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
Robots have become an essential part of modern industries in welding departments to increase the accuracy and rate of production. The intelligent detection of welding line edges to start the weld in a proper position is very important. This work introduces a new approach using image processing to detect welding lines by tracking the edges of plates according to the required speed by three degrees of a freedom robotic arm. The two different algorithms achieved in the developed approach are the edge detection and top-hat transformation. An adaptive neuro-fuzzy inference system ANFIS was used to choose the best forward and inverse kinematics of the robot. MIG welding at the end-effector was applied as a tool in this system, and the wel
... Show More
(17)
(17)
The ring modulator described in part I of this paper is designed here for two operating wavelengths 1550nm and 1310nm. For each wavelength, three structures are designed corresponding to three values of polymer slot widths (40, 50 and 60nm). The performance of these modulators are simulated using COMSOL software (version 4.3b) and the results are discussed and compared with theoretical predictions. The performance of intensity modulation/direct detection short range and long rang optical communication systems incorporating the designed modulators is simulated for 40 and 100Gb/s data rates using Optisystem software (version 12). The results reveal that an average energy per bit as low as 0.05fJ can be obtained when the 1550nm modulator is d
... Show MoreThis paper presents comprehensive analysis and investigation for 1550nm and 1310nm ring optical modulators employing an electro-optic polymer infiltrated silicon-plasmonic hybrid phase shifter. The paper falls into two parts which introduce a theoretical modeling framework and performance assessment of these advanced modulators, respectively. In this part, analytical expressions are derived to characterize the coupling effect in the hybrid phase shifter, transmission function of the modulator, and modulator performance parameters. The results can be used as a guideline to design compact and wideband optical modulators using plasmonic technology
This research studies the effect of adding micro, nano and hybrid by ratio (1:1) of (Al2O3,TiO2) to epoxy resin on thermal conductivity before and after immersion in HCl acid for (14 day) with normality (0.3 N) at weight fraction (0.02, 0.04, 0.06, 0.08) and thickness (6mm). The results of thermal conductivity reveled that epoxy reinforced by (Al2O3) and mixture (TiO2+Al2O3) increases with increasing the weight fraction, but the thermal conductivity (k) a values for micro and Nano (TiO2) decrease with increasing the weight fraction of reinforced, while the immersion in acidic solution (HCl) that the (k) values after immersion more than the value in before immersion.
(1)
The mixed-spin ferrimagnetic Ising system consists of two-dimensional sublattices A and B with spin values and respectively .By used the mean-field approximation MFA of Ising model to find magnetism( ).In order to determined the best stabile magnetism , Gibbs free energy employ a variational method based on the Bogoliubov inequality .The ground-state (Phase diagram) structure of our system can easily be determined at , we find six phases with different spins values depend on the effect of a single-ion anisotropies .these lead to determined the second , first orders transition ,and the tricritical points as well as the compensation phenomenon .
<span lang="EN-US">The fundamental of a downlink massive multiple-input multiple-output (MIMO) energy- issue efficiency strategy is known as minimum mean squared error (MMSE) implementation degrades the performance of a downlink massive MIMO energy-efficiency scheme, so some improvements are adding for this precoding scheme to improve its workthat is called our proposal solution as a proposed improved MMSE precoder (PIMP). The energy efficiency (EE) study has also taken into mind drastically lowering radiated power while maintaining high throughput and minimizing interference issues. We further find the tradeoff between spectral efficiency (SE) and EE although they coincide at the beginning but later their interests become con
... Show More
(16)
(12)
(12)
(10)
(6)
To expedite the learning process, a group of algorithms known as parallel machine learning algorithmscan be executed simultaneously on several computers or processors. As data grows in both size andcomplexity, and as businesses seek efficient ways to mine that data for insights, algorithms like thesewill become increasingly crucial. Data parallelism, model parallelism, and hybrid techniques are justsome of the methods described in this article for speeding up machine learning algorithms. We alsocover the benefits and threats associated with parallel machine learning, such as data splitting,communication, and scalability. We compare how well various methods perform on a variety ofmachine learning tasks and datasets, and we talk abo
... Show More
(24)
(17)