Iraqi Journal for Computers and Informatics
Not a member yet
273 research outputs found
Sort by
Artificial Intelligence (AI) and Internet of Things (IoT) Applications in Smart Cities: Literature Review
No full textSmart cities employ advanced technology like artificial intelligence (AI) and the Internet of Things (IoT) to resolve urban challenges and improve the quality of life. However, the literature lacks one comprehensive synthesis of AI and IoT\u27s joint contribution to building smart city literature and beyond. The study wanted to take a systematic review to find the role and combined roles of AI and IoT.Researchers conducted research by following PRIMA guidelines, mostly on applications of AI and IoT in building smarter cities by taking many research papers as their sources. A total of 30 relevant peer-reviewed studies were identified from an initial pool of about 16,600 records generated primarily from four biggest databases: Science Direct, Scopus, Web of Science, IEEE Explore, and ProQuest, including related articles of the identified papers AI and IoT together play a vital role in six significant domains. AI, especially the Internet of Things (IoT), helps provide a broader data set in real-time. Whenever the AI techniques are set, it collects data and finds results in it to optimize and automate the city operations to improve the city\u27s sustainability and public services. The most common domains of the application of Riot are: Data-driven urban service efficiency Energy efficiency and environmental sustainability Efficacy in smart transportation and traffic management to provide smart surveillance and avoid future cybersecurity threats. Urban planning also requires decision support
New Hybrid Model Combining NoSQL and SQL Database to Ameliorate the Performance of Big Data System
No full textDue to their flexibility, NoSQL databases have gained popularity as a preferred data storage destination of modern web applications and can accommodate easy growth. But they are not without risk: Technical Articles can be susceptible to injection attacks that could result in a data breach or security concern. This study explores the ability to detect such NoSQL injection attacks which involves both machine learning models and data balancing techniques. We projected several classifiers - Support Vector Machines, Decision Trees, AdaBoost, Random Forest and Logistic Regression – in data balanced with approaches such as SMOTE, Random Oversamplingand NearMiss or downsampled with either Random UnderSampling, SMOTEENN or SMOTETomek. The findings indicate that ensemble classifiers (i.e., AdaBoost and Random Forest) consistently outperform the others, achieving weighted F1-scores of 0.920--1.0 with various resampling techniques. Hybrid balancing approaches triggered a significant boost in detection malicious queries, which becomes close to the ideal performance (i.e., precision and recall) for both infrequent and frequent types of GPCs. Less complex models such as Logistic Regression and Naive Bayes also performed extremely well with hybrid resampling, attaining weighted F1-scores greater than 0.99. Discussing these results show that the hybrid resampling strategy along with ensemble learning are able to make the most robust and accurate NoSQL injection detection system to secure threats web applications without ignoring real NoSQL threats.
Event-Triggered Tracking Algorithm for Maritime Vessels Using Remote Sensing and Game Theory
No full textThe ship\u27s event-triggered tracking algorithm, which combines game theory and remote sensing. The technique addresses issues with conventional continuous and discrete control techniques, which consume excessive amounts of energy and prematurely wear out actuators due to frequent updates. In order to locate ships, this paper first employs the YOLOv8 deep neural network and radar-based remote sensing. After determining the distances and connections between ships, the target trajectory is altered using a game-theoretic framework. In order to reduce needless computations and communications, the controller only activates when significant events take place. This is not the same as conventional time-triggered techniques. Good results were obtained from tests on two benchmark datasets: the Synthetic Aperture Radar Ship Dataset (SAR-Ship-Dataset) and the SAR Ship Detection Dataset (SSDD). On SSDD, the proposed algorithm achieved 92% accuracy and 93% sensitivity, while on SAR-Ship-Dataset, it achieved 93% accuracy and 91% sensitivity. These results lay the foundation for the development of more efficient marine tracking systems by demonstrating that event-triggered tracking can maintain high tracking accuracy while using less energy.
 
Terahertz Communication for 5G and beyond: A Comprehensive Review
No full textThe rapid growth of mobile data traffic, supported via applications like extended reality (XR), communication-based holographic, and huge machine-type connectivity, led 5G network communications to the performance restrictions. Terahertz communication in 5G mobile communications has appeared as a promising solution for overcoming the limited spectrum lack and performing ultra-high data rates, in addition to capacity. This review paper supplies a thorough overview of modern evolution in Terahertz (THz) wireless communication systems, focusing on their potential to uphold data rates exceeding hundreds of gigabits per second. This review paper argues that the new key trends, like the availability of spectrum, the channels-based ultra-broadband, and consolidated arrays of utilized antennas, which are used to make THz communication necessary progress for the next generation of mobile communication systems. Crucial challenges consisting of coverage restrictions, propagation loss, hardware complexity, and scarcity of standardization are examined. Prospect strategies for mitigating such challenges have also been surveyed via the combination of intelligent considering surfaces, transceivers-based photonic-assisted, and characterized beamforming. Total, this paper concludes that THz mobile communication introduces a transformative move in realizing the ultra-high-capacity, very low latency, and high-efficiency aims of 5G mobile communications and beyond generations. The presented analysis in this review paper illuminates the practical trade-offs that presently restrict empirical deployment of THz and summarizes the extremely promising research study trends to get the better of them. This will provide a base for future expansion aimed at combining THz communication systems with 5G and beyond mobile communication network systems
Talking Machine: A Survey of Chatbot Foundation, Use Case, and Challenges
No full textRecently, chatbot systems have grown from the very basic rule-based systems to more advanced ones, such as natural and context-aware systems that incorporate sophisticated neural network techniques. This paper provides a comprehensive review of evolution and taxonomy and analyzes the application of chatbots in various fields, such as healthcare, banking, education, mental health, customer service, and image recognition, to reveal contemporary strengths and applications. In addition to observation of the most important assessment measurements and highlights of the latest studies, promising performance has been reported in the literature, with accuracy/success rates over 90% for some studies, with user satisfaction levels reaching 95% in certain health-related scenarios; however, these results remain specific to their settings rather than generalizable for all chat applications. The paper concludes that contemporary AI-based chatbots are strong in response generation and context appreciation but are still weak when dealing with ambiguous questions and multi-turn dialogues. Some of the key challenges, such as making the system scalable and personal and achieving human-like conversational quality in different contexts, were identified. This in-depth review summarizes recent developments as well as challenges in the area of chatbot technology and emphasizes the necessity of innovation in AI and NLP to overcome these challenges and improve chatbot performance and user experience
Innovative strategies for IoT security using AI and blockchain: a comprehensive review
No full textThe Internet of Things (IoT) is an emerging technological revolution, where devices communicate with each other over the internet to receive communications and information. These devices generate massive amounts of information. As industries increasingly rely on IoT devices, the need for technologies to enhance data security and privacy has emerged. This data faces significant security challenges, such as cyberattacks or data tampering. Therefore, it is imperative to develop effective protection for this data. This study aims to review the role of artificial intelligence (AI) and blockchain technology in enhancing IoT security by integrating these two technologies. The combination of AI and IoT represents a tremendous revolution in the rapidly evolving field, given its ability to simplify tasks easily and efficiently. AI analyzes and classifies data, detects threats and malicious attacks, while blockchain technology provides an additional layer of protection for the IoT through decentralized storage that prevents data tampering and ensures its integrity and confidentiality. In this study, we present a structured and systematic review of research published between 2021 and 2025, focusing on the role of AI and blockchain in securing IoT data. The results demonstrate that integrating AI with blockchain technology improves IoT security by detecting attacks early, reducing vulnerabilities, and preventing unauthorized access or data tampering. However, the evolving nature of attacks and challenges calls for further research to find or develop solutions capable of addressing future challenges to ensure security and reliability in data exchange between devices
Performance Evaluation of FSO-OCDMA Based on Security Perspective
No full textالاتصالات البصرية في الفضاء الحر (FSO) المدمجة مع تقنية التقسيم المتعدد للرموز البصرية (OCDMA) توفر حلاً آمنًا وعالي السعة لأنظمة الاتصالات البصرية اللاسلكية المتقدمة.تهدف هذه الورقة إلى تقييم فعالية تطبيقات FSO-OCDMA المختلفة في ظل ظروف جوية متنوعة، مع التركيز بشكل خاص على الجانب الأمني.
يتم تحليل تقنيات متعددة مثل PD-NOMA، وSAC-OCDMA باستخدام مخططات ترميز مختلفة، بالإضافة إلى الأنظمة الهجينة FiWi، وتقنية التعدد باستخدام الزخم الزاوي المداري(OAM-based multiplexing).تشمل الدراسة تحليلمعدل الخطأ في البتات (BER)، وقوة الإشارة، والخصائص الأمنية، وذلك بالاعتماد على محاكاة ونتائج تجريبية مستمدة من أبحاث حديثة ومتقدمة.
وتستنتج الدراسة أن استراتيجيات التضمين والترميز المحددة تُسهم بشكل كبير في تعزيز أمن الطبقة الفيزيائية وزيادة مرونة النظام.With the high explosion in data traffic in today\u27s networks, the importance of secure and high-capacity optical wireless communication has become more pressing than ever before. Free Space Optics (FSO) in combination with Optical Code Division Multiple Access (OCDMA) has great potential to meet these demands. However, most of the current research has considered system performance and physical layer security independently and left a major gap in our knowledge on how they interact, particularly under practical conditions in the real atmosphere. This study takes up this challenge by investigating the combined operation of performance and security in FSO-OCDMA systems that are necessary for protection against eavesdropping, jamming and unauthorized access. We investigate a few FSO-OCDMA techniques such as PD-NOMA, SAC-OCDMA with various coding schemes, hybrid fiber-wireless (FiWi) systems and OAM-based multiplexing schemes in various turbulence conditions. Through simulation testing, we cover some of the most important metrics including Bit Error Rate (BER), signal robustness and security threats. Our results demonstrate that well-optimized modulation and coding schemes, and specifically that SAC-OCDMA combined with sophisticated zero cross-correlation coding schemes, dramatically enhance the system security while at the same time enhancing the communication reliability. These results offer practical advice for construction of the next generation of secure, high-performance optical wireless networks
Ensuring data protection within multi-tenant databases built on cloud infrastructure
No full textCloud computing has swiftly become a prominent trend in the technology industry, owing to its various benefits such as scalability, high availability, and cost-effectiveness. Consequently, an increasing number of organizations are shifting their operations to cloud-based environments. It is anticipated that cloud technologies will soon form a foundational component of nearly every enterprise.
This transformation has significantly influenced sectors like Software as a Service (SaaS), where traditional Database Management Systems (DBMSs) have transitioned into Cloud-based DBMSs (CDBMSs). Alongside this evolution, there has been a movement from conventional single-tenant database structures to multi-tenant architectures, which allow for more efficient utilization of infrastructure and resources.
However, despite these benefits, many organizations are still hesitant to adopt multi-tenant database systems due to persistent concerns over data security. The practice of storing data from multiple tenants on the same server—or even within shared tables—introduces considerable risks related to unauthorized access. In response to these concerns, the current research centers on database security in cloud settings, with a specific focus on the unique challenges associated with multi-tenant systems
Improving Network Security: Blockchain-based Authentication and Authorization Scheme in Accordance with Weighted Nodes in a Clustered Network
Full text linkABSTRACT Addressing concerns related to network security involves protecting a network from various threats, including internal and external risks, such as identity theft, collusion, malicious activities, and other attacks. This study aims to address these challenges by introducing the authentication of the identity of nodes that are connected to a network, utilizing blockchain technology and consensus algorithms as integral elements of its security framework. To improve security and deal with identity theft and spoofing attacks in clustered networks, we suggest implementing a blockchain-based authentication and authorization scheme. This scheme ensures that the authentication of nodes or devices relies on blockchain technology, employing a voting algorithm to validate the eligibility of nodes that are seeking access to a network. A new block is generated for each incoming node, and this block contains essential information about that node. The decision to accept a new node into the network is determined through a voting process that considers individual node weights calculated based on three key factors: initial weight, age, and incentive. Java NetBeans IDE 8.0.2 is used to design and implement the simulator. Experimental results comprise the implementation of consensus algorithms and demonstrate the effect of the highest weight nodes. Moreover, these algorithms will launch attacks on the network and are aware of our scheme’s ability to detect such attacks. The simulation results show that our authentication scheme exhibits advantages in terms of security, scalability, and resistance capability against attacks
Prediction of Hypertension Patients with Machine Learning Algorithm
Full text linkHypertension, known as the "silent killer," is one of the leading causes of global mortality, with a steadily increasing prevalence. Worldwide, the prevalence of hypertension reaches approximately 30%, with only 50% of cases being diagnosed and a low level of treatment adherence. Hypertension symptoms are often invisible, making early detection crucial to preventing serious complications. This paper aims to develop a hypertension prediction system using the Decision Tree and Random Forest algorithms, which are machine learning techniques used to solve classification and regression problems. These algorithms can predict hypertension risk based on clinical data, such as age, medical history, and lifestyle. The findings of this paper indicate that the Decision Tree and Random Forest algorithms are effective in predicting hypertension risk, achieving accuracies of 99.6% and 99.5%, respectively. This prediction system can provide fast and accurate information, assisting healthcare professionals in designing appropriate intervention strategies while also supporting better medical decision-making