Search Results for anomaly-detection
Abstract
Rapid evolution of the Internet of Things (IoT) has transformed the urban infrastructure because it is possible to interconnect systems that can improve transportation, healthcare, security, energy management, and public services. Implementation of IoT network in Iraqi cities faces numerous constraints including lack of infrastructural development, network saturation, unstable connections, poor cybersecurity and lack of resource management. These factors largely affect dependability and functionality of smart city applications. This paper examined how Artificial Intelligence (AI) methods applied to improve IoT network performance in Iraqi cities through effective data routing, predictive maintenance, anomaly detection, bandwidth optimization, and intelligent resource management. Machine learning, Deep Learning and reinforcement learning methods were commonly used methods to address the conditions of dynamic networks and maximize operational efficiency. The study aims at the application of AI techniques to strengthen current IoT systems to enhance scalability, minimize latency, enhance security, and energy efficiency. The research, based on analytical modeling and comparative performance analysis, shows that AI-based IoT systems significantly improve technological resilience of cities and assist Iraq in the development of smart cities. The results offer viable advice to policy makers, network engineers and urban planners who wish to develop modern cities in Iraq using intelligent technology.
Abstract
This research aims to provide a theoretical and applied framework for employing machine learning algorithms in management accounting and costing systems.
The research focuses on the importance of improving resource consumption monitoring, accurately tracking cost behavior, identifying unutilized energy, and supporting decision-making through historical data analysis to enhance the accuracy of production reports.
To achieve the research objective, a descriptive approach was adopted, drawing on available studies. A field study was also used, using a questionnaire to collect data from the research sample (the Electrical Cables and Wires Factory - Ur General Company).
The research also reached a number of conclusions, most notably that employing machine learning algorithms contributes to improving the prediction of quantitative resource consumption, which helps detect deviations and identify their potential causes, and enhances the accuracy and comprehensiveness of production reports.
The research concluded with a set of recommendations, most notably the need to establish an integrated data management system that includes operational data processing to provide real-time solutions and alternatives that contribute to supporting decision-making related to rationalizing resource consumption.
Abstract
This research highlights the critical gap in integrated digital accounting and tax auditing studies concerning complex financial fraud. The problem lies in the inadequacy of traditional auditing to keep pace with digital sophistication and big data. This study aims to analyze the role of intelligent technologies in mitigating fraud and enhancing financial information quality. Adopting a descriptive-analytical approach, a survey was conducted with a purposive sample of 100 experts. The research contribution involves testing the "Fraud Diamond" model using anomaly detection algorithms and continuous auditing. Results revealed a strong positive impact of digital auditing on fraud mitigation (R=0.78), with high predictive power for information quality when mediated by fraud reduction (Sig=0.000). These findings surpass previous studies in risk prediction accuracy. The study benefits society by protecting investor rights and advocating for electronic integration with tax authorities to ensure national economic integrity