About Journal

The Al-Rafidain Journal of Computer Sciences and Mathematics (CSMJ) is an international one which publishes written researches articles in English language in the areas of both computer sciences and mathematics. Contribution is open for researchers of all nationalities. One volume is published each year, and each volume consists of two issues ( June and December).
Read More ...

Deep Learning for Retinal Disease Detection Surveys

attallh salih; Manar Y. Kashmoola

AL-Rafidain Journal of Computer Sciences and Mathematics, 2022, Volume 16, Issue 2, Pages 1-9
DOI: 10.33899/csmj.2022.176583

 Retinal image analysis is crucial for The classification of retinal diseases such as “Age Related Macular Degeneration (AMD)”, “Diabetic Retinopathy (DR)”, “Retinoblastoma”, “Macular Bunker”, “Retinitis Pigmentosa”, and “Retinal Detachment”. The early detection of such diseases is important insofar as it contributes in mitigating future implications. Many approaches have been developed in the literature for auto-detecting of retinal landmarks and pathologies. The current revolution in deep learning techniques has opened the horizon for researchers in the field of ophthalmology. This paper is a comprehensive review of the deep learning techniques applied for the classification of retinal images, pathology, retinal landmarks, and disease classification. This review is based on indicators such as sensitivity, Area under ROC curve, specificity, F score, and accuracy.

Use Different Mathematical Methods to Solve Three Dimensional Conduction Heat Equation in Cartesian Coordinate

AHMED SALAR; Ahmed M.J. Jassim

AL-Rafidain Journal of Computer Sciences and Mathematics, 2022, Volume 16, Issue 2, Pages 11-14
DOI: 10.33899/csmj.2022.176584

In this paper three-dimensional heat conduction equation in cartesian coordinate has been solved in two different methods one of which depends on the separation of variables and the other depends on the integral transform .The results are got and plotted by using Matlab. And the results obtained showed the difference between the two methods that were used in the solution . That difference is evident in the illustrations . According to the results it was concluded that the integral transform method is the best because it has fewer steps to reached to the solution 

A survey on tamper detection techniques for digital images

Amina Taha; Sundus Khaleel Ebraheem

AL-Rafidain Journal of Computer Sciences and Mathematics, 2022, Volume 16, Issue 2, Pages 15-23
DOI: 10.33899/csmj.2022.176585

Recently, fake and fabricated images that have been manipulated for several purposes, including cosmetic and some for illegal purposes, have spread on social media. And because this is not an easy matter, it has become necessary for researchers in this field to search and investigate the types of images, to verify their authenticity and how to manipulate them. Therefore, the aim of this research is to serve as an assistant to the researcher who wants to enter this field. In this research, a survey of the types of forgery was presented with examples. The most important common methods for detecting forgery were also presented, and the previous studies that contributed to the process of detecting fraud, both traditional detection and deep learning-based detection, were highlighted, while giving the most important strengths and weaknesses of both types. We note from this that detecting the forgery process is a difficult process and takes time to detect the changes that have been made to the image that cannot be detected by the naked eye. In this research, researchers have been urged to go towards deep learning for the purpose of detecting the  forgery of the features that it enjoys.

Hybridization of Swarm for Features Selection to Modeling Heart Attack Data

Omar Shakir; Ibrahim Ahmed Saleh

AL-Rafidain Journal of Computer Sciences and Mathematics, 2022, Volume 16, Issue 2, Pages 25-34
DOI: 10.33899/csmj.2022.176587

Predicting heart attacks using machine learning is an important topic. Medical data sets contain different features, some of which are related to the target group for prediction and some are not. In addition, the data sets are excessively unbalanced, which leads to the bias of machine learning models when modeling heart attacks. To model the unbalanced heart attack data set, this paper proposes the hybridization of Particle swarm optimization (PSO), BAT, and Cuckoo Search (CS) to select the features and adopt the precision for minority classes as a fitness function for each swarm to select the influential features. In order to model the data, set in which the features were selected, it was proposed to use the boosting (Catboost) as a classifier for predicting heart attacks. The proposed method to select features has been compared with each of the three swarms, and the Catboost algorithm has been compared to traditional classification algorithms (naive Bayes, decision trees). The study found that the proposed method of hybridization of the results of the (PSO,  BAT, and BCS) algorithms in selecting features is a promising solution in the field of selecting features and increases the accuracy of the system, and that traditional machine learning models are biased in the case of unbalanced data sets and that selecting the important features according to the target class has an impact on the performance of the models, In addition, the definition of hyperparameters reduces the bias of the selected model. The final model achieved an overall accuracy of 96% on the Accuracy scale and 56% on the Precision scale for the minority class

A Comprehensive Study of Traditional and Deep-learning Schemes for Privacy and Data Security in the Cloud

mohammed Fawzy sheet; Melad jader saeed

AL-Rafidain Journal of Computer Sciences and Mathematics, 2022, Volume 16, Issue 2, Pages 35-24
DOI: 10.33899/csmj.2022.176588

After the availability of Internet infrastructure all over the world, and connectivity is no longer an obstacle over the Internet, cloud computing has emerged as a practical and ideal solution. A huge revolution has taken place in the field of cloud computing, where it is now an industry. However, it faces great difficulties in ensuring data confidentiality and privacy. People hesitate to use it due to the risk of innumerable attacks and security breaches. This article has covered a several directions relayed to cloud computing ideas. This research would focus on traditional and deep-learning based schemes to secure user’s data in the cloud. This study concluded some points about the capabilities of the traditional and deep learning-based scheme. The comparison showed that both of them increased the levels of security and privacy of the cloud. The study conclude that the Deep learning-based method had been implanted to secure clouds’ data in combination with other technique performed better than others.

Melanoma Skin Lesion Classification Using Neural Networks: A systematic review

ahmed hammo; Mohammed Younis

AL-Rafidain Journal of Computer Sciences and Mathematics, 2022, Volume 16, Issue 2, Pages 43-55
DOI: 10.33899/csmj.2022.176589

Melanoma is considered a serious health disease and one of the most dangerous and deadly types of skin cancer, due to its unlimited spread. Therefore, detection of this disease must be early and sound due to the high mortality rate. It is driven by researchers' desire to use computers to obtain accurate diagnostic systems to help diagnose and detect this disease early. Given the growing interest in cancer prediction, we have presented this paper, a systematic review of recent developments, using artificial intelligence focusing on melanoma skin lesion detection, particularly systems designed on neural networks. Using the neural networks for melanoma detection could be part of system of assistance for dermatologists who must make the final decision on whether to recommend a biopsy if at least one of the dermatologist's diagnoses and the support system (a helpful method) indicate melanoma or to investigate if another type of cancerous lesion exists. In the latter situation, the system can be trained to recognize distinct types of cancerous skin lesions. On the other hand, the system is incapable of making final decisions. Given neural networks' evolutionary patterns, updated, changed, and integrated networks are expected to increase the performance of such systems. Based on the decision fusion, theoretical and applied contributions were studied using traditional classification algorithms and multiple neural networks. The period 2018-2021 has been focused on new trends. Also for the detection of melanomas, the most popular datasets and how they're being used to train neural network models were presented. Furthermore, the field of research emphasized in order to promote better the subject during different directions. Finally, a research agenda was highlighted to advance the field towards the new trends.

Strongly Nil* Clean Ideals

Muayad Mohammed Noor Alali; Nazar Hamdoon Shuker

AL-Rafidain Journal of Computer Sciences and Mathematics, 2022, Volume 16, Issue 2, Pages 57-59
DOI: 10.33899/csmj.2022.176591

An element  is known a strongly nil* clean element if a=e1 - e1e2 + n , where e1,e2  are idempotents and n is nilpotent, that commute with one another. An ideal I of a ring R is called a strongly nil* clean ideal if each element of I is strongly nil* clean element. We investigate some of its fundamental features, as well as its relationship to the nil clean ideal.

The Homotopy Perturbation Method to Solve Initial Value Problems of First Order with Discontinuities

Mohammed J. Ahmed; Waleed Al-Hayani

AL-Rafidain Journal of Computer Sciences and Mathematics, 2022, Volume 16, Issue 2, Pages 61-70
DOI: 10.33899/csmj.2022.176592

In this work, the homotopy perturbation method (HPM) is used to solve initial value
problems of first order with various types of discontinuities. The numerical results obtained (are
compared) using the traditional HPM, and the integral equation of the nth equation with the
solution numerical obtained using Simpson and Trapezoidal Rules to demonstrate that the
solution results are extremely accurate when compared to the exact solution. The maximum
absolute error, ‖ . ‖ , maximum relative error, maximum residual error, and expected
convergence order are also provided.

Spectral Extension Property of Perturbed Triple Product on Semisimple Commutative Banach Algebras

مروان عزیز جردو; Amir A. Mohammed

AL-Rafidain Journal of Computer Sciences and Mathematics, 2022, Volume 16, Issue 2, Pages 71-75
DOI: 10.33899/csmj.2022.176593

Under a perturbed triple product defined on three semisimple commutative Banach algebras with the influence of two homomorphisms defined on two of them and that carry certain characteristics, we proved that the spectral extension property is stable.

Software Implementation Solutions of A Lightweight Block Cipher to Secure Restricted IoT Environment: A Review


AL-Rafidain Journal of Computer Sciences and Mathematics, 2022, Volume 16, Issue 2, Pages 77-88
DOI: 10.33899/csmj.2022.176594

With the development of the Internet of Things (IoT) technology, IoT devices are integrated into many of our daily lives, including industrial, security, medical, and personal applications. Many violations of IoT safety have appeared due to the critical physical infrastructure, and network vulnerabilities. Considering the nature of the restricted and limited resources of these devices in terms of size, capacity, and energy, Security is becoming increasingly important. Lightweight cryptography is one of the directions that offer security solutions in resource-constrained environments such as Radio-frequency identification (RFID) and wireless sensor network (WSN).This paper discusses the security issues of these resource-constrained IoT devices and reviews the most prominent Lightweight Bock Cipher suitable for software implementation. Through studying thespecifications and the inner structure for each cipher and their implementation of the performance evaluation on some kind of platform, we provide a design strategies guideline for cryptographic developers to design improved Lightweight Block cipher solutions and compact software implementation for resource-constrained environments.

A Comparative Study for Speech Summarization Based on Machine Learning: A Survey

Hiba Adreese Altememi; Yusra Faisal Al-Irhaim

AL-Rafidain Journal of Computer Sciences and Mathematics, 2022, Volume 16, Issue 2, Pages 89-96
DOI: 10.33899/csmj.2022.176595

The most important aspect of human communication is speech. Lengthy media such as speech takes a long time to read and understand. This difficulty is solved by providing a reduced summary with semantics. Speech summarization can either convert speech to text using automated speech recognition (ASR) and then build the summary, or it can process the speech signal directly and generate the summary. This survey will look at a various of recent studies that have used machine and deep learning algorithms to summarize speech. it discusses the speech summarizing literatures in terms of time restrictions, research methodology, and lack of interest in particular databases for literature searches. As newer deep learning approaches were not included in earlier surveys, this is a new survey in this discipline where different approaches with various datasets were explored for speech summarization and evaluated using subjective or objective methods.

Different Biometrical Features for Detecting Human Intrusion Using Artificial Intelligence: Literature Review

Ansam Nazar Younis

AL-Rafidain Journal of Computer Sciences and Mathematics, 2022, Volume 16, Issue 2, Pages 97-107
DOI: 10.33899/csmj.2022.176596

Many cases of theft and property trespass in addition to crimes occur in the world after these people break into people's homes and buildings illegally, so this article aims to shed light on most of the smart methods and computer technologies used in identifying people that help to reduce these crimes. Where the diversity of biometric traits was relied upon, such as fingerprint, handprint, ear, face, texture, some deformations characteristic of people, eye, footprints, DNA analysis and other important biometric traits. Also, many intelligent algorithms were used to identify these traits.

Medical Image Classification Using Different Machine Learning Algorithms

Sami H. Ismael; Shahab W. Kareem; Firas H. Almukhtar

AL-Rafidain Journal of Computer Sciences and Mathematics, 2020, Volume 14, Issue 1, Pages 135-147
DOI: 10.33899/csmj.2020.164682

The different types of white blood cells equips us an important data for diagnosing and identifying of many diseases. The automation of this task can save time and avoid errors in the identification process. In this paper, we explore whether using shape features of nucleus is sufficient to classify white blood cells or not. According to this, an automatic system is implemented that is able to identify and analyze White Blood Cells (WBCs) into five categories (Basophil, Eosinophil, Lymphocyte, Monocyte, and Neutrophil). Four steps are required for such a system; the first step represents the segmentation of the cell images and the second step involves the scanning of each segmented image to prepare its dataset. Extracting the shapes and textures from scanned image are performed in the third step. Finally, different machine learning algorithms such as (K* classifier, Additive Regression, Bagging, Input Mapped Classifier, or Decision Table) is separately applied to the extracted (shapes and textures) to obtain the results. Each algorithm results are compared to select the best one according to different criteria’s.

Data Modeling and Design Implementation for CouchDB Database

Shaymaa Ahmed Razoqi

AL-Rafidain Journal of Computer Sciences and Mathematics, 2021, Volume 15, Issue 1, Pages 39-55
DOI: 10.33899/csmj.2021.168252

In the modern database environment, new non-traditional database types appear that are Not SQL database (NoSQL). This NoSQL database does not rely on the principles of the relational database. Couchdb is one of the NoSQL Document-Oriented databases, in Couchdb the basic element was a document. All types of databases have the same conceptual data model and it was deferent in the logical and physical model, this mean UML class diagram can be used in the  NoSQL design at a conceptual level, that is, it can be used to design a Couchdb database. In this research, we suggest a method to model and implement the conceptual level of the Couchdb database from the UML class diagram in using simple way depending on the association types. Depending on the types of relationships between classes, we can have more than one database model to choose from and find the most suitable for the system to be designed. A medical clinic database was proposed to implement the transfer steps according to the proposed method. Three database models were designed and implemented to study the suitability of the proposed transfer method.

Nineveh Blood: Android Based Blood Donation Application for Nineveh Governorate in Iraq

Ahmed Mostfa; Aya A. Alabass; Abdel-Nasser Sharkawy

AL-Rafidain Journal of Computer Sciences and Mathematics, 2020, Volume 14, Issue 2, Pages 85-96
DOI: 10.33899/csmj.2020.167341

Blood donation (BD) is one of the most significant contributions that a person can make towards the society. The growing android technology has made the process of BD easier and hassle-free. The Nineveh blood bank is an android application made for such great and noble cause. The application connects the givers and the requesters of blood who live in the Nineveh province, Iraq. The blood requester can serach from a list of all donors who have the same blood group and directly contact them without any third-party involvement. The Nineveh Blood application creates giver’s/requester’s profile through the Google Firebase Real-time database. In which, a one WebSocket two-way channel can constantly send the data back-and-forth between the server and the clients, and store the data as a JavaScript Object Notation (JSON) file.  

Survey on Human Activity Recognition using Smartphone

Adeeba KH; Laheeb M. Ibrahim

AL-Rafidain Journal of Computer Sciences and Mathematics, 2021, Volume 15, Issue 1, Pages 55-67
DOI: 10.33899/csmj.2021.168253

The field of Human Activity Recognition (HAR) is an active research field in which methods are being developed to understand human behavior by interpreting features obtained from various sources, these activities can be recognized using interactive sensors that are affected by human movement. Sensor can embed elements within Smartphones or Personal Digital Assistants (PDAs). The great increase in smart phone users and the increase in the sensor ability of these smart phones, and users usually carry their smartphones with them. This fact makes HAR more important and accepted.
In this survey, A number of previous studies were studied and analyzed, where we prepared a comparison of the research works conducted over the period 2010-2020 in human activity recognition using Smartphone sensors. Comparison charts highlight their most important aspects such as a type of sensor used, activities, sensor placement, HAR- system type (offline, online), computing device, classifier (type of algorithms) and system accuracy levels.

Build a Real-Time Home Security Alarm System Using a Kinect Sensor

Zaid A. Mundher; Khalida Basheer; Safaa Ayad Najeeb; Rami Zuhair

AL-Rafidain Journal of Computer Sciences and Mathematics, 2019, Volume 13, Issue 2, Pages 26-34
DOI: 10.33899/csmj.2020.163512

Surveillance camera systems have been widely used in homes, businesses and other places of work. These systems with its all capabilities and features provide protection to people who uses them.  In this work, a home security alarm system was designed and implemented based on the Microsoft Kinect sensor. The introduced system can detect intrusion and respond to it in real-time. If the intrusion is detected, the system sends SMS as a notification to the authorized user. Moreover, as soon as the intrusion is detected, pictures will be taken using the RGB camera of the Kinect. These pictures will be sent to the authorized user via email, and saved on the local drive. Simultaneously, the proposed system emits a loud sound to frighten away intruders. The proposed system could be used in homes, offices, warehouses, banks, hospitals, etc..

Studying the Bessell Equation of Complex Order

Thair Y. Thanoon; Omar Thaher shalal

AL-Rafidain Journal of Computer Sciences and Mathematics, 2019, Volume 13, Issue 2, Pages 13-27
DOI: 10.33899/csmj.2020.163517

In this paper we derive Bessel equation of complex order (n + i), after that generalized recurrence relations from Bessel equation of order (n) to Bessel equation of complex order (n + i) and will satisfy that. We given illustrates example of different cases .

Applying Classical and Intelligence Techniques for Digital Image Contrast Enhancement

Alyaa taqi

AL-Rafidain Journal of Computer Sciences and Mathematics, 2008, Volume 5, Issue 2, Pages 135-158
DOI: 10.33899/csmj.2008.163990

Modern digital camera technology has produced huge services for the users from different ages and specifications .It made it easer to have images, but the user still needs to enhance those images, which have some problems when taken by the camera, for not applying enough light, as taking it in cloudy weather or on bright light or dark area or taking it from a far distance, all these reasons make the picture not clear having ambiguous details and colors. So, through this research we used some image contrast enhancement techniques to adjust the light for dark images, to make them have deep detail, sharp edges and better quality. Contrast problem is one of the most problems that face those who work on research field or normal users.
            The aim of this research is to improve the contrast of images that have bad contrast using both classical techniques and intelligence techniques. Among intelligence techniques we chose the fuzzy logic methods, to have images contain better colors all over the image and make the images look brighter. By studying the classical and fuzzy logic methods, we proposed a method named (Fuzzy Hyperbolic Threshold), the proposed method gave very good results. We applied the methods on gray, colored images and on a video, and used (Matlab 7) to implement those methods.

Representation of a Distributed Database System for the Medical Purposes Using Oracle

Basam A. Mustafa; Ahmed A. Al-Saman

AL-Rafidain Journal of Computer Sciences and Mathematics, 2013, Volume 10, Issue 2, Pages 173-187
DOI: 10.33899/csmj.2013.163493

This research concerned with the designing and implementation of a distributed database system for the medical purposes. The system has been applied on dental clinic unit and statistics department at Al-Khansaa Educational Hospital at Mosul, and dental clinic unit at Woman Health Care Center at Mosul as a case study.
Client/server model has been used to implement the proposed system's architecture. The computers have been connected together through a local area network (LAN). Horizontal fragmentation technique has been used to distribute the database which achieved a good level of local autonomy. Oracle software were used and utilized to implement the system. It played a dramatic role in protecting data using combination of passwords and user roles hierarchies in addition to achieving transparency and data integrity concepts in the system. The proposed system simplified saving and retrieving data of dental clinics. It also provides dental clinics units  and statistics department with necessary reports and statistics. The proposed system has the ability to automatically perform daily backup for the database in addition to the manual options for database backup and recovery.

Parallel Gaussian Elimination Method

Muhammad W. Muhammad Ali

AL-Rafidain Journal of Computer Sciences and Mathematics, 2008, Volume 5, Issue 2, Pages 59-77
DOI: 10.33899/csmj.2008.163986

The aim of the project is to develop parallel approaches for Gaussian Elimination Methods that are used in linear programming  to solve linear module  systems.
            Most of these models are time-consuming when executed and processed in the sequential microprocessor computers. During the project, we try to decrease this time and increase the efficiency of the algorithm for the Gaussian Elimination Method, through developing parallel methods appropriate to be executed on MIMD type computers.
            In this paper, three algorithms were suggested for paralleling a developed algorithm of Gaussian Elimination Method and a comparison was made between the three algorithms and the original.
            As we have been able to accelerate the three parallel methods and the speedup was one of the following:
          Speedup =  ,  no. of processor is (50)
            In general, the practical results and the suggested programs for these new algorithms proved to be better in performance than their analogues that are executed in computers of sequential processor in view of the two elements of execution time and algorithm time.

Evaluation of Clustering Validity

Rudhwan Yousif Sideek; Ghaydaa A.A. Al-Talib

AL-Rafidain Journal of Computer Sciences and Mathematics, 2008, Volume 5, Issue 2, Pages 79-97
DOI: 10.33899/csmj.2008.163987

Clustering is a mostly unsupervised procedure and the majority of the clustering algorithms depend on certain assumptions in order to define the subgroups present in a data set. As a consequence, in most applications the resulting clustering scheme requires some sort of evaluation as regards its validity.
            In this paper, we present a clustering validity procedure, which evaluates the results of clustering algorithms on data sets. We define a validity indexes, S_Dbw & SD, based on well-defined clustering criteria enabling the selection of the optimal input parameters values for a clustering algorithm that result in the best partitioning of a data set.
            We evaluate the reliability of our indexes experimentally, considering clustering algorithm (K_Means) on real data sets.
Our approach is performed favorably in finding the correct number of clusters fitting a data set.

Publisher: Mosul University

Email:  rafjcomath@gmail.com

Managing Editor: Professor Dr. Ahmed Mohammed Ali

Print ISSN: 1815-4816

Online ISSN: 2311-7990

Keyword Cloud