Preferred Language
Articles
/
iRe5Po8BVTCNdQwCz2Wy
Lossy Image Compression Using Hybrid Deep Learning Autoencoder Based On kmean Clusteri
...Show More Authors

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

Publication Date
Sun Feb 25 2024
Journal Name
Baghdad Science Journal
Simplified Novel Approach for Accurate Employee Churn Categorization using MCDM, De-Pareto Principle Approach, and Machine Learning
...Show More Authors

Churning of employees from organizations is a serious problem. Turnover or churn of employees within an organization needs to be solved since it has negative impact on the organization. Manual detection of employee churn is quite difficult, so machine learning (ML) algorithms have been frequently used for employee churn detection as well as employee categorization according to turnover. Using Machine learning, only one study looks into the categorization of employees up to date.  A novel multi-criterion decision-making approach (MCDM) coupled with DE-PARETO principle has been proposed to categorize employees. This is referred to as SNEC scheme. An AHP-TOPSIS DE-PARETO PRINCIPLE model (AHPTOPDE) has been designed that uses 2-stage MCDM s

... Show More
View Publication Preview PDF
Scopus (4)
Crossref (3)
Scopus Crossref
Publication Date
Thu Jan 13 2011
Journal Name
Tikrit Journal Of Agricultural Sciences
ESTIMATION OF GENE ACTION AND GENETIC PARAMETERS FOR SOME CHARACTERS OF YIELD AND ITS COMPONENTS IN SUMMER SQUASH (Cucurbita pepo L.) BY USING MEAN GENERATION ANALYSIS
...Show More Authors

An experiment was carried out in the vegetables field of Horticulture Department / College of Agriculture / Baghdad University , for the three seasons : spring and Autumn of 2005 , and spring of 2007 , to study the type of gene action in some traits of yield and its components in summer squash crosses (4 x 3 = cross 1 , 3 x 7 = cross 2 , 3 x 4 = cross 3 , 3 x 5 = cross 4 , 5 x 1 = cross 5 , 5 x 2 = cross 6). The study followed generation mean analysis method which included to each cross (P1 , P2 , F1 , F2 , Bc1P1 , Bc1P2) , and those populations obtained by hybridization during the first and second seasons. Experimental comparison was performed in the second (Two crosses only) and third seasons , (four crosses) by using RCBD with three repl

... Show More
View Publication
Publication Date
Thu Dec 31 2020
Journal Name
Iraqi Journal Of Market Research And Consumer Protection
SYNTHESIS OF THE NEW NAPROXEN SELECTIVE ELECTRODE BASED ON IMPRINTED POLYMER USING DIFFERENT MONOMERS AND ITS DETERMINATION AT PHARMACEUTICAL PREPARATION: SYNTHESIS OF THE NEW NAPROXEN SELECTIVE ELECTRODE BASED ON IMPRINTED POLYMER USING DIFFERENT MONOMERS AND ITS DETERMINATION AT PHARMACEUTICAL PREPARATION
...Show More Authors

ABSTRACT

Naproxen(NPX) imprinted liquid electrodes of polymers are built using polymerization precipitation. The molecularly imprinted (MIP) and non imprinted (NIP) polymers were synthesized using NPX as a template. In the polymerization precipitation involved, styrene(STY) was used as monomer, N,N-methylenediacrylamide (N,N-MDAM) as a cross-linker and benzoyl peroxide (BPO) as an initiator. The molecularly imprinted membranes and the non-imprinted membranes were prepared using acetophenone(AOPH) and di octylphathalate(DOP)as plasticizers in PVC matrix. The slopes and detection limits of the liquid electrodes ranged from)-18.1,-17.72 (mV/decade and )4.0 x 10-

... Show More
View Publication Preview PDF
Publication Date
Sun Jun 01 2014
Journal Name
Baghdad Science Journal
Classification of fetal abnormalities based on CTG signal
...Show More Authors

The fetal heart rate (FHR) signal processing based on Artificial Neural Networks (ANN),Fuzzy Logic (FL) and frequency domain Discrete Wavelet Transform(DWT) were analysis in order to perform automatic analysis using personal computers. Cardiotocography (CTG) is a primary biophysical method of fetal monitoring. The assessment of the printed CTG traces was based on the visual analysis of patterns that describing the variability of fetal heart rate signal. Fetal heart rate data of pregnant women with pregnancy between 38 and 40 weeks of gestation were studied. The first stage in the system was to convert the cardiotocograghy (CTG) tracing in to digital series so that the system can be analyzed ,while the second stage ,the FHR time series was t

... Show More
View Publication Preview PDF
Crossref
Publication Date
Thu Mar 09 2017
Journal Name
Ibn Al-haitham Journal For Pure And Applied Sciences
Increase the Intelligibility of Multispectral Image Using Pan-Sharpening Techniques for Many Remotely Sensed Images
...Show More Authors

 Pan sharpening (fusion image) is the procedure of merging suitable information from two or more images into a single image. The image fusion techniques allow the combination of different information sources to improve the quality of image and increase its utility for a particular application. In this research, six pan-sharpening method have been implemented between the panchromatic and multispectral images, these methods include Ehlers, color normalize, Gram-Schmidt, local mean and variance matching, Daubechies of rank two and Symlets of rank four  wavelet transform. Two images captured by two different sensors such as landsat-8 and world view-2 have been adopted to achieve the fusion purpose. Different fidelity metric like MS

... Show More
View Publication Preview PDF
Publication Date
Tue Jan 01 2019
Journal Name
Energy Procedia
Calculation of Salinity and Soil Moisture indices in south of Iraq - Using Satellite Image Data
...Show More Authors

A band rationing method is applied to calculate the salinity index (SI) and Normalized Multi-Band Drought Index (NMDI) as pre-processing to take Agriculture decision in these areas is presented. To separate the land from other features that exist in the scene, the classical classification method (Maximum likelihood classification) is used by classified the study area to multi classes (Healthy vegetation (HV), Grasslands (GL), Water (W), Urban (U), Bare Soil (BS)). A Landsat 8 satellite image of an area in the south of Iraq are used, where the land cover is classified according to indicator ranges for each (SI) and (NMDI).

View Publication
Scopus (8)
Crossref (3)
Scopus Clarivate Crossref
Publication Date
Wed Jan 01 2020
Journal Name
Ieee Access
A Novel Approach to Improving Brain Image Classification Using Mutual Information-Accelerated Singular Value Decomposition
...Show More Authors

View Publication
Scopus (43)
Crossref (42)
Scopus Clarivate Crossref
Publication Date
Sun Aug 13 2017
Journal Name
Ibn Al-haitham Journal For Pure And Applied Sciences
Estimation Optimal Threshold Value for Image Edge Detection
...Show More Authors

      A new approach presented in this study to determine the optimal edge detection threshold value. This approach is base on extracting small homogenous blocks from unequal mean targets. Then, from these blocks we generate small image with known edges (edges represent the lines between the contacted blocks). So, these simulated edges can be assumed as true edges .The true simulated edges, compared with the detected edges in the small generated image is done by using different thresholding values. The comparison based on computing mean square errors between the simulated edge image and the produced edge image from edge detector methods. The mean square error computed for the total edge image (Er), for edge regio

... Show More
View Publication Preview PDF
Publication Date
Wed Aug 30 2023
Journal Name
Baghdad Science Journal
Post COVID-19 Effect on Medical Staff and Doctors' Productivity Analysed by Machine Learning
...Show More Authors

The COVID-19 pandemic has profoundly affected the healthcare sector and the productivity of medical staff and doctors. This study employs machine learning to analyze the post-COVID-19 impact on the productivity of medical staff and doctors across various specialties. A cross-sectional study was conducted on 960 participants from different specialties between June 1, 2022, and April 5, 2023. The study collected demographic data, including age, gender, and socioeconomic status, as well as information on participants' sleeping habits and any COVID-19 complications they experienced. The findings indicate a significant decline in the productivity of medical staff and doctors, with an average reduction of 23% during the post-COVID-19 period. T

... Show More
View Publication Preview PDF
Scopus (8)
Crossref (13)
Scopus Crossref
Publication Date
Thu Jul 20 2023
Journal Name
Ibn Al-haitham Journal For Pure And Applied Sciences
Applying Ensemble Classifier, K-Nearest Neighbor and Decision Tree for Predicting Oral Reading Rate Levels
...Show More Authors

For many years, reading rate as word correct per minute (WCPM) has been investigated by many researchers as an indicator of learners’ level of oral reading speed, accuracy, and comprehension. The aim of the study is to predict the levels of WCPM using three machine learning algorithms which are Ensemble Classifier (EC), Decision Tree (DT), and K- Nearest Neighbor (KNN). The data of this study were collected from 100 Kurdish EFL students in the 2nd-year, English language department, at the University of Duhok in 2021. The outcomes showed that the ensemble classifier (EC) obtained the highest accuracy of testing results with a value of 94%. Also, EC recorded the highest precision, recall, and F1 scores with values of 0.92 for

... Show More
View Publication Preview PDF
Crossref