Image compression plays an important role in reducing the size and storage of data while increasing the speed of its transmission through the Internet significantly. Image compression is an important research topic for several decades and recently, with the great successes achieved by deep learning in many areas of image processing, especially image compression, and its use is increasing Gradually in the field of image compression. The deep learning neural network has also achieved great success in the field of processing and compressing various images of different sizes. In this paper, we present a structure for image compression based on the use of a Convolutional AutoEncoder (CAE) for deep learning, inspired by the diversity of human eyes' observation of the different colors and features of images. We propose a multi-layer hybrid system for deep learning using the unsupervised CAE architecture and using the color clustering of the K-mean algorithm to compress images and determine their size and color intensity. The system is implemented using Kodak and Challenge on Learned Image Compression (CLIC) dataset for deep learning. Experimental results show that our proposed method is superior to the traditional compression methods of the autoencoder, and the proposed work has better performance in terms of performance speed and quality measures Peak Signal To Noise Ratio (PSNR) and Structural Similarity Index (SSIM) where the results achieved better performance and high efficiency With high compression bit rates and low Mean Squared Error (MSE) rate the results recorded the highest compression ratios that ranged between (0.7117 to 0.8707) for the Kodak dataset and (0.7191 to 0.9930) for CLIC dataset. The system achieved high accuracy and quality in comparison to the error coefficient, which was recorded (0.0126 to reach 0.0003) below, and this system is onsidered the most quality and accurate compared to the methods of deep learning compared to the deep learning methods of the autoencoder
The dimensions of bubbles were measured in a stirrer tank electrochemical reactor, where the analysis of the bubble size distribution has a substantial impact on the flow dynamics. The high-speed camera and image processing methods were used to obtain a reliable photo. The influence of varied air flow rates (0.3; 0.5; 1 l/min) on BSD was thoroughly investigated. Two types of distributors (cubic and circular) were examined, and the impact of various airflow rates on BSD was investigated in detail. The results showed that the bubbles for the two distributors were between 0.5 and 4.5 mm. For both distributors at each airflow, the Sauter mean diameter for the bubbles was calculated. According to the results, as the flow rate raised, the bubb
... Show More
In this paper, Mann-Kendall test was used to investigate the existence of possible deterministic and stochastic climatic trends in (Baghdad,Basrah,Mosul,Al-Qaim) stations. The statistical test was applied to annual monthly mean of temperatures for the period (19932009). The values of S-statistic were (62, 44, 52, 64) by comparing these values with the table of null probability values for S we get a probability of (0.002, 0.026, 0.010, 0.002) this result is less than α for the 95% confidence level (α = 0.05) indicating a significant result at this level of confidence. Concluded that an increasing trend in concentration is present at the 95% confidence level and the variance of the S-statistic is calculated and it is com
... Show More|
The quadrupole moment of 14B exotic nucleus has been calculated using configuration mixing shell model with limiting number of orbital's in the model space. The core- polarization effects, are included through a microscopic theory which considers a particle-hole excitations from the core and the model space orbits into the higher orbits with 6ħω excitations using M3Y interaction. The simple harmonic oscillator potential is used to generate the single particle wave functions. Large basis no-core shell model with (0+2)ћω truncation is used for 14B nucleus. The effective charges for the protons and neutrons were calculated su |
A new approach for baud time (or baud rate) estimation of a random binary signal is presented. This approach utilizes the spectrum of the signal after nonlinear processing in a way that the estimation error can be reduced by simply increasing the number of the processed samples instead of increasing the sampling rate. The spectrum of the new signal is shown to give an accurate estimate about the baud time when there is no apriory information or any restricting preassumptions. The performance of the estimator for random binary square waves perturbed by white Gaussian noise and ISI is evaluated and compared with that of the conventional estimator of the zero crossing detector.
Empirical equation has been presented to predict the optimum hydrodynamic
pressure gradient with optimum mud flow rate (one equation) of five Iraqi oil wells
to obtain the optimum carrying capacity of the drilling fluid ( optimum transport
cuttings from the hole to the surface through the annulus).
This equation is a function of mud flow rate, mud density and penetration
rate without using any charts or graphs.
The correlation coefficient accuracy is more than 0.9999.
The evolution in the field of Artificial Intelligent (AI) with its training algorithms make AI very important in different aspect of the life. The prediction problem of behavior of dynamical control system is one of the most important issue that the AI can be employed to solve it. In this paper, a Convolutional Multi-Spike Neural Network (CMSNN) is proposed as smart system to predict the response of nonlinear dynamical systems. The proposed structure mixed the advantages of Convolutional Neural Network (CNN) with Multi -Spike Neural Network (MSNN) to generate the smart structure. The CMSNN has the capability of training weights based on a proposed training algorithm. The simulation results demonstrated that the proposed
... Show More
(1)
In information security, fingerprint verification is one of the most common recent approaches for verifying human identity through a distinctive pattern. The verification process works by comparing a pair of fingerprint templates and identifying the similarity/matching among them. Several research studies have utilized different techniques for the matching process such as fuzzy vault and image filtering approaches. Yet, these approaches are still suffering from the imprecise articulation of the biometrics’ interesting patterns. The emergence of deep learning architectures such as the Convolutional Neural Network (CNN) has been extensively used for image processing and object detection tasks and showed an outstanding performance compare
... Show More
(2)
(1)
This article will introduce a new iteration method called the zenali iteration method for the approximation of fixed points. We show that our iteration process is faster than the current leading iterations like Mann, Ishikawa, oor, D- iterations, and *- iteration for new contraction mappings called quasi contraction mappings. And we proved that all these iterations (Mann, Ishikawa, oor, D- iterations and *- iteration) equivalent to approximate fixed points of quasi contraction. We support our analytic proof by a numerical example, data dependence result for contraction mappings type by employing zenali iteration also discussed.
(2)
In this paper ,the problem of point estimation for the two parameters of logistic distribution has been investigated using simulation technique. The rank sampling set estimator method which is one of the Non_Baysian procedure and Lindley approximation estimator method which is one of the Baysian method were used to estimate the parameters of logistic distribution. Comparing between these two mentioned methods by employing mean square error measure and mean absolute percentage error measure .At last simulation technique used to generate many number of samples sizes to compare between these methods.
(1)