Advanced Computational Intelligence for Complex Problems

Dear Colleagues,

The rapid evolution of computational intelligence (CI) has revolutionized problem-solving in domains characterized by uncertainty, nonlinearity, and high-dimensional data. This Special Issue aims to highlight cutting-edge advancements in CI methodologies, including evolutionary algorithms, fuzzy systems, neural networks, deep learning, and hybrid models, that address the challenges of complex real-world problems.

We invite researchers to submit original studies that bridge theoretical innovation with practical applications. Topics of interest include, but are not limited to, the following:

• Evolutionary and swarm-based optimization for complex problems (e.g., multi-objective, dynamic, large-scale, expensive, multi-task, constrained, multi-level optimization);
• Deep neural architectures (e.g., transformers, CNNs, and GANs) and learning methods for complex learning tasks and complex systems;
• Fuzzy logic and rule-based systems in decision-making under uncertainty;
• Hybrid CI methods such as symbolic reasoning, metaheuristics, and machine learning for complex problem-solving (e.g., LLM, automated design, generative AI, and cognitive systems);
• Application studies in various fields (e.g., transportation, healthcare, autonomous systems, scheduling, manufacturing, design, energy management, and climate modelling).

This Special Issue aims to foster interdisciplinary collaboration, highlighting how CI techniques can yield innovative solutions to complex problems. Interdisciplinary studies integrating domain-specific knowledge (e.g., physics-informed neural networks, bio-inspired optimization) are also encouraged. The central scientific questions guiding this Special Issue include the following: How can CI methodologies be advanced to more effectively solve complex real-world problems? What theoretical innovations are needed to bridge the gap between CI techniques and practical applications? And how can interdisciplinary approaches enhance the efficiency, robustness, and scalability of CI solutions?

Dr. Jian-Yu Li
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• computational intelligence
• evolutionary computation
• fuzzy systems
• machine learning
• deep learning
• deep neural networks
• swarm intelligence
• complex optimization
• hybrid intelligent models
• large language models
• real-world applications