Research Articles

Permanent URI for this collection

https://dir.muni.ac.ug/handle/20.500.12260/17

Browse

Now showing 1 - 20 of 76

A Comprehensive review on cryptographic techniques for securing internet of medical things: A state-of-the-art, applications, security attacks, mitigation measures, and future research direction.
(Mesopotamian Journal of Artificial Intelligence in Healthcare, 2024-11-30) Wamusi, Robert; Asiku, Denis; Adebo, Thomas; Aziku, Samuel; Kabiito, Simon Peter; Zaward, Morish; Guma, Ali
As healthcare becomes increasingly dependent on the Internet of Medical Things (IoMT) infrastructure, it is essential to establish a secure system that guarantees the confidentiality and privacy of patient data. This system must also facilitate the secure sharing of healthcare information with other parties within the healthcare ecosystem. However, this increased connectivity also introduces cybersecurity attacks and vulnerabilities. This comprehensive review explores the state-of-the-art in the IoMT, security requirements in the IoMT, cryptographic techniques in the IoMT, application of cryptographic techniques in securing the IoMT, security attacks on cryptographic techniques, mitigation strategies, and future research directions. The study adopts a comprehensive review approach, synthesizing findings from peer-reviewed journals, conference proceedings, book chapters, Books, and websites published between 2020 and 2024 to assess their relevance to cryptographic applications in IoMT systems. Despite advancements, cryptographic algorithms in IoMT remain susceptible to security attacks, such as man-in-the-middle attacks, replay attacks, ransomware attacks, cryptanalysis attacks, key management attacks, chosen plaintext/chosen ciphertext attacks, and side-channel attacks. While techniques like homomorphic encryption enhance security, their high computational and power demands pose challenges for resource-constrained IoMT devices. The rise of quantum computing threatens the efficacy of current cryptographic protocols, highlighting the need for research into quantum-resistant cryptography. The review identifies critical gaps in existing cryptographic research and emphasizes future directions, including lightweight cryptography, quantum-resistant methods, and artificial intelligence-driven security mechanisms. These innovations are vital for meeting the growing security requirements of IoMT systems and protecting against increasingly sophisticated threats.
A secure and efficient blockchain and distributed ledger technology-based optimal resource management in digital twin beyond 5G networks using hybrid energy valley and levy flight distributer optimization algorithm.
(IEEE, 2024-08-19) Kumar, K. Suresh; Alzubi, Jafar A.; Sarhan, Nadia M.; Awwad, E. M.; Kandasamy, V.; Ali, Guma
This paper aims to establish a virtual object management system, as well as optimal task scheduling using the foundation of Digital Twins (DT), to improve the user’s experience with management and to accomplish the task efficiently. On the other hand, offloading tasks using IoT gadgets to edge computing, fails to speed up control by users. The capabilities of the DT are provided by executing processes such as visualization, virtualization, synchronization, and simulation. The optimal selection of the virtual objects for the DT is done by utilizing the implemented Hybrid Energy Valley with Lévy Flight Distribution Optimization (HEV-LFDO) in order to optimally offload the task by the edge devices. The optimal selection of the virtual objects is done with the aid of the HEV-LFDO in the DT by considering the total cost of executing all tasks using the selected virtual objects and the decision variables to determine whether a virtual object is taken for executing a task or not as the constraint. The data for performing resource management is secured using the blockchain or distributed ledger technology. This accounts for the minimization of the local loss function. Finally, the secured data is considered for optimal resource management tasks. The optimal resource management is done using the same HEV-LFDO. This optimal resource management is carried out by considering the constraints like the cost of assigning a virtual object for the task to the edge device, and the cost of assigning the task to the edge device. These two costs are analyzed by taking the network’s bandwidth, energy consumption, and computational resources into consideration. Experimental verifications are conducted on the executed optimal resource management scheme to prove the ability of the implemented model to be integrated with the edge computing network. The overall processing time as well as the latency are also minimized by executing the optimal resource management scheme.
A Survey on artificial intelligence and blockchain applications in cybersecurity for smart cities
(2025-01-10) Asiku, Denis; Adebo, Thomas; Wamusi, Robert; Aziku, Samuel; Kabiito, Simon Peter; Zaward, Morish; Sallam, Malik; Ali, Guma; Mijwil, Maad M.
Smart cities rapidly evolve into transformative ecosystems where advanced technologies work together to improve urban living. These interconnected environments use emerging technologies to offer efficient services and sustainable solutions for urban challenges. As these systems become more complex, their vulnerability to cybersecurity threats also increases. Integrating artificial intelligence (AI) and Blockchain technologies to address these challenges presents promising solutions that ensure secure and resilient infrastructures. This study provides a comprehensive survey of integrating AI, Blockchain, cybersecurity, and smart city technologies based on an analysis of peer-reviewed journals, conference proceedings, book chapters, and websites. Seven independent researchers reviewed relevant literature published between January 2021 and December 2024 using ACM Digital Library, Wiley Online Library, Taylor & Francis, Springer, ScienceDirect, MDPI, IEEE Xplore Digital Library, IGI Global, and Google Scholar. The study explores how AI can enhance threat detection, anomaly detection, and predictive analytics, enabling real-time responses to cyber threats. It examines various AI methodologies, including machine learning and deep learning, to identify vulnerabilities and prevent attacks. It discusses the role of Blockchain in securing data integrity, improving transparency, and providing decentralized control over sensitive information. Blockchain’s tamper-proof ledger and smart contract capabilities offer innovative solutions for identity management, secure transactions, and data sharing among smart city stakeholders. The study also highlights how combining AI and Blockchain can create robust cybersecurity frameworks, enhancing resilience against emerging threats. The survey concludes by outlining future research directions and offering recommendations for policymakers, urban planners, and cybersecurity professionals. This study identifies emerging trends and applications for enhancing the security and resilience of smart cities through innovative technological solutions. The survey provides valuable insights for researchers and practitioners who aim to utilize AI and Blockchain to improve smart city cybersecurity.
A survey on artificial intelligence in cybersecurity for smart agriculture: state-of-the-art, cyber threats, artificial intelligence applications, and ethical concerns.
(Mesopotamian Academic Press, Imam Ja'afar Al-Sadiq University, 2024-07-20) Ali, Guma; Mijwil, Maad M.; Buruga, Bosco Apparatus; Abotaleb, Mostafa; Adamopoulos, Ioannis
Wireless sensor networks and Internet of Things devices are revolutionizing the smart agriculture industry by increasing production, sustainability, and profitability as connectivity becomes increasingly ubiquitous. However, the industry has become a popular target for cyberattacks. This survey investigates the role of artificial intelligence (AI) in improving cybersecurity in smart agriculture (SA). The relevant literature for the study was gathered from Nature, Wiley Online Library, MDPI, ScienceDirect, Frontiers, IEEE Xplore Digital Library, IGI Global, Springer, Taylor & Francis, and Google Scholar. Of the 320 publications that fit the search criteria, 180 research papers were ultimately chosen for this investigation. The review described advancements from conventional agriculture to modern SA, including architecture and emerging technology. It digs into SA’s numerous uses, emphasizing its potential to transform farming efficiency, production, and sustainability. The growing reliance on SA introduces new cyber threats that endanger its integrity and dependability and provide a complete analysis of their possible consequences. Still, the research examined the essential role of AI in combating these threats, focusing on its applications in threat identification, risk management, and real-time response mechanisms. The survey also discusses ethical concerns such as data privacy, the requirement for high-quality information, and the complexities of AI implementation in SA. This study, therefore, intends to provide researchers and practitioners with insights into AI’s capabilities and future directions in the security of smart agricultural infrastructures. This study hopes to assist researchers, policymakers, and practitioners in harnessing AI for robust cybersecurity in SA, assuring a safe and sustainable agricultural future by comprehensively evaluating the existing environment and future trends.
Advancing green hydrogen production in Algeria with opportunities and challenges for future directions
(Springer Nature, 2025-02-14) Benchenina, Yacine; Zemmit, Abderrahim; Bouzaki, Mohammed Moustafa; Loukriz, Abdelouadoud; Elsayed, Salah K.; Alzaed, Ali; Ghoneim, Sherif S. M.
Green hydrogen represents a sustainable energy solution capable of supporting the global shift away from fossil fuels. In Algeria, with its abundant solar resources, this potential is significant. However, challenges related to water resource management and the energy cost of production limit large-scale implementation. Addressing these issues is crucial for effectively harnessing Algeria’s renewable energy potential. This study conducts an in-depth analysis leveraging advanced simulation tools like HOMER Pro to compare photovoltaic (PV) productivity and hydrogen yields in Algerian regions. The study identifies both desert regions and non-desert areas for their potential, employing innovative methods such as seawater electrolysis and wastewater utilization for sustainable water sourcing. The potential integration of hydrogen fuel cells into microgrids is also explored for enhanced energy stability and storage. The findings reveal that desert regions, such as Tamanrasset and Adrar, exhibit the highest photovoltaic electricity productivity, generating 33.5 GWh/year and 32.9 GWh/year, respectively. This translates into green hydrogen production capacities of 679 tons/year and 668 tons/year. Meanwhile, northern regions like Tlemcen and Skikda demonstrate substantial potential, producing 29 GWh/year and 26.6 GWh/year of solar electricity, which results in green hydrogen production outputs of 589 tons/year and 539 tons/year, respectively. This underscores Algeria’s ability to leverage solar energy across diverse regions. The study highlights that while desert regions exhibit high solar and hydrogen production, northern areas provide a strategic advantage due to their proximity to European markets. Algeria’s existing infrastructure supports efficient export to European markets, offering a strategic advantage in green hydrogen trade.
An Editorial vision for civil engineering: navigating intelligence and innovation
(Mesopotamian Academic Press, 2025-11-01) Mijwil, Maad M.; Adamopoulos, Ioannis; Ali, Guma
The integration of Artificial Intelligence in civil engineering has seen a major advancement over the applications of primitive data-driven models, reaching advanced hybrid physics-informed models. This evolution represents a significant change of paradigm from the basic predictive analytics to what is now called "structural cognition." But in this cutting-edge paradigm, the evolutionary learning of AI beyond the structural prediction is further developed, with the ability to learn underlying causal relationships in complicated engineering systems. This not only allows them to diagnose potential problems, but also to proactively propose well-targeted remedial measures, giving engineers a greater understanding of the situation as well as better, better-informed decision-making with respect to infrastructure sustainability and safety [1], [2]. A critical element to this evolution is the emergence of "perceptive infrastructure." This idea is further greatly supported by similar inventions like wavelet-diffusion architectures, and it is very useful in the design of the most robust vision-based monitoring systems. The systems are especially well-suited to demanding environments, such as low-light and other bad weather conditions where conventional surveillance techniques tend to break down. By equipping infrastructure with the ability to sense and make real-time sense of their environment with high fidelity, these technologies are ushering in a new era of self-sensing, self-reporting and even self-predicting civil assets, heading toward constant intelligent self-diagnosis [1]. Figure 1 illustrates artificial intelligence tools in civil engineering.
Analysing the connection between ai and industry 4.0 from a cybersecurity perspective: defending the smart revolution
(Mesopotamian Journal of Big Data, 2023-05-05) Bala, Indu; Mijwil, Maad M.; Ali, Guma; Sadıkoğlu, Emre
In recent years, the significance and efficiency of business performance have become dependent heavily on digitization, as jobs in companies are seeking to be transformed into digital jobs based on smart systems and applications of the fourth industrial revolution. Cybersecurity systems must interact and continuously cooperate with authorized users through the Internet of Things and benefit from corporate services that allow users to interact in a secure environment free from electronic attacks. Artificial intelligence methods contribute to the design of the Fourth Industrial Revolution principles, including interoperability, information transparency, technical assistance, and decentralized decisions. Through this design, security gaps may be generated that attackers can exploit in order to be able to enter systems, control them, or manipulate them. In this paper, the role of automated systems for digital operations in the fourth industrial revolution era will be examined from the perspective of artificial intelligence and cybersecurity, as well as the most significant practices of artificial intelligence methods. This paper concluded that artificial intelligence methods play a significant role in defending and protecting cybersecurity and the Internet of Things, preventing electronic attacks, and protecting users' privacy.
Arduino based smart energy saving system in Ugandan public universities: a case study of Muni university
(International Journal of Innovative Research and Development, 2019-06) Nkamwesiga, Lawrence; Kazibwe, Julius Junior; Male, Paul
The application of internet of things in the real world offers numerous benefits including smart homes and offices, a technology that does not only save energy but also saves money. Office automation is becoming popular due to its numerous benefits as applied in the world of internet of things. The specific objectives of the study were: to assess the current energy usage, identify current energy saving measures, and design and implement a smart energy saving system for Muni University. System requirements were collected from the respondents who were staff of Muni University. The study considered 2 respondents from estates office, 2 from procurement, 1 from each of the three departments of education, Computer and Information Science, and Nursing Sciences. User requirements were gathered a qualitative protocol using focus group discuss and thematic analysis technique was employed. Heterogeneous home automation systems and technologies were considered in review with central controller-based Arduino, sensors, web based, email, Bluetooth, mobile, SMS, ZigBee, Dual Tone Multi Frequency, and cloud based. The study design utilized the Global system for mobile communication technology as a user interface using SMS based communication with Arduino as the central controller. The system supports internet of things concept that can be applied in saving electrical energy usage in public places including public universities. The study further recommends the Ugandan government to advocate for Arduino Based Smart Energy Saving System that can reduce electrical energy expenditure in Ugandan public universities Muni University inclusive.
Artificial intelligence in corneal topography: A short article in enhancing eye care
(Mesopotamian Journal of Artificial Intelligence in Healthcare, 2023-06-17) Ali, Guma; Eid, Marwa M.; Ahmed, Omar G.; Abotaleb, Mostafa; Alaabdin, Anas M. Zein; Buruga, Bosco Apparatus
The eye is a critical part of the human being, as it provides complete vision and the ability to receive and process visual details, and any deficiency in it may affect vision and loss of sight. Corneal topography is one of the essential diagnostic tools in the field of ophthalmology, as it can provide important information about the cornea and the problems that appear in it. Artificial intelligence strategies contribute to the development of the healthcare domain through a group of approaches that have a significant and vital impact on improving the field of ophthalmology. The primary purpose of this paper is to highlight the efficiency of artificial intelligence in extracting features from corneal topography and how these techniques contribute to helping ophthalmologists diagnose corneal topography. Furthermore, the focus is on the performance of AI algorithms, their diagnostic capabilities, and their importance in helping physicians and patients. The effects of this paper confirm the effectiveness and efficiency of artificial intelligence algorithms in the clinical diagnosis of various eye concerns.
Artificial intelligence solutions for health 4.0: overcoming challenges and surveying applications
(Mesopotamian Journal of Artificial Intelligence in Healthcare, 2023-03-10) Al-Mistarehi, Abdel-Hameed; Mijwil, Maad M.; Filali, Youssef; Bounabi, Mariem; Ali, Guma; Abotaleb, Mostafa
In recent years, the term Health 4.0 has appeared in health services and is related to the concept of Industry 4.0. The term Health 4.0 focuses on replacing traditional care in hospitals and medical clinics with home health services that are based on artificial intelligence techniques through the use of telemedicine applications that allow the monitoring of patients in a virtual environment. This term is utilized to represent digital change in the healthcare sector. Governments aim to develop the level of medical care in hospitals and clinics to ensure the provision of healthcare benefits at low costs and increase patient satisfaction. It has become vital for hospitals to grow their environment into digital environments in their services through the use of a set of computer programs based on artificial intelligence. Artificial intelligence techniques in Health 4.0 provide a set of procedures that benefit patients and healthcare workers, including early diagnosis, make inquiries into treatment, data analysis, reports on the patient's condition, and others. The primary purpose of this article is to determine the significance of Health 4.0 and AI techniques in healthcare by mentioning the most important benefits and weaknesses of using AI techniques in healthcare.
Assessing organisational information systems security by human insiders in private and public universities in Uganda
(IMPACT: International Journal of Research in Engineering & Technology, 2015) Businge, Phelix Mbabazi
Information system security management is expected to be a high priority for organizational success, given that Information is critical both as input and output of an organization. Hence, there is need to have a secure information system to conduct any business related activities to ensure six objectives of information security: confidentiality; integrity; availability; legitimate use (identification, authentication, and authorization); auditing or traceability; and non-repudiation of the information. This study identified the objectives of information security, key human insider threats which affect information system security of Business organization and the level of information security policy compliance in organizations. The study was carried out in two Universities one private and another Public University where forty (40) Questionnaires were distributed and the findings showed Institutional data security (protecting company information assets) with mean of 3.79 and Employees (safety, satisfaction, retention) with mean of 3.00 which helps to motivate insider to feel part of organization were given law priority and Respondents also identified Laptops ranked as number 1 (mean =3.91) as frequently used device in the institution to cause threat on institutional data security followed by Mobile phones ranked as Number 2(mean=3.75). The study also further discovered that Policies on cyber security (use of social medias e.g. face book) (mean=2.45) was not implemented, Policies on Bring Your Own Device to be used at the Institution (Mean =2.53) was not implemented and Data destruction policies for your Institutional data materials that contain sensitive information (mean=2.52) was not implemented. The following behaviors were ranked top which need to be worked on; usage of secondary storage devices like flash discs, CD, Hard disks (mean=3.88), Sharing of secondary storage devices like flash discs, CD, Hard disks (Mean=3.48) was also frequent and using of personally owned mobile devices to do office work (mean=3.27) was also ranked among the top behaviors.
Blockchain and deep Q-learning for trusted cloud-enabled drone network in smart forestry: A Survey
(Imam Ja’afar Al-Sadiq University, 2025-12-14) Ali, Guma; Wamusi, Robert; Mijwil, Maad M.; Al-Hamzawi, Hassan A. Hameed; Al Sailawi, Ali S. Abed; Salau, Ayodeji Olalekan
The convergence of drone technology, cloud computing, and intelligent decision-making is revolutionizing precision forestry. However, deploying large-scale drone networks in smart forestry faces challenges such as trust, security, data integrity, and autonomous coordination. This survey examines how combining Blockchain technology with deep Q-learning (DQL) can address these issues within cloud-enabled drone networks. Drawing on 102 peer-reviewed sources published between 2022 and 2025 from reputable platforms such as ACM Digital Library, Frontiers, Wiley Online Library, PLoS, Nature, Springer, ScienceDirect, MDPI, IEEE Xplore Digital Library, Taylor & Francis, Sage, and Google Scholar, this work highlights recent advancements in secure and intelligent drone ecosystems. Blockchain provides a decentralized, tamper-resistant framework for validating transactions and securing data exchange among autonomous drones, ensuring the integrity, confidentiality, and authenticity of environmental data. This is critical in forestry, where data manipulation and unauthorized access pose significant risks. Complementing this, DQL enables drones to make autonomous decisions by interpreting real-time environmental data and learning from past experiences, allowing drones to adjust their flight paths, optimize resource utilization, and enhance data collection in dynamic forest environments, such as wildfires or illegal logging operations. Together, Blockchain and DQL create a resilient, scalable architecture that supports secure, real-time, and intelligent forest monitoring. This framework lays the groundwork for developing autonomous and trustworthy drone networks that promote sustainable and climate-smart forestry management.
Blockchain and federated learning in edge-fog-cloud computing environments for smart logistics
(Mesopotamian Academic Press, 2025-07-22) Ali, Guma; Adebo, Thomas; Mijwil, Maad M.; Al-Mahzoum, Kholoud; Sallam, Malik; Salau, Ayodeji Olalekan; Adamopoulos, Ioannis; Bala, Indu; Al-jubori, Aseed Yaseen Rashid
The rapid growth of smart logistics, driven by IoT devices and data-intensive applications, necessitates secure, scalable, and efficient computing frameworks. As the edge-fog-cloud (EFC) paradigm supports real-time data processing, it faces significant security threats and attacks, including privacy risks, data breaches, and unauthorized access. To address these security threats and attacks, blockchain and federated learning (FL) have gained popularity as potential solutions in EFC computing environments for smart logistics. This survey reviews the current landscape in EFC computing environments for smart logistics, highlighting the existing benefits and challenges identified in 134 research studies published between January 2023 and June 2025. The applications of blockchain and FL demonstrate their ability to enhance data security and privacy, improve real-time tracking and monitoring, and ensure inventory and supply chain optimization. Although these technologies offer promising solutions, challenges such as scalability issues, data quality, interoperability and standardization hinder their effective implementation. The survey suggests future research directions focused on developing advanced blockchain and FL, integrating emerging technologies, developing policies and regulations, fostering collaborative research, and ensuring cross-industry adoption and interoperability. Integrating blockchain and FL within the EFC model offers a transformative path toward building secure, intelligent, and resilient logistics systems.
Blockchain and quantum machine learning approach for securing smart water management systems: A Scoping review.
(Peninsula Publishing Press, 2025-09-01) Ali, Guma; Mijwil, Maad M.; Adamopoulo, Ioannis; Dhoska, Klodian
Smart water management systems (SWMS) increasingly rely on Internet of Things (IoT) devices to enhance water distribution, detect leaks, and support sustainable resource use, but this reliance also heightens exposure to cyberattacks, data manipulation, and privacy risks. Conventional security approaches often fall short due to the decentralized design and real-time demands of these systems. This scoping review analyzes 266 studies published between January 2022 and December 2025 to assess how integrating Blockchain and quantum machine learning (QML) can strengthen the security, privacy, and reliability of SWMS. The review examines Blockchain-enabled water management, quantum computing applications, and QML-based security frameworks, using thematic analysis to categorize emerging architectures and challenges. Findings of the focused studies show growing adoption of Blockchain for secure data logging, access control, and tamper-proof auditing. At the same time, QML demonstrates strong potential in anomaly detection, predictive maintenance, and optimizing distribution networks. Although these technologies offer a promising foundation for resilient water infrastructure, most research remains conceptual, with limited real-world deployment or scalability assessments. Integrating Blockchain with QML could create robust, privacy-preserving SWMS frameworks. However, significant barriers persist, including the computational intensity of quantum models, interoperability issues with existing IoT infrastructures, and the absence of standardized protocols. Addressing these gaps is essential for practical implementation. This review underscores the need for scalable hybrid designs, applied validation, and cross-disciplinary standards to advance secure, efficient, and sustainable smart water management solutions.
Chinese generative AI models challenge western AI in clinical chemistry MCQs: A Benchmarking follow-up study on AI use in health education
(Mesopotamian Press, 2025-02-08) Sallam, Malik; Al-Mahzoum, Kholoud; Eid, Huda; Al-Salahat, Khaled; Sallam, Mohammed; Ali, Guma; Mijwil, Maad M.
Background: The emergence of Chinese generative AI (genAI) models, such as DeepSeek and Qwen, has introduced strong competition to Western genAI models. These advancements hold significant potential in healthcare education. However, benchmarking the performance of genAI models in specialized medical disciplines is crucial to assess their strengths and limitations. This study builds on prior research evaluating ChatGPT (GPT-3.5 and GPT-4), Bing, and Bard against human postgraduate students in Medical Laboratory Sciences, now incorporating DeepSeek and Qwen to assess their effectiveness in Clinical Chemistry Multiple-Choice Questions (MCQs). Methods: This study followed the METRICS framework for genAI-based healthcare evaluations, assessing six models using 60 Clinical Chemistry MCQs previously administered to 20 MSc students. The facility index and Bloom’s taxonomy classification were used to benchmark performance. GenAI models included DeepSeek-V3, Qwen 2.5-Max, ChatGPT-4, ChatGPT-3.5, Microsoft Bing, and Google Bard, evaluated in a controlled, non-interactive environment using standardized prompts. Results: The evaluated genAI models showed varying accuracy across Bloom’s taxonomy levels. DeepSeek-V3 (0.92) and ChatGPT-4 (1.00) outperformed humans (0.74) in the Remember category, while Qwen 2.5-Max (0.94) and ChatGPT-4 (0.94) surpassed human performance (0.61) in the Understand category. ChatGPT-4 (+23.25%, p < 0.001), DeepSeek-V3 (+18.25%, p = 0.001), and Qwen 2.5-Max (+18.25%, p = 0.001) significantly outperformed human students. Decision tree analysis identified cognitive category as the strongest predictor of genAI accuracy (p < 0.001), with Chinese AI models performing comparably to ChatGPT-4 in lower-order tasks but exhibiting lower accuracy in higher-order domains. Conclusions: The findings highlighted the growing capabilities of Chinese genAI models in healthcare education, proving that DeepSeek and Qwen can compete with, and in some areas outperform, Western genAI models. However, their relative weakness in higher-order reasoning raises concerns about their ability to fully replace human cognitive processes in clinical decision-making. As genAI becomes increasingly integrated into health education, concerns regarding academic integrity, genAI dependence, and the validity of MCQ-based assessments must be addressed. The study underscores the need for a re-evaluation of medical assessment strategies, ensuring that students develop critical thinking skills rather than relying on genAI for knowledge retrieval.
Comparative analysis of PWM AC choppers with different loads with and without neural network application.
(Wasit Journal of Computer and Mathematics Science, 2023-09) Bounab, Mariem; Ali, Guma
In this paper, we focus on the "Artificial Neural Network (ANN) based PWM-AC chopper". This system is based on the PWM AC chopper-encouraged single-phase induction motor. The main purpose of this paper is to design and implement an ideal technique regarding speed control. Here analyzed PWM-based AC-AC converter with resistive load, R-L load and finally, the PWM AC chopper is fed to single phase induction for speed control. Using other soft computing and optimization techniques such as Artificial Neural Networks, Fuzzy Logic, Convolution algorithm, PSO, and Neuro Fuzzy can control the Speed. We used Artificial Neural Network to control the Speed of the PWM-AC Single phase induction motor drive. The Neural Network toolbox has been further used for getting desired responses. Neural system computer programs are executed in MATLAB. The performance of the proposed method of ANN system of PWM AC Chopper fed single phase induction motor drive is better than other traditional and base methods for controlling the Speed, based on the MOSFET.
A Comprehensive review on cybersecurity issues and their mitigation measures in FinTech
(Al-Iraqia Univeristy, 2024-06-10) Ali, Guma; Mijwil, Maad M.; Buruga, Bosco Apparatus; Abotaleb, Mostafa
The fourth industrial revolution has seen the evolution and wide adoption of game-changing and disruptive innovation, "financial technologies (FinTech), around the globe. However, the security of FinTech systems and networks remains critical. This research paper comprehensively reviews cybersecurity issues and their mitigation measures in FinTech. Four independent researchers reviewed relevant literature from IEEE Xplore, ScienceDirect, Taylor & Francis, Emerald Insight, Springer, SAGE, WILEY, Hindawi, MDPI, ACM, and Google Scholar. The key findings of the analysis identified privacy issues, data breaches, malware attacks, hacking, insider threats, identity theft, social engineering attacks, distributed denial-of-service attacks, cryptojacking, supply chain attacks, advanced persistent threats, zero-day attacks, salami attacks, man-in-the-middle attacks, SQL injection, and brute-force attacks as some of the significant cybersecurity issues experienced by the FinTech industry. The review paper also suggested authentication and access control mechanisms, cryptography, regulatory compliance, intrusion detection and prevention systems, regular data backup, basic security training, big data analytics, use of artificial intelligence and machine learning, FinTech regulatory sandboxes, cloud computing technologies, blockchain technologies, and fraud detection and prevention systems as mitigation measures for cybersecurity issues. However, tackling cybersecurity issues will be paramount if FinTech is to realize its full potential. Ultimately, this research will help develop robust security mechanisms for FinTech systems and networks to achieve sustainable financial inclusion.
Computerized private students’ admission system: a case study of Muni university
(International Journal of Science and Research (IJSR), 2017) Taban, Habibu; Draku, Job
Admission of students into any institution of learning such as Muni University is a core activity. Every academic institution needs students to exist and survive. Thus an admission system of a University needs to be efficient and effective in order to avoid unnecessary delays and losses associated with such delays and inefficiencies. The aim of this paper was undertaken to design and develop the under-graduate Private Students’ Admission System at Muni University. The system targets at quickening and simplifying the process of admitting students into the University on private scheme. The data was mainly collected through interviews and document reviews followed by a design in Unified Modelling Language (UML) to meet the admission system requirements. The system was developed using Python, PHP, HTML, JavaScript and MySQL. The system was tested numerous times with real data by the department of Academic Registrar, Muni University.
Cybersecurity for sustainable smart healthcare: State of the Art, taxonomy, mechanisms, and essential roles
(Mesopotamian Journal of CyberSecurity, 2024-05-23) Ali, Guma; Mijwil, Maad M.
Cutting-edge technologies have been widely employed in healthcare delivery, resulting in transformative advances and promising enhanced patient care, operational efficiency, and resource usage. However, the proliferation of networked devices and data-driven systems has created new cybersecurity threats that jeopardize the integrity, confidentiality, and availability of critical healthcare data. This review paper offers a comprehensive evaluation of the current state of cybersecurity in the context of smart healthcare, presenting a structured taxonomy of its existing cyber threats, mechanisms and essential roles. This study explored cybersecurity and smart healthcare systems (SHSs). It identified and discussed the most pressing cyber threats and attacks that SHSs face, including fake base stations, medjacking, and Sybil attacks. This study examined the security measures deployed to combat cyber threats and attacks in SHSs. These measures include cryptographic-based techniques, digital watermarking, digital steganography, and many others. Patient data protection, the prevention of data breaches, and the maintenance of SHS integrity and availability are some of the roles of cybersecurity in ensuring sustainable smart healthcare. The long-term viability of smart healthcare depends on the constant assessment of cyber risks that harm healthcare providers, patients, and professionals. This review aims to inform policymakers, healthcare practitioners, and technology stakeholders about the critical imperatives and best practices for fostering a secure and resilient smart healthcare ecosystem by synthesizing insights from multidisciplinary perspectives, such as cybersecurity, healthcare management, and sustainability research. Understanding the most recent cybersecurity measures is critical for controlling escalating cyber threats and attacks on SHSs and networks and encouraging intelligent healthcare delivery.
Deep learning-based neural network modeling for economic performance prediction: An empirical study on Iraq
(Peninsula Publishing Press, 2025-02-20) Shaker, Atheel Sabih; Ali, Guma; Wamusi, Robert; Habib, Hassan
This study investigates the application of deep learning-based neural networks for predicting Iraq’s economic performance. Traditional econometric models impose restrictive assumptions that limit their predictive accuracy, especially in volatile economic environments. To overcome these limitations, we propose an artificial neural network (ANN) model trained on six key macroeconomic indicators: Gross Domestic Product (GDP), inflation rate, unemployment rate, exchange rate, trade volume, and government spending. The dataset spans from 2000 to 2023, sourced from authoritative economic institutions. The methodology incorporates feature scaling, hyperparameter tuning, and backpropagation optimization to minimize mean squared error (MSE) and enhance generalization performance. The model is validated through cross-validation and out-of-sample testing. Descriptive statistical analysis highlights the variability of macroeconomic indicators, while the ANN model effectively captures nonlinear dependencies. The results indicate that GDP and government spending are the most influential factors in economic performance prediction, while unemployment rate and exchange rate exhibit lower predictive significance. The model demonstrates superior accuracy compared to traditional regression-based approaches, with minimal error in both training and testing phases. This research contributes to the empirical literature on machine learning in economic forecasting by presenting a robust alternative to conventional predictive models. The findings provide policymakers with valuable insights for designing data-driven economic policies. Future work should explore hybrid models integrating deep learning with traditional econometrics to improve interpretability while maintaining predictive power.

Browse

Browsing Research Articles by Title

Results Per Page

Sort Options