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
This paper presents a nonlinear finite element modeling and analysis of steel fiber reinforced concrete (SFRC) deep beams with and without openings in web subjected to two- point loading. In this study, the beams were modeled using ANSYS nonlinear finite element
software. The percentage of steel fiber was varied from 0 to 1.0%.The influence of fiber content in the concrete deep beams has been studied by measuring the deflection of the deep beams at mid- span and marking the cracking patterns, compute the failure loads for each deep beam, and also study the shearing and first principal stresses for the deep beams with and without openings and with different steel fiber ratios. The above study indicates that the location of openings an
(5)
Cyber-attacks keep growing. Because of that, we need stronger ways to protect pictures. This paper talks about DGEN, a Dynamic Generative Encryption Network. It mixes Generative Adversarial Networks with a key system that can change with context. The method may potentially mean it can adjust itself when new threats appear, instead of a fixed lock like AES. It tries to block brute‑force, statistical tricks, or quantum attacks. The design adds randomness, uses learning, and makes keys that depend on each image. That should give very good security, some flexibility, and keep compute cost low. Tests still ran on several public image sets. Results show DGEN beats AES, chaos tricks, and other GAN ideas. Entropy reached 7.99 bits per pix
... Show More
Reinforced concrete (RC) slabs strengthened with carbon fibre reinforced polymer (CFRP) and subjected to flexural actions may experience many types of failure, including FRP debonding, FRP rupture and concrete crushing. Of these different types of failure modes, FRP debonding stands out as the most predominant type of failure because of its dependence on the relatively weak bond interface between the soffit of the RC member and the FRP sheet attached to it. Many anchorage systems have been developed to enhance the performance of strengthened systems, one of which is the hybrid anchor, which combines the effects of patch anchors and spike anchors. Hybrid anchors have shown significant enhancement when used with RC members subjected to shear
... Show More
(20)
—Medical images have recently played a significant role in the diagnosis and detection of various diseases. Medical imaging can provide a means of direct visualization to observe through the human body and notice the small anatomical change and biological processes associated by different biological and physical parameters. To achieve a more accurate and reliable diagnosis, nowadays, varieties of computer aided detection (CAD) and computer-aided diagnosis (CADx) approaches have been established to help interpretation of the medical images. The CAD has become among the many major research subjects in diagnostic radiology and medical imaging. In this work we study the improvement in accuracy of detection of CAD system when comb
... Show More
(1)
Objectives: Recently, there have been important advances in the clinical application of targeted hybrid near-infrared (NIR) fluorescent-radioactive tracers. ICG-99mTc-nanocolloid, for example, is already being used by some centres for sentinel lymph node biopsy in head and neck cancer. The radioactive component allows imaging at depths which would not be possible with NIR alone and, once exposed, the NIR fluorescence reporter can be imaged at very high resolution. Gamma detection is currently carried out with a separate hand-held gamma camera or with a non-imaging probe. Visualisation of NIR fluorescence during surgery requires a dedicated NIR camera, several of which are available commercially. We describe a novel hand-held hybrid NIR-gamm
... Show More
This paper proposes a hybrid speech enhancement estimator that integrates the Perceptually-motivated Karhunen–Loève Transform (PKLT) with the Dual-Masking Harmonic-based (DMH) algorithm in a unified framework termed PKDMH. The main novelty lies in combining perceptual subspace projection with harmonic-residual suppression, enabling the system to jointly remove noise while preserving speech-relevant spectral cues. PKLT first performs perceptual subspace projection and suppresses inaudible components, after which DMH eliminates remaining broadband and harmonic residuals. The proposed PKDMH system was evaluated using the TIMIT dataset contaminated with five noise types: White, Pink, F16, Airport, and Car noise—across five SNR leve
... Show More
(1)
(27)
(20)
