Predrag S. Stanimirović – författare

This book presents the proceedings of the 6th EAI International Conference on Robotics and Networks 2022 (ROSENET 2022). The conference explores the integration of networks and robotic technologies, which has become a topic of increasing interest for both researchers and developers from academic fields and industries worldwide. The authors posit that big networks will be the main approach to the next generation of robotic research, with the explosive number of networks models and increasing computational power of computers significantly extending the number of potential applications for robotic technologies while also bringing new challenges to the networking community. The conference provided a platform for researchers to share up-to-date scientific achievements in this field. The conference took place at Swansea University, Wales, Great Britain.

This book presents the proceedings of the 6th EAI International Conference on Robotics and Networks 2022 (ROSENET 2022). The conference explores the integration of networks and robotic technologies, which has become a topic of increasing interest for both researchers and developers from academic fields and industries worldwide. The authors posit that big networks will be the main approach to the next generation of robotic research, with the explosive number of networks models and increasing computational power of computers significantly extending the number of potential applications for robotic technologies while also bringing new challenges to the networking community. The conference provided a platform for researchers to share up-to-date scientific achievements in this field. The conference took place at Swansea University, Wales, Great Britain.

Delivering innovative methods for addressing complex systems, this book presents the latest advances in hybrid modeling, machine learning, and digital technologies. Based on selected papers from the III International Workshop “Hybrid Methods of Modeling and Optimization in Complex Systems” held December 2–4, 2024, in Krasnoyarsk, Russia, the book covers hybrid modeling and optimization, intelligent data analysis, financial forecasting, industrial and educational digitalization, AI-guided decision support, and digital system security. Readers will find such interdisciplinary applications as climate project modeling, agricultural digital services, and the digital platform economy; e-learning analysis and digital competence development; digital twins and production optimization; as well as research on network systems. It is essential for researchers, practitioners, and educators seeking practical solutions and advanced hybrid methods for diverse scientific and engineering challenges.

This book presents a comprehensive exploration of the dynamical system approach in numerical linear algebra, with a special focus on computing generalized inverses, solving systems of linear equations, and addressing linear matrix equations. Bridging four major scientific domains—numerical linear algebra, recurrent neural networks (RNNs), dynamical systems, and unconstrained nonlinear optimization—this book offers a unique, interdisciplinary perspective.Generalized Matrix Inversion: A Machine Learning Approach explores the theory and application of recurrent neural networks, particularly continuous-time recurrent neural networks (CTRNNs), which use systems of ordinary differential equations to model the influence of inputs on neurons. Special attention is given to CTRNNs designed for finding zeros of equations or minimizing nonlinear functions, with detailed coverage of two important classes: Gradient Neural Networks (GNN) and Zhang (Zeroing) Neural Networks (ZNN). Both time-varying and time-invariant models are examined across scalar, vector, and matrix cases.Based on the authors’ research that has been published in leading scientific journals, the book spans a variety of disciplines, including linear and multilinear algebra, generalized inverses, recurrent neural networks, dynamical systems, time-varying problem solving, and unconstrained nonlinear optimization. Readers will find a global overview of activation functions, rigorous convergence analysis, and innovative improvements in the definition of error functions for GNN and ZNN dynamic systems.Generalized Matrix Inversion: A Machine Learning Approach is an essential resource for researchers and practitioners seeking advanced methods at the intersection of machine learning, optimization, and matrix computation.

This book presents a comprehensive exploration of the dynamical system approach in numerical linear algebra, with a special focus on computing generalized inverses, solving systems of linear equations, and addressing linear matrix equations. Bridging four major scientific domains—numerical linear algebra, recurrent neural networks (RNNs), dynamical systems, and unconstrained nonlinear optimization—this book offers a unique, interdisciplinary perspective. Generalized Matrix Inversion: A Machine Learning Approach explores the theory and application of recurrent neural networks, particularly continuous-time recurrent neural networks (CTRNNs), which use systems of ordinary differential equations to model the influence of inputs on neurons. Special attention is given to CTRNNs designed for finding zeros of equations or minimizing nonlinear functions, with detailed coverage of two important classes: Gradient Neural Networks (GNN) and Zhang (Zeroing) Neural Networks (ZNN). Both time-varying and time-invariant models are examined across scalar, vector, and matrix cases. Based on the authors’ research that has been published in leading scientific journals, the book spans a variety of disciplines, including linear and multilinear algebra, generalized inverses, recurrent neural networks, dynamical systems, time-varying problem solving, and unconstrained nonlinear optimization. Readers will find a global overview of activation functions, rigorous convergence analysis, and innovative improvements in the definition of error functions for GNN and ZNN dynamic systems. Generalized Matrix Inversion: A Machine Learning Approach is an essential resource for researchers and practitioners seeking advanced methods at the intersection of machine learning, optimization, and matrix computation.

This volume presents selected papers from the IV International Workshop on Hybrid Methods of Modeling and Optimization in Complex Systems, introducing hybrid methodologies integrating mathematical modeling, machine learning, and intelligent optimization to enhance prediction, analysis, and decision-making. The volume covers hybrid modeling and optimization, AI-driven monitoring systems, cybersecurity and data protection, blockchain infrastructures, logistics and manufacturing integration, as well as advances in data mining, recommender systems, reinforcement learning, pattern recognition, and adaptive intelligence using evolutionary algorithms and neural networks. Combining theoretical advances with applied case studies, the book demonstrates how hybrid methods improve predictive accuracy, system efficiency, and intelligent decision support. It is intended for researchers, engineers, data scientists, and graduate students working with complex systems and artificial intelligence.

This volume presents selected papers from the IV International Workshop on Hybrid Methods of Modeling and Optimization in Complex Systems, introducing hybrid methodologies integrating mathematical modeling, machine learning, and intelligent optimization to enhance prediction, analysis, and decision-making. The volume covers hybrid modeling and optimization, AI-driven monitoring systems, cybersecurity and data protection, blockchain infrastructures, logistics and manufacturing integration, as well as advances in data mining, recommender systems, reinforcement learning, pattern recognition, and adaptive intelligence using evolutionary algorithms and neural networks. Combining theoretical advances with applied case studies, the book demonstrates how hybrid methods improve predictive accuracy, system efficiency, and intelligent decision support. It is intended for researchers, engineers, data scientists, and graduate students working with complex systems and artificial intelligence.

This book provides a comprehensive overview of the latest breakthroughs and research trends in applied physics and mathematics, as presented at the IV International Conference on Advances in Applied Physics and Mathematics-2026. Designed to bridge the gap between theoretical innovation and real-world application, it brings together leading experts to address critical challenges in energy, environment, materials, and computational science. Covering six major topics, this book delves into the application of physics and mathematics in energy systems, highlighting advancements in renewable energy technologies, energy storage, and the optimization of energy networks for greater efficiency and sustainability. It explores environmental physics and mathematical modeling, offering insights into climate dynamics, pollution dispersion, and ecosystem analysis using advanced mathematical and computational tools. The section on applied physics in earth sciences and resource management examines seismic imaging, remote sensing, and the optimization of mineral and water resources, providing essential knowledge for sustainable development. This book also features a dedicated chapter on computational physics and mathematical methods, showcasing state-of-the-art numerical techniques, algorithm development, and high-performance computing for solving complex physical problems, including simulations of fluid dynamics and quantum systems. In the realm of advanced materials, electromagnetic, and optical physics, readers find the latest research on nanomaterials, metamaterials, photonic devices, and plasmonics, with a focus on both experimental and theoretical approaches to material characterization and device fabrication. The final chapter investigates physical phenomena in materials and environmental systems, integrating experimental findings with mathematical modeling to deepen understanding of phase transitions, transport phenomena, and environmental interactions. By addressing pressing scientific and technological issues, this book aims to foster interdisciplinary collaboration and inspire innovative solutions to global challenges.

This volume presents selected papers from the IV International Workshop on Hybrid Methods of Modeling and Optimization in Complex Systems, focusing on interdisciplinary advances in hybrid modeling, artificial intelligence, optimization, and digital technologies for complex problem solving. The volume explores hybrid optimization techniques, transfer learning, fuzzy systems, cyber-physical systems, AI-driven economic and industrial applications, digital transformation, sustainable development, BIM and digital twins, intelligent forecasting, and decision-support systems. It also covers data mining, machine learning, multimodal analysis, semantic search, financial and medical data processing, as well as domain-specific applications in architecture, environmental engineering, forestry, and industrial systems. Combining theoretical developments with practical implementations, the book demonstrates how hybrid methodologies improve analytical accuracy, system adaptability, and intelligent decision-making across scientific, technological, and economic domains. It is intended for researchers, engineers, practitioners, and graduate students working in complex systems, artificial intelligence, and interdisciplinary modeling.

This book features selected papers from the 9th International Conference on Mathematics and Computing (ICMC 2023), organized at BITS Pilani K. K. Birla Goa Campus, India, during 6–8 January 2023. It covers recent advances in the field of mathematics, statistics, and scientific computing. The book presents innovative work by leading academics, researchers, and experts from industry in mathematics, statistics, cryptography, network security, cybersecurity, machine learning, data analytics, and blockchain technology in computer science and information technology.