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
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
(23)
(15)
In this paper, a design of the broadband thin metamaterial absorber (MMA) is presented. Compared with the previously reported metamaterial absorbers, the proposed structure provides a wide bandwidth with a compatible overall size. The designed absorber consists of a combination of octagon disk and split octagon resonator to provide a wide bandwidth over the Ku and K bands' frequency range. Cheap FR-4 material is chosen to be a substate of the proposed absorber with 1.6 thicknesses and 6.5×6.5 overall unit cell size. CST Studio Suite was used for the simulation of the proposed absorber. The proposed absorber provides a wide absorption bandwidth of 14.4 GHz over a frequency range of 12.8-27.5 GHz with more than %90 absorp
... Show More
(5)
Abstract:
One of the important things provided by fuzzy model is to identify the membership functions. In the fuzzy reliability applications with failure functions of the kind who cares that deals with positive variables .There are many types of membership functions studied by many researchers, including triangular membership function, trapezoidal membership function and bell-shaped membership function. In I research we used beta function. Based on this paper study classical method to obtain estimation fuzzy reliability function for both series and parallel systems.
This research is concerned to investigate the behavior of reinforced concrete (RC) deep beams strengthened with carbon fiber reinforced polymer (CFRP) strips. The experimental part of this research is carried out by testing seven RC deep beams having the same dimensions and steel reinforcement which have been divided into two groups according to the strengthening schemes. Group one was consisted of three deep beams strengthened with vertical U-wrapped CFRP strips. While, Group two was consisted of three deep beams strengthened with inclined CFRP strips oriented by 45o with the longitudinal axis of the beam. The remaining beam is kept unstrengthening as a reference beam. For each group, the variable considered
... Show MoreThe present work aims to study the effect of using an automatic thresholding technique to convert the features edges of the images to binary images in order to split the object from its background, where the features edges of the sampled images obtained from first-order edge detection operators (Roberts, Prewitt and Sobel) and second-order edge detection operators (Laplacian operators). The optimum automatic threshold are calculated using fast Otsu method. The study is applied on a personal image (Roben) and a satellite image to study the compatibility of this procedure with two different kinds of images. The obtained results are discussed.
In the latest years there has been a profound evolution in computer science and technology, which incorporated several fields. Under this evolution, Content Base Image Retrieval (CBIR) is among the image processing field. There are several image retrieval methods that can easily extract feature as a result of the image retrieval methods’ progresses. To the researchers, finding resourceful image retrieval devices has therefore become an extensive area of concern. Image retrieval technique refers to a system used to search and retrieve images from digital images’ huge database. In this paper, the author focuses on recommendation of a fresh method for retrieving image. For multi presentation of image in Convolutional Neural Network (CNN),
... Show More
(10)
(3)
This 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
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 More
(8)