Lecturer

An Ensemble DCNNs-Based Regression Model for Automatic Facial Beauty Prediction and Analyzation

Traitement du Signal (Issue: 1) (Volume: 40)

One of the most effective social aspects of the human face is its attractiveness. Automatic facial beauty prediction (FBP) is an emerging research area that has gained much interest recently. However, identifying the significant facial traits and attributes that can contribute to the process of beauty attractiveness estimation is one of the main challenges in this research area. Furthermore, learning the beauty pattern from a relatively small, imbalanced dataset is another concern that needs to be addressed. This research proposes an ensemblebased regression model that integrates judgments made by three various DCNNs, each with a different structure representation. The proposed method efficiently predicts the beauty score by leveraging the strengths of each network as a complementary data source, and it draws attention to the most important beauty-related face features through the Gradientweighted Class Activation Mapping (Grad-CAM). The findings are promising, demonstrating the efficiency of fusing the decision of multiple predictors of the proposed ensemble DCNNs regression models that is significantly consistent with the ground truth of the employed datasets (SCUT-FBP, SCUT-FBP5500, and ME Beauty). Moreover, it can assist in comprehending the relationship between facial characteristics and the impression of attractiveness.

Smart Healthcare for ECG Telemonitoring System

Journal of Soft Computing and Data Mining (Issue: 2) (Volume: 2)

Cardiovascular disorders are one of the major causes of sudden death among older and middle-aged people. Over the past two decades, health monitoring services have evolved quickly and had the ability to change the way health care is currently provided. However, the most challenging aspect of the mobile and wearable sensor-based human activity recognition pipeline is the extraction of the related features. Feature extraction decreases both computational complexity and time. Deep learning techniques are used for automatic feature learning in a variety of fields, including health, image classification, and, most recently, for the extraction and classification of simple and complex human activity recognition in smart health care. This paper presents a review on a recent state of the art in the area of electrocardiogram (ECG) smart health monitoring systems based on the Internet of things with the machine and deep learning techniques. Moreover, the paper provided possible lines of research and challenges that can help researchers in advancing the state of art in future work.

Facial beauty prediction and analysis based on deep convolutional neural network: a review

Journal of Soft Computing and Data Mining (Issue: 1) (Volume: 1)

Facial attractiveness or facial beauty prediction (FBP) is a current study that has several potential usages. It is a key difficulty area in the computer vision domain because of the few public databases related to FBP and its experimental trials on the minor-scale database. Moreover, the evaluation of facial beauty is personalized in nature, with people having personalized favor of beauty. Deep learning techniques have displayed a significant ability in terms of analysis and feature representation. The previous studies focussed on scattered portions of facial beauty with fewer comparisons between diverse techniques. Thus, this article reviewed the recent research on computer prediction and analysis of face beauty based on deep convolution neural network DCNN. Furthermore, the provided possible lines of research and challenges in this article can help researchers in advancing the state–of-art in future work.

Skin lesion classification based on deep convolutional neural networks architectures

Journal of Applied Science and Technology Trends (Issue: 1) (Volume: 2)

Skin cancer is among the primary cancer types that manifest due to various dermatological disorders, which may be further classified into several types based on morphological features, color, structure, and texture. The mortality rate of patients who have skin cancer is contingent on preliminary and rapid detection and diagnosis of malignant skin cancer cells. Limitations in current dermoscopic images, including shadow, artifact, and noise, affect image quality, which may hamper detection effort. Attempts to overcome these challenges have been made by analyzing the images using deep learning neural networks to perform skin cancer detection. In this paper, the authors review the state-of-the-art in authoritative deep learning concepts pertinent to skin cancer detection and classification.

A Review on Region of Interest Segmentation Based on Clustering Techniques for Breast Cancer Ultrasound Images

JOURNAL OF APPLIED SCIENCE AND TECHNOLOGY TRENDS (Issue: 3) (Volume: 1)

The most prevalent cancer amongst women is woman breast cancer. Ultrasound imaging is a widely employed method for identifying and diagnosing breast abnormalities. Computer-aided diagnosis technologies have lately been developed with ultrasound images to help radiologists enhance the accuracy of the diagnosis. This paper presents several ultrasound image segmentation techniques, mainly focus on eight clustering methods over the last 10 years, and it shows the advantages and disadvantages of these approaches. Breast ultrasound image segmentation is, therefore, still an accessible and challenging issue due to numerous ultrasound artifacts introduced in the imaging process, including high speckle noise, poor contrast, blurry edges, weak signal-to-noise ratio, and intensity inhomogeneity.

Image Steganography Based on Swarm Intelligence Algorithms: A Survey

Test Engineering & Mangement (Issue: May-June 2020) (Volume: 83)

Information security and confidentiality are the prime concern of any type of communication. The techniques that utilizing inconspicuous digital media such as text, audio, video and image for hiding confidential data in it are collectively called Steganography. The key challenge of steganographic system design is to maintain a fair trade-off between, security, robustness, higher bit embedding rate and imperceptibility. Thus, with the massive progress in digital technology, to transmit secret messages through the internet effective steganography algorithms are required. However, the object which has been used to hide secret messages within may be exposed by compression or any type of noise which leads to extract secret message incorrectly. Therefore, utilizing the non-traditional basics for information security is required, such as swarm intelligence algorithms which are focused as a new aspect to achieve better security. In this paper, a survey of recent swarm intelligence algorithms based on steganography is covered. The objective function for swarm intelligence algorithms is realized in a way that the quality and robustness of the object that has been used for hiding messages are acceptable. With a particular emphasis on the main purpose and the objective of the proposed method based on the particular swarm intelligence algorithm has been reviewed. To present a more secure, efficient steganography algorithm based on swarm intelligence algorithms for future work, this will be helpful.

Hiding Image by Using Contourlet Transform

Test Engineering and Management (Issue: May - June 2020) (Volume: 83)

The goal of the paper is to provide a practical conceptual framework based on hiding of watermarks embedded within coefficients image disintegrated by contourlet transform, that is characterized by extra sustenance for the potential and actual security of the hiding methods, and strengthen distribution techniques of watermarking inside the cover image; thus this can be done through achieving a kind of merge between those techniques and others techniques of image processing. A case study approach was used to allow the algorithms of the recommended system (non-blind) through concealing the watermarking which is resulted in the possibility of altering the watermarking dimensions with the fixed cover measurements and reciprocally. Another important practical implication is that the quartet tried to divide the techniques into four sections before it has been embedded inside the cover-image then after they have been split up, they distribute them among the fragments of the watermark within the cover-image regarding the quartet try the method. The techniques of using the three suggested algorithms by employing the watermarks cover image of various dimensions displayed that, the correlation factor ratio preceding and succeeding the process of hiding of the cover-image has been exceeded 0.99%. The most striking outcome to emerge from the data is that the result of this research which is in the watermark measured before and after the process depending on the PSNR, SNR, MSE, NC.

A Comprehensive Review of Dimensionality Reduction Techniques for Feature Selection and Feature Extraction

Journal of Applied Science and Technology Trends (Issue: 2) (Volume: 1)

Abstract Due to sharp increases in data dimensions, working on every data mining or machine learning (ML) task requires more efficient techniques to get the desired results. Therefore, in recent years, researchers have proposed and developed many methods and techniques to reduce the high dimensions of data and to attain the required accuracy. To ameliorate the accuracy of learning features as well as to decrease the training time dimensionality reduction is used as a pre-processing step, which can eliminate irrelevant data, noise, and redundant features. Dimensionality reduction (DR) has been performed based on two main methods, which are feature selection (FS) and feature extraction (FE). FS is considered an important method because data is generated continuously at an ever-increasing rate; some serious dimensionality problems can be reduced with this method, such as decreasing redundancy effectively, eliminating irrelevant data, and ameliorating result comprehensibility. Moreover, FE transacts with the problem of finding the most distinctive, informative, and decreased set of features to ameliorate the efficiency of both the processing and storage of data. This paper offers a comprehensive approach to FS and FE in the scope of DR. Moreover, the details of each paper, such as used algorithms/approaches, datasets, classifiers, and achieved results are comprehensively analyzed and summarized. Besides, a systematic discussion of all of the reviewed methods to highlight authors' trends, determining the method(s) has been done, which significantly reduced computational time, and selecting the most accurate classifiers. As a result, the different types of both methods have been discussed and analyzed the findings.

A SURVEY OF ULTRASONOGRAPHY BREAST CANCER IMAGE SEGMENTATION TECHNIQUES

Academic Journal of Nawroz University (AJNU) (Issue: 1) (Volume: 9)

ABSTRACT The most common cause of death among women globally is breast cancer. One of the key strategies to reduce mortality associated with breast cancer is to develop effective early detection techniques. The segmentation of breast ultrasound (BUS) image in Computer-Aided Diagnosis (CAD) systems is critical and challenging. Image segmentation aims to represent the image in a simplified and more meaningful way while retaining crucial features for easier analysis. However, in the field of image processing, image segmentation is a tough task particularly in ultrasound (US) images due to challenges associated with their nature. This paper presents a survey on several techniques of ultrasonography images segmentation including threshold based, region based, watershed, active contour and learning based techniques, their merits, and demerits. This can provide significant insights for CAD developers or researchers to advance this field.

2D Facial Images Attractiveness Assessment Based on Transfer Learning of Deep Convolutional Neural Networks

Iraq, Zakho, Iraq As Presenter

—While beauty is subjective, it is not easy to quantify. Assessing facial beauty based on a computer perspective is an emerging research area with various applications. Different trainable models have been proposed to identify the attractiveness of facial beauty utilizing different types of features, machine learning techniques and lately, convolutional neural networks (CNNs) have proven their efficiency in image classification. The main objective of recent previous work is to enhance the performance of the existing trainable methods and make them suitable for beauty attractiveness identification. In this study, the accuracy and effectiveness of four affective pre-trained CNNs models (AlexNet, GoogleNet, ResNet-50, and VGG16) in assessing the attractiveness of human facial images using the CelebA dataset have been explored, evaluated, and analyzed. The results demonstrate that GoogleNet surpassed the investigated pretrained networks with a performance accuracy of 82.8%.

FIAC-Net: Facial Image Attractiveness Classification Based on Light Deep Convolutional Neural Network

India, India As Presenter

2022 Second International Conference on Computer Science, Engineering and Applications (ICCSEA)

NTICT2020

Iraq, Baghdad,Iraq As Guest

The conference was held virtually at Zoom plateform

2019 International Conference on Advanced Science and Engineering (ICOASE)

Iraq, Zakho - Duhok, Iraq, Iraq As Presenter

Participate as an author

Image compression analysis using multistage vector quantization based on discrete wavelet transform

India, New Delhi, India As Presenter

Abstract: A fundamental goal of digital image compression is to reduce the bit rate for transmission or data storage while maintaining an acceptable fidelity or image quality. In this study a proposed coding (compression) scheme for grey scale image by combining discrete wavelet transform (DWT), multistage vector quantization (MSVQ) and Huffman coding is presented. These combinations are utilized to take the advantages provided by all of them to get high compression ratio with acceptable recovered image quality in term of Peak Signal to Noise Ratio (PSNR) instead of using each method separately. First, the discrete wavelet transform is performed on the original image using bi-orthogonal 9/7 filter (bior4.4) resulting in number of sub-bands according to the decomposition level that can be one, two or three in the proposed scheme. Huffman coding applied on the approximation sub-band, and on the indices of the last level detail sub-bands that are vector quantized by two stages using LBG algorithm which forms the basis of most vector quantizer designs, other detail sub-bands set to zero if the decomposition level is greater than one to increase the compression ratio.

Introduction to the Micro-Controllers and Arduino

Wasit. Iraq As Guest

held online at FCC platform

Online Platform for Academic Teaching and Learning in Iraq and Iran( OPATEL)

Duhok, Iraq As Guest

Online Platform for Academic Teaching and Learning in Iraq and Iran( OPATEL)

تحضير وتقييم التقاريير و السمنارات الطلابية

Duhok Technical Institute (DTI) As Guest

تحضير وتقييم التقاريير و السمنارات الطلابية للفبوف الدكتور صديق يوسف امين

انجازات البحوث الجامعية و نشرها في المجلات العلمية المعتمدة

Duhok Technical Institute (DTI) As Guest

انجازات البحوث الجامعية و نشرها في المجلات العلمية المعتمدة اابروف الدكتور صديق يوسف امين

E_waste

IT, Hall3 As Presenter

Bitcoin

IT, Hall3 As Presenter

Prprogramming Languages

IT, Hall3 As Presenter

Introduction to swarm intelligence

IT, DTI/Hall3 As Attend

Global Optimization Overview

IT, DTI/Hall3 As Attend

FPGAS: General Overview

IT, DTI/Hall3 As Attend

Effect of breed and iron supplementation on plasma copper suits of lamps

تحليلات مرضية, DTI/Hall3 As Attend

Software defined networking

IT, DTI/Hall3 As Attend

Virtual Reality

IT, DTI/Hall3 As Attend

Cognitive Technology

IT, DTI/Hall3 As Attend

Anemia and cobalt deficiency

تحليلات مرضية, DTI/Hall3 As Attend