset, respectively. The confusion matrix is calculated in the testing phase and the evaluation metrics including F1 score, accuracy, precision, specificity and sensitivity are calculated from the confusion matrix. The comparison results demonstrate that the classification accuracy when using X-ray dataset is better than that of using CT-scan datasets. Moreover, the Mobilenetv2 delivered the greatest results for different datasets in which the accuracy is greater than 99% for X-ray images and the accuracy is less than 80% for CT-scan images . Our conclusion is that the using of Mobilenetv2 network with the X-ray images is more suitable than the others.