Preferred Language
Articles
/
ijs-360
Effect of Successive Convolution Layers to Detect Gender
...Show More Authors

Image classification can be defined as one of the most important tasks in the area of machine learning. Recently, deep neural networks, especially deep convolution networks, have participated greatly in end-to-end learning which reduce need for human designed features in the image recognition like Convolution Neural Network. It is offers the computation models which are made up of several processing layers for learning data representations with several abstraction levels. In this work, a pre-trained deep CNN is utilized according to some parameters like filter size, no of convolution, pooling, fully connected and type of activation function which includes 300 images for training and predict 100 image gender using probability measures. Results in Classification and precision accuracy equal to 0.68 and 0.3225 respectively.

View Publication Preview PDF
Quick Preview PDF
Publication Date
Wed Dec 01 2021
Journal Name
Iraqi Journal Of Physics
Effect of Deposit Au thin Layer Between Layers of Perovskite Solar Cell on Cell's Performance
...Show More Authors

The present work aims to fabricate n-i-p forward perovskite solar cell (PSC) withئ structure (FTO/ compact TiO2/ compact TiO2/ MAPbI3 Perovskite/ hole transport layer/ Au). P3HT, CuI and Spiro-OMeTAD were used as hole transport layers. A nano film of 25 nm gold layer was deposited once between the electron transport layer and the perovskite layer, then between the hole transport layer and the perovskite layer. The performance of the forward-perovskite solar cell was studied. Also, the role of each electron transport layer and the hole transport layer in the perovskite solar cell was presented. The structural, morphological and electrical properties were studied with X-ray diffractometer, field emission s

... Show More
View Publication Preview PDF
Crossref (2)
Crossref
Publication Date
Tue Jul 01 2014
Journal Name
Journal Of The Faculty Of Medicine Baghdad
Effect of Age and Gender on QRS Complex Amplitude in Healthy Adults.
...Show More Authors

Background: There is controversy about the upper normal value of QRS complex amplitude in adult population under the age of 40 years. Most of the left ventricular hypertrophy voltage criteria were designed or tested for people above 40 years. In addition to age, QRS amplitude is also affected by gender and racial factors.

Objectives: To evaluate the impact of age on QRS amplitude in each gender separately in healthy adults.

Patients and Methods: Electrocardiograms from 563 overtly healthy adults (386 male and 177 female) aged 18-40 years were obtained using Cardios PC based ECG machine, 12-lead ECGs were recorded and QRS amplitude was measured as the sum of (SV1+RV5) and

... Show More
View Publication Preview PDF
Crossref
Publication Date
Fri Dec 01 2023
Journal Name
Baghdad Science Journal
Building a Statistical Model to Detect Foreground Objects and using it in Video Steganography
...Show More Authors

Video steganography has become a popular option for protecting secret data from hacking attempts and common attacks on the internet. However, when the whole video frame(s) are used to embed secret data, this may lead to visual distortion. This work is an attempt to hide sensitive secret image inside the moving objects in a video based on separating the object from the background of the frame, selecting and arranging them according to object's size for embedding secret image. The XOR technique is used with reverse bits between the secret image bits and the detected moving object bits for embedding. The proposed method provides more security and imperceptibility as the moving objects are used for embedding, so it is difficult to notice the

... Show More
View Publication Preview PDF
Scopus Crossref
Publication Date
Sat Oct 01 2022
Journal Name
Baghdad Science Journal
Offline Signature Biometric Verification with Length Normalization using Convolution Neural Network
...Show More Authors

Offline handwritten signature is a type of behavioral biometric-based on an image. Its problem is the accuracy of the verification because once an individual signs, he/she seldom signs the same signature. This is referred to as intra-user variability. This research aims to improve the recognition accuracy of the offline signature. The proposed method is presented by using both signature length normalization and histogram orientation gradient (HOG) for the reason of accuracy improving. In terms of verification, a deep-learning technique using a convolution neural network (CNN) is exploited for building the reference model for a future prediction. Experiments are conducted by utilizing 4,000 genuine as well as 2,000 skilled forged signatu

... Show More
View Publication Preview PDF
Scopus (2)
Crossref (1)
Scopus Clarivate Crossref
Publication Date
Fri Jul 24 2020
Journal Name
Indian Journal Of Forensic Medicine & Toxicology
Using Bioluminescence Assay to Detect Snps Cause Drug Resistant of Mycobacterium Tuberculosis in Iraq
...Show More Authors

In this search, a new bioluminescent technique was proved for pyrophosphate which was employed to single- nucleotide polymorphism (SNP) diagnosis using one-base extension reaction. Four Mycobacterium tuberculosis genes were chosen (Rpob, InhA, KatG, GyrA) genes. Fifty-four specimens were used in this study fifty-three proved as drug-resistant specimens by The Iraqi Institute of Chest and Respiratory Diseases in Baghdad., also one specimen was used as a negative control. The procedure of this assay was as follows. A specific primer within each aliquot owning a short 3-OH end of the base of the target gene was hybridized to the single-stranded DNA template. Then, (exo-) Klenow DNA polymerase and one of either ?-thio-dATP, dTTP, dGTP, or dCTP

... Show More
Crossref
Publication Date
Sun Apr 03 2011
Journal Name
Journal Of The Faculty Of Medicine Baghdad
Determination of the layers of temporal fascia.
...Show More Authors

Background: The temporal fascia has not been studied properly yet.

View Publication Preview PDF
Crossref
Publication Date
Wed Feb 06 2013
Journal Name
Eng. & Tech. Journal
A proposal to detect computer worms (malicious codes) using data mining classification algorithms
...Show More Authors

Malicious software (malware) performs a malicious function that compromising a computer system’s security. Many methods have been developed to improve the security of the computer system resources, among them the use of firewall, encryption, and Intrusion Detection System (IDS). IDS can detect newly unrecognized attack attempt and raising an early alarm to inform the system about this suspicious intrusion attempt. This paper proposed a hybrid IDS for detection intrusion, especially malware, with considering network packet and host features. The hybrid IDS designed using Data Mining (DM) classification methods that for its ability to detect new, previously unseen intrusions accurately and automatically. It uses both anomaly and misuse dete

... Show More
Publication Date
Sat Sep 30 2023
Journal Name
Journal Of Accounting And Financial Studies ( Jafs )
Auditing the comprehensive electronic banking system to detect operational business risks (applied research)
...Show More Authors

Abstract:

                In light of the development in the banking environment and the increasing reliance on electronic systems in providing banking services and due to the intense competition witnessed by the banking sector, the need has emerged to apply the comprehensive electronic banking system, which works on the Internet in providing new and diverse banking services regardless of time and place by linking all branches to one central database, and despite the advantages achieved from the application of the comprehensive system, there is a set of risks that accompany the use of that system, What requires the auditors to develop the audit method in line with the size of the development in the

... Show More
View Publication Preview PDF
Publication Date
Thu Mar 02 2023
Journal Name
Applied Sciences
Machine Learning Techniques to Detect a DDoS Attack in SDN: A Systematic Review
...Show More Authors

The recent advancements in security approaches have significantly increased the ability to identify and mitigate any type of threat or attack in any network infrastructure, such as a software-defined network (SDN), and protect the internet security architecture against a variety of threats or attacks. Machine learning (ML) and deep learning (DL) are among the most popular techniques for preventing distributed denial-of-service (DDoS) attacks on any kind of network. The objective of this systematic review is to identify, evaluate, and discuss new efforts on ML/DL-based DDoS attack detection strategies in SDN networks. To reach our objective, we conducted a systematic review in which we looked for publications that used ML/DL approach

... Show More
View Publication Preview PDF
Scopus (49)
Crossref (47)
Scopus Clarivate Crossref
Publication Date
Mon Feb 01 2021
Journal Name
Engenharia Agrícola
HYPERSPECTRAL SPECTROSCOPY TO DETECT DIFFERENT RESPONSES OF TWO SOYBEAN (GLYCINE MAX) CULTIVARS TO CHARCOAL ROT (MACROPHOMINA PHASEOLINA) TOXIN
...Show More Authors

View Publication
Scopus (1)
Crossref (1)
Scopus Clarivate Crossref