Neural cryptography deals with the problem of “key exchange” between two neural networks by using the mutual learning concept. The two networks exchange their outputs (in bits) and the key between two communicating parties ar eventually represented in the final learned weights, when the two networks are said to be synchronized. Security of neural synchronization is put at risk if an attacker is capable of synchronizing with any of the two parties during the training process.

Diabetes is one of the increasing chronic diseases, affecting millions of people around the earth. Diabetes diagnosis, its prediction, proper cure, and management are compulsory. Machine learning-based prediction techniques for diabetes data analysis can help in the early detection and prediction of the disease and its consequences such as hypo/hyperglycemia. In this paper, we explored the diabetes dataset collected from the medical records of one thousand Iraqi patients. We applied three classifiers, the multilayer perceptron, the KNN and the Random Forest. We involved two experiments: the first experiment used all 12 features of the dataset. The Random Forest outperforms others with 98.8% accuracy. The second experiment used only five att

Shadow detection and removal is an important task when dealing with color outdoor images. Shadows are generated by a local and relative absence of light. Shadows are, first of all, a local decrease in the amount of light that reaches a surface. Secondly, they are a local change in the amount of light rejected by a surface toward the observer. Most shadow detection and segmentation methods are based on image analysis. However, some factors will affect the detection result due to the complexity of the circumstances. In this paper a method of segmentation test present to detect shadows from an image and a function concept is used to remove the shadow from an image.

            Eye Detection is used in many applications like pattern recognition, biometric, surveillance system and many other systems. In this paper, a new method is presented to detect and extract the overall shape of one eye from image depending on two principles Helmholtz & Gestalt. According to the principle of perception by Helmholz, any observed geometric shape is perceptually "meaningful" if its repetition number is very small in image with random distribution. To achieve this goal, Gestalt Principle states that humans see things either through grouping its similar elements or recognize patterns. In general, according to Gestalt Principle, humans see things through genera

Water/oil emulsion is considered as the most refractory mixture to separate because of the interference of the two immiscible liquids, water and oil. This research presents a study of dewatering of water / kerosene emulsion using hydrocyclone. The effects of factors such as: feed flow rate (3, 5, 7, 9, and 11 L/min), inlet water concentration of the emulsion (5%, 7.5%, 10%, 12.5%, and 15% by volume), and split ratio (0.1, 0.3, 0.5, 0.7, and 0.9) on the separation efficiency and pressure drop were studied. Dimensional analysis using Pi theorem was applied for the first time to model the hydrocyclone based on the experimental data. It was shown that the maximum separation efficiency; at split ratio 0.1, was 94.3% at 10% co

Compressing the speech reduces the data storage requirements, leading to reducing the time of transmitting the digitized speech over long-haul links like internet. To obtain best performance in speech compression, wavelet transforms require filters that combine a number of desirable properties, such as orthogonality and symmetry.The MCT bases functions are derived from GHM bases function using 2D linear convolution .The fast computation algorithm methods introduced here added desirable features to the current transform. We further assess the performance of the MCT in speech compression application. This paper discusses the effect of using DWT and MCT (one and two dimension) on speech compression. DWT and MCT performances in terms of comp

In Automatic Speech Recognition (ASR) the non-linear data projection provided by a one hidden layer Multilayer Perceptron (MLP), trained to recognize phonemes, and has previous experiments to provide feature enhancement substantially increased ASR performance, especially in noise. Previous attempts to apply an analogous approach to speaker identification have not succeeded in improving performance, except by combining MLP processed features with other features. We present test results for the TIMIT database which show that the advantage of MLP preprocessing for open set speaker identification increases with the number of speakers used to train the MLP and that improved identification is obtained as this number increases beyond sixty.

In this paper, a subspace identification method for bilinear systems is used . Wherein a " three-block " and " four-block " subspace algorithms are used. In this algorithms the input signal to the system does not have to be white . Simulation of these algorithms shows that the " four-block " gives fast convergence and the dimensions of the matrices involved are significantly smaller so that the computational complexity is lower as a comparison with " three-block " algorithm .