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
Shallow foundations are usually used for structures with light to moderate loads where the soil underneath can carry them. In some cases, soil strength and/or other properties are not adequate and require improvement using one of the ground improvement techniques. Stone column is one of the common improvement techniques in which a column of stone is installed vertically in clayey soils. Stone columns are usually used to increase soil strength and to accelerate soil consolidation by acting as vertical drains. Many researches have been done to estimate the behavior of the improved soil. However, none of them considered the effect of stone column geometry on the behavior of the circular footing. In this research, finite ele
... Show MoreThis study utilized low-cost agricultural waste (molasses production waste powder) to extract copper ions from aqueous solutions. The present investigation explored a range of factors that influence the adsorption process, including temperature, pH, ionic strength, contact time, quantity of adsorbent, and particle size. Spectrophotometric analysis was used to determine the solution's absorbance both before and after the adsorption procedure. The Langmuir and Freundlich adsorption models were used to match the equilibrium data. The Freundlich model was determined to be the best isotherm model using the linear regression coefficient R2=0.9868. Thermodynamic parameters, including enthalpy, entropy, and Gibbs free energy, were calculate
... Show MoreVoice Activity Detection (VAD) is considered as an important pre-processing step in speech processing systems such as speech enhancement, speech recognition, gender and age identification. VAD helps in reducing the time required to process speech data and to improve final system accuracy by focusing the work on the voiced part of the speech. An automatic technique for VAD using Fuzzy-Neuro technique (FN-AVAD) is presented in this paper. The aim of this work is to alleviate the problem of choosing the best threshold value in traditional VAD methods and achieves automaticity by combining fuzzy clustering and machine learning techniques. Four features are extracted from each speech segment, which are short term energy, zero-crossing rate, auto
... Show MoreAn experimental study was performed to estimate the forced convection heat transfer performance and the pressure drop of a single layer graphene (GNPs) based DI-water nanofluid in a circular tube under a laminar flow and a uniform heat flux boundary conditions. The viscosity and thermal conductivity of nanofluid at weight concentrations of (0.1 to 1 wt%) were measured. The effects of the velocity of flow, heat flux and nanoparticle weight concentrations on the enhancement of the heat transfer are examined. The Nusselt number of the GNPs nanofluid was enhanced as the heat flux and the velocity of flow rate increased, and the maximum Nusselt number ratio (Nu nanofluid/ Nu base fluid) and thermal performance factor
... Show MoreWith the great development in the field of the Internet, the talk about the new media and its implications began, And its interactive services have made the future of media material sometimes participating in it and manufacturing it at other times,
the public is seeking information and choosing the appropriate ones, as well as exchanging messages with the sender after what the role of the receiver is just receiving information only.
This study aims to demonstrate the effects of using digital media in various forms and types to construct the value system of Iraqi society through the identification of the following aims:
Identify the most popular digital media for the Iraqi public in their daily lives on the Internet.
Identify
In this paper we investigate the automatic recognition of emotion in text. We propose a new method for emotion recognition based on the PPM (PPM is short for Prediction by Partial Matching) character-based text compression scheme in order to recognize Ekman’s six basic emotions (Anger, Disgust, Fear, Happiness, Sadness, Surprise). Experimental results with three datasets show that the new method is very effective when compared with traditional word-based text classification methods. We have also found that our method works best if the sizes of text in all classes used for training are similar, and that performance significantly improves with increased data.
Human posture estimation is a crucial topic in the computer vision field and has become a hotspot for research in many human behaviors related work. Human pose estimation can be understood as the human key point recognition and connection problem. The paper presents an optimized symmetric spatial transformation network designed to connect with single-person pose estimation network to propose high-quality human target frames from inaccurate human bounding boxes, and introduces parametric pose non-maximal suppression to eliminate redundant pose estimation, and applies an elimination rule to eliminate similar pose to obtain unique human pose estimation results. The exploratory outcomes demonstrate the way that the proposed technique can pre
... Show MoreThe study aims to identify the extent the academics in colleges of applied sciences are familiar with the themes of the national strategy of education 2040 in the Sultanate of Oman. The researchers used the descriptive approach, as well as they adopted a questionnaire with five dimensions as a tool for data collection, which was applied to (120) academics. The results showed that the academics of the applied colleges' familiarity with the National Strategy for Education 2040 in the Sultanate of Oman is average. The study also found that there were no statistically significant differences in the academics estimates of the extent of the Colleges of Applied Sciences academics’ familiarity with the themes of the National Education 2040 Str
... Show More