Iraqi Journal for Computers and Informatics 2022-10-12T21:48:33+03:00 Prof. Dr. Safaa O. Al-mamory Open Journal Systems <p>Iraqi Journal for Computers and Informatics is an open access ,double-blind peer reviewed, international academic journal published biannual (since 2017). It is institutional journal issued by the University of Information Technology and Communications (UoITC) in Baghdad- Iraq; UoITC is one of governmental universities which established by the Ministry of Higher Education in Iraq. IJCI aims to contribute to the constant scientific research and to provide a sober scientific journal that enriches scholars around the world and it deals with all aspects of computer science.</p> SURVEY: AUDIO READING SYSTEM FOR BLIND PERSONS 2022-04-02T21:30:57+03:00 Mohammed Ali Mohammed Karim Q. Hussein Mustafa Dhiaa Al-Hassani <p>Audio Reading System is used to help blind people to read the text based on camera as input device and speaker as output device. The system used the OCR algorithm to extract the text from input image and Text-to-Speech algorithm to convert text into corresponding voice. In this paper, we review newest research of audio reading system. We discuss the hardware and software, which is used, on system for different types approach. Finally, the result of this paper that is: Raspberry pi, python and tesseract are best tools used in Audio reading system. Also the braille and finger print devices are not efficient and not easy to use.</p> 2022-04-02T00:00:00+03:00 Copyright (c) 2022 IMPROVING THE PRIORITIZATION PROCEDURE OF PATIENTS WITH COVID-19 IN HOSPITALS BASED ON DECISION-MAKING TECHNIQUES: A SYSTEMATIC REVIEW 2022-08-11T22:01:26+03:00 Thura J. Mohammed Suha M. Hadi A. S. Albahri <p>Coronavirus-specific antibodies can be detected in the blood of people who have recently recovered from coronavirus disease-2019 (COVID-19). Convalescent-Plasma (CP) transfusion process proved that it's among the most efficient protocols, and it's used in hospitals to treat various infections and diseases. Several medical issues have been addressed due to the growing interest in creating Artificial Intelligence (AI) applications. However, considering the virus's enormous potential harm to global public health, such uses are insufficient. This proposed systematic review and meta-analysis aims to obtain an overview of COVID-19, highlight the limits of decision-making approaches, and give healthcare professionals information about the technique's advantages. Between 2016 and 2021, five databases, namely IEEE Xplore, Web of Science, PubMed, Science Direct, and Scopus, were utilized to run four sequences of search queries. As a result, 477 studies are found to be relevant. Only six studies were thoroughly examined and included in this review after screening articles and using proper inclusion criteria, highlighting the lack of research on this crucial topic. Studies' findings were reviewed to identify the gaps in all the evaluated papers. Motivations, problems, constraints, suggestions, and case examples were thoroughly examined. This study seeks to answer how we support the researchers with collected information for managing transfusion of the highest quality CP to the most critical COVID-19 patients across telemedicine hospitals.</p> 2022-05-05T00:00:00+03:00 Copyright (c) 2022 Review of Detection Denial of Service Attacks using Machine Learning through Ensemble Learning 2022-10-12T21:48:33+03:00 Nazanin Najm Abdulla Rajaa K. Hasoun <p>Today's network hacking is more resource-intensive because the goal is to prohibit the user from using the network's resources when the target is either offensive or for financial gain, especially in businesses and organizations. That relies on the Internet like Amazon Due to this, several techniques, such as artificial intelligence algorithms like machine learning (ML) and deep learning (DL), have been developed to identify intrusion and network infiltration and discriminate between legitimate and unauthorized users. Application of machine learning and ensemble learning algorithms to various datasets, consideration of homogeneous ensembles using a single algorithm type or heterogeneous ensembles using several algorithm types, and evaluation of the discovery outcomes in terms of accuracy or discovery error for detecting attacks. The survey literature provides an overview of the many approaches and approaches of one or more machine-learning algorithms used in various datasets to identify denial of service attacks. It has also been shown that employing the hybrid approach is the most common and produces better attack detection outcomes than using the sole approaches. Numerous machine learning techniques, including support vector machines (SVM), K-Nearest Neighbors (KNN), and ensemble learning like random forest (RF), bagging, and boosting, are illustrated in this work (DT). That is employed in several articles to identify different denial of service (DoS) assaults, including the trojan horse, teardrop, land, smurf, flooding, and worm. That attacks network traffic and resources to deny users access to the resources or to steal confidential information from the company without damaging the system and employs several algorithms to obtain high attack detection accuracy and low false alarm rates.</p> 2022-06-30T00:00:00+03:00 Copyright (c) 2022