Theory and Applications of Swarm Intelligence Optimization and Machine Learning

TOPICAL COLLECTIONS

Guest Editors

Jiankai Xue

School of Computer Science and Technology, Anhui University of Technology

Dr. Jiankai Xue earned his MSc and PhD degrees from the College of Information Sciences and Technology at Donghua University in Shanghai, China, in 2020 and 2024, respectively. He is currently affiliated with the School of Computer Science and Technology at Anhui University of Technology. He was included in the 2024 Stanford-Elsevier list of the world's top 2% of scientists. Dr. Xue is an active reviewer for many international journals. His primary research focus is swarm intelligence optimization, encompassing the design and improvement of bio-inspired algorithms, their theoretical analysis, and practical applications in complex optimization problems. These include industrial scheduling, resource allocation, and machine learning parameter tuning.

Chenglong Zhang

The Chinese University of Hong Kong, Shenzhen

Dr. Chenglong Zhang received his BSc degree from Qufu Normal University, China, in 2014, his MSc degree from Guizhou University, China, in 2017, and his PhD degree from the School of Computer Science and Technology, China University of Mining and Technology, in 2023. He is currently a postdoctoral fellow at the Chinese University of Hong Kong, Shenzhen, and the University of Science and Technology of China. His main research interests include randomized neural networks, deep stochastic configuration networks, particle swarm optimization algorithm, and medical biometrics. He has published more than 30 papers in international conferences and journals.

Collection Overview

Swarm intelligence optimization algorithms, such as particle swarm optimization (PSO), ant colony optimization (ACO), artificial bee colony (ABC), and sparrow search algorithm (SSA), provide flexible and robust solutions for complex optimization problems. These algorithms effectively handle high-dimensional, nonlinear, and dynamic optimization tasks. Over the last few decades, as the complexity of problems increases, the need for optimization techniques has become more evident than before. Therefore, in-depth study of the swarm intelligent optimization algorithms is of great practical signiﬁcance and theoretical value.

Machine learning models often involve complex optimization processes such as hyperparameter tuning, feature selection, and weight optimization. These processes face challenges like high-dimensional search spaces, non-convex objective functions, and the risk of falling into local optima, where traditional gradient-based methods may struggle to achieve satisfactory results.

In this context, the importance of swarm intelligence optimization algorithms is becoming increasingly recognized in machine learning. This collection aims to consolidate cutting-edge research on these algorithms, providing a comprehensive resource that highlights best practices and showcases innovative applications. It will empower the research community to adopt, adapt, and advance these tools more effectively, accelerating progress in both theoretical understanding and practical implementations across various fields.