Classification of imbalanced data is an important issue. Many algorithms have been developed for classification, such as Back Propagation (BP) neural networks, decision tree, Bayesian networks etc., and have been used repeatedly in many fields. These algorithms speak of the problem of imbalanced data, where there are situations that belong to more classes than others. Imbalanced data result in poor performance and bias to a class without other classes. In this paper, we proposed three techniques based on the Over-Sampling (O.S.) technique for processing imbalanced dataset and redistributing it and converting it into balanced dataset. These techniques are (Improved Synthetic Minority Over-Sampling Technique (Improved SMOTE),  Border

Free-Space Optical (FSO) can provide high-speed communications when the effect of turbulence is not serious. However, Space-Time-Block-Code (STBC) is a good candidate to mitigate this seriousness. This paper proposes a hybrid of an Optical Code Division Multiple Access (OCDMA) and STBC in FSO communication for last mile solutions, where access to remote areas is complicated. The main weakness effecting a FSO link is the atmospheric turbulence. The feasibility of employing STBC in OCDMA is to mitigate these effects. The current work evaluates the Bit-Error-Rate (BER) performance of OCDMA operating under the scintillation effect, where this effect can be described by the gamma-gamma model. The most obvious finding to emerge from the analysis

Free Space Optical (FSO) technology offers highly directional, high bandwidth communication channels. This technology can provide fiber-like data rate over short distances. In order to improve security associated with data transmission in FSO networks, a secure communication method based on chaotic technique is presented. In this paper, we have turned our focus on a specific class of piece wise linear one-dimensional chaotic maps. Simulation results indicate that this approach has the advantage of possessing excellent correlation property. In this paper we examine the security vulnerabilities of single FSO links and propose a solution to this problem by implementing the chaotic signal generator “reconfigurable tent map”. As synchronizat

In this paper, we introduce a DCT based steganographic method for gray scale images. The embedding approach is designed to reach efficient tradeoff among the three conflicting goals; maximizing the amount of hidden message, minimizing distortion between the cover image and stego-image,and maximizing the robustness of embedding. The main idea of the method is to create a safe embedding area in the middle and high frequency region of the DCT domain using a magnitude modulation technique. The magnitude modulation is applied using uniform quantization with magnitude Adder/Subtractor modules. The conducted test results indicated that the proposed method satisfy high capacity, high preservation of perceptual and statistical properties of the steg

In this study, dynamic encryption techniques are explored as an image cipher method to generate S-boxes similar to AES S-boxes with the help of a private key belonging to the user and enable images to be encrypted or decrypted using S-boxes. This study consists of two stages: the dynamic generation of the S-box method and the encryption-decryption method. S-boxes should have a non-linear structure, and for this reason, K/DSA (Knutt Durstenfeld Shuffle Algorithm), which is one of the pseudo-random techniques, is used to generate S-boxes dynamically. The biggest advantage of this approach is the production of the inverted S-box with the S-box. Compared to the methods in the literature, the need to store the S-box is eliminated. Also, the fabr

In this paper, we will present proposed enhance process of image compression by using RLE algorithm. This proposed yield to decrease the size of compressing image, but the original method used primarily for compressing a binary images [1].Which will yield increasing the size of an original image mostly when used for color images. The test of an enhanced algorithm is performed on sample consists of ten BMP 24-bit true color images, building an application by using visual basic 6.0 to show the size after and before compression process and computing the compression ratio for RLE and for the enhanced RLE algorithm.

In recent years, with the rapid development of the current classification system in digital content identification, automatic classification of images has become the most challenging task in the field of computer vision. As can be seen, vision is quite challenging for a system to automatically understand and analyze images, as compared to the vision of humans. Some research papers have been done to address the issue in the low-level current classification system, but the output was restricted only to basic image features. However, similarly, the approaches fail to accurately classify images. For the results expected in this field, such as computer vision, this study proposes a deep learning approach that utilizes a deep learning algorithm.