Abstract
Intelligent systems have become indispensable in the modern era, transforming industries and revolutionizing fields such as energy management, smart cities, healthcare, and cultural heritage preservation. Over recent decades, advancements in IoT, artificial intelligence, and computational architectures have unlocked unprecedented opportunities for innovation. However, these advancements come with significant challenges, including ensuring seamless interoperability among heterogeneous devices, managing and processing vast amounts of data efficiently, and maintaining robust real-time performance in dynamic, resource-constrained environments. Central questions include how to design systems that can adapt to varying operational demands, optimize resource allocation, and ensure fault tolerance while balancing scalability and energy efficiency. This research addresses these questions by proposing innovative solutions that enhance the performance and adaptability of intelligent systems across ...
Intelligent systems have become indispensable in the modern era, transforming industries and revolutionizing fields such as energy management, smart cities, healthcare, and cultural heritage preservation. Over recent decades, advancements in IoT, artificial intelligence, and computational architectures have unlocked unprecedented opportunities for innovation. However, these advancements come with significant challenges, including ensuring seamless interoperability among heterogeneous devices, managing and processing vast amounts of data efficiently, and maintaining robust real-time performance in dynamic, resource-constrained environments. Central questions include how to design systems that can adapt to varying operational demands, optimize resource allocation, and ensure fault tolerance while balancing scalability and energy efficiency. This research addresses these questions by proposing innovative solutions that enhance the performance and adaptability of intelligent systems across diverse applications. At the core of this study are advanced optimization techniques and innovative architectural frameworks designed to meet the demands of modern intelligent systems. Key contributions include the integration of predictive analytics and federated learning, enabling dynamic resource allocation and real-time data processing. These methodologies enhance system responsiveness integrating Artificial Intelligence while maintaining energy efficiency, even in complex IoT ecosystems. Architectural innovations, including hybrid (cloud-edge) frameworks, demonstrate how scalability and flexibility can be achieved without compromising system’s performance. Together, these contributions provide a cohesive foundation for intelligent systems that are robust, adaptable, and capable of addressing the challenges posed by diverse operational environments. The proposed frameworks and techniques were validated through a rigorous combination of experimental analysis and real-world case studies. Experimental results demonstrated significant improvements across critical metrics, including reduced latency, optimized resource utilization, enhanced fault tolerance, and increased energy efficiency. The case studies, drawn from diverse domains such as building management systems, smart cities, and cultural heritage documentation, demonstrated the scalability and replicability of these solutions. By tailoring the frameworks to sector-specific requirements, the research underscores their versatility and practical relevance, paving the way for their adoption across multiple industries. The findings of this research have profound implications for the development and deployment of intelligent systems. By addressing fundamental challenges such as scalability, interoperability, and energy efficiency, the proposed solutions advance the state of the art while providing actionable insights for future research. These contributions establish a pathway for the design of intelligent systems that are not only technically robust but also scalable and compliant with regulatory standards. This thesis also identifies emerging opportunities for innovation, including advanced security measures, the integration of more sophisticated AI models, and the expansion of these frameworks to address new domains such as autonomous systems and next-generation IoT applications. In conclusion, this thesis bridges the gap between theoretical advancements and practical implementation, offering transformative contributions to the field of intelligent systems. By addressing critical research questions and delivering robust, adaptable solutions, it provides a comprehensive framework for the development of intelligent systems capable of driving innovation across diverse sectors. The findings demonstrate the potential of these systems to enhance efficiency, scalability, and reliability, creating a solid foundation for future exploration and real-world application in an increasingly interconnected and dynamic global landscape.
show more
