Artificial Intelligence Techniques in Mathematical Modeling and OptimizationEdition 1

Artificial Intelligence Techniques in Mathematical Modeling and Optimization offers a dynamic and comprehensive examination of the intersection between artificial intelligence and mathematical modeling. This edited volume brings together innovative research exploring how AI-driven methods revolutionize traditional approaches to complex optimization problems, enabling enhanced performance, interpretability, and real-world applicability across diverse domains.

Covering foundational and advanced topics, the book introduces readers to machine learning, deep learning, and reinforcement learning as critical tools for modeling high-dimensional, nonlinear, and stochastic systems. Chapters delve into essential aspects like data pre-processing, feature engineering, neural network architectures, swarm intelligence, quantum optimization, and multi-objective decision-making. Emerging techniques such as Fire Hawk Optimization Plus (FHO+), hybrid deep learning-quantum frameworks, and explainable AI (XAI) are discussed in the context of real-world scenarios ranging from energy systems and manufacturing to disaster prediction and healthcare analytics.

This volume uniquely bridges theory and application by integrating algorithmic strategies with case studies on predictive maintenance, renewable energy optimization, cyclone detection, heart disease prediction, and postpartum mental health risk assessment. It also investigates the role of circular economy principles in inventory optimization and examines future trends including neuromorphic computing and ethical AI.

Key Features:

· Systematic exploration of AI-based optimization in mathematical modeling.

· In-depth coverage of ML/DL methods, quantum algorithms, and nature-inspired techniques.

· Practical applications in industrial manufacturing, healthcare, smart energy, and environmental resilience.

· Detailed discussions on model training, generalization, hyperparameter tuning, and overfitting control.

· Includes practical tools such as AutoML, PINNs, CNNs, and quantum convolutional networks.

· Forward-looking insights into sustainable optimization, interpretability, and autonomous AI systems.

This volume is an essential resource for graduate students, researchers, and practitioners in applied mathematics, computer science, engineering, and data-driven optimization, offering the theoretical depth and application-driven clarity needed to tackle modern scientific and engineering challenges through AI-powered modeling and decision systems.