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
(32)
(30)
This study proposes a hybrid predictive maintenance framework that integrates the Kolmogorov-Arnold Network (KAN) with Short-Time Fourier Transform (STFT) for intelligent fault diagnosis in industrial rotating machinery. The method is designed to address challenges posed by non-linear and non-stationary vibration signals under varying operational conditions. Experimental validation using the FALEX multispecimen test bench demonstrated a high classification accuracy of 97.5%, outperforming traditional models such as SVM, Random Forest, and XGBoost. The approach maintained robust performance across dynamic load scenarios and noisy environments, with precision and recall exceeding 95%. Key contributions include a hardware-accelerated K
... Show More
(12)
(11)
The study of images in the cognitive field receives considerable attention by researchers, whether in the field of media and public relations or in other humanities. Due to the great importance in shaping trends of public opinion, especially trends that individuals and the behaviors of people, institutions or ideas are determined by forming images that they hold in their minds towards these persons or institutions. Modern enterprises have realized, whether they are governmental ministries and official departments or non-governmental organizations as civil society organizations, the importance of studying the dominant image in the minds of the masses and make decisions and draw plans to configure this image as these institutions wishes.&n
... Show More
الغرض من هذا العمل هو دراسة الفضاء الإسقاطي ثلاثي الأبعاد PG (3، P) حيث p = 4 باستخدام المعادلات الجبرية وجدنا النقاط والخطوط والمستويات وفي هذا الفضاء نبني (k، ℓ) -span وهي مجموعة من خطوط k لا يتقاطع اثنان منها. نثبت أن الحد الأقصى للكمال (k، ℓ) -span في PG (3،4) هو (17، ℓ) -span ، وهو ما يساوي جميع نقاط المساحة التي تسمى السبريد.
(1)
Fractal geometry is receiving increase attention as a quantitative and qualitative model for natural phenomena description, which can establish an active classification technique when applied on satellite images. In this paper, a satellite image is used which was taken by Quick Bird that contains different visible classes. After pre-processing, this image passes through two stages: segmentation and classification. The segmentation carried out by hybrid two methods used to produce effective results; the two methods are Quadtree method that operated inside Horizontal-Vertical method. The hybrid method is segmented the image into two rectangular blocks, either horizontally or vertically depending on spectral uniformity crit
... Show MoreThe efficiency of the Honeywords approach has been proven to be a significant tool for boosting password security. The suggested system utilizes the Meerkat Clan Algorithm (MCA) in conjunction with WordNet to produce honeywords, thereby enhancing the level of password security. The technique of generating honeywords involves data sources from WordNet, which contributes to the improvement of authenticity and diversity in the honeywords. The method encompasses a series of consecutive stages, which include the tokenization of passwords, the formation of alphabet tokens using the Meerkat Clan Algorithm (MCA), the handling of digit tokens, the creation of unique character tokens, and the consolidation of honeywords. The optimization of t
... Show More
B3LYP/6-31G, DFT method was applied to hypothetical study the design of six carbon nanotube materials based on [8]circulene, through the use of cyclic polymerization of two and three molecules of [8]circulene. Optimized structures of [8]circulene have saddle-shaped. Design of six carbon nanotubes reactions were done by thermodynamically calculating (Δ S, Δ G and Δ H) and the stability of these hypothetical nanotubes depending on the value of HOMO energy level. Nanotubes obtained have the most efficient gap energy, making them potentially useful for solar cell applications.
Far infrared photoconductive detectors based on multi-wall carbon nanotubes (MWCNTs) were fabricated and their characteristics were tested. MWCNTs films deposited on porous silicon (PSi) nanosurface by dip and drop coating techniques. Two types of deposited methods were used; dip coating sand drop –by-drop methods. As well as two types of detector were fabricated one with aluminum mask and the other without, and their figures of merits were studied. The detectors were illuminated by 2.2 and 2.5 Watt from CO2 of 10.6 m and tested. The surface morphology for the films is studied using AFM and SEM micrographs. The films show homogeneous distributed for CNTs on the PSi layer. The root mean square (r.m.s.) of the films surface roughness in
... Show MorePhotonic Crystal Fiber Interferometers (PCFIs) are greatly used
for sensing applications. This work presents the fabrication and
characterization of a relative humidity sensor based on Mach-
Zehnder Interferometer (MZI), which operates in reflection mode.
The humidity sensor operation based on the adsorption and
desorption of water vapour at the silica-air interface within the PCF.
The fabrication of this sensor is simple, it only includes splicing and
cleaving the PCF with SMF.PCF (LMA-10) with a certain length
spliced to SMF (Corning-28).
The spectrum of PCFI exhibits good sensitivity to humidity
variations. The PCFI response is observed for a range of humidity
values from (27% RH to 85% RH), the positi
(1)