This book discusses an integration of machine learning with metaheuristic techniques that provide more robust and efficient ways to address traditional optimization problems. Modern metaheuristic techniques, along with their main characteristics and recent applications in artificial intelligence, software engineering, data mining, planning and scheduling, logistics and supply chains, are discussed in this book and help global leaders in fast decision making by providing quality solutions to important problems in business, engineering, economics and science. Novel ways are also discovered to attack unsolved problems in software testing and machine learning. The discussion on foundations of optimization and algorithms leads beginners to apply current approaches to optimization problems. The discussed metaheuristic algorithms include genetic algorithms, simulated annealing, ant algorithms, bee algorithms and particle swarm optimization. New developments on metaheuristics attract researchers and practitioners to apply hybrid metaheuristics in real scenarios.
Performance analysis of Heuristic optimization algorithms for Transportation problem.- Source Code Features Based Branch Coverage Prediction using Ensemble Technique.- Implicit Methods of Multi-Factor Authentication.- Comparative Analysis of different Classifiers Using Machine Learning Algorithm for Diabetes Mellitus.- Survey on Machine Learning Techniques for Software Reliability Accuracy Prediction.- Classification of Pest in Tomato Plants using CNN.- Deep Neural Network Approach For Identifying Good Answers in Community Platforms.- Time Series Analysis of SAR-Cov-2 virus in India using Facebooks Prophet.- Model-Based Smoke Testing Approach of Service Oriented Architecture (SOA).- Role of Hybrid Evolutionary Approaches for Feature Selection in Classification: A Review.- Evaluation of Deep Learning Models for Detecting Breast Cancer using Mammograms.- Evaluation of Crol£™