Evolutionary Algorithms and Their Real-World Applications

Dear Colleagues,

Evolutionary algorithms have been successfully used to address complex real-world problems. For a large set of domains, they can calculate or approximate solutions within a reasonable time. There exist many successful optimization applications that are drawn from the field of genetic algorithms, especially in combinatorial optimization applications, as well as from the need to evolve patterns and structures. These have highly multimodal search landscapes. Evolution strategies often show their strengths in terms of efficiency and adaptability in parameter optimization problems, such as in the issue of simulation-based optimization. Genetic programming, especially symbolic regression applications based on tree-based representation, is becoming increasingly important in the field of explainable and interpretable AI due to its unique ability to learn complex relationships in an interpretable form.

A current drawback of the evolutionary algorithms applied in the real-world is their tendency to be very domain-specific and to suffer from a high problem dependency, based on the no-free-lunch theorem. In order to overcome these limitations and enhance the efficiency and applicability of evolutionary algorithms in real-world scenarios, several approaches have been suggested, leading to the design of self-adaptive algorithms. These suggested methods including the extension of basic algorithms through the analysis of the topology and features of search spaces. Hybridization, local search, and specialized operators are also promising approaches that could lead to the development of even more efficient algorithms in terms of computational effort and solution quality. Moreover, the recent improvement in computational power and the successful implementation of advanced parallel and grid computing concepts have improved the efficiency of solving these problems.

This Special Issue aims to present the latest advances in the real-world applications of evolutionary algorithms. The scope of this Issue encompasses a broad range of topics, including new theoretical developments, innovative techniques, novel applications, and real-world optimization benchmarks, both with and without constraints. Suggested topics for papers include, but are not limited to:

• Theory and applications of genetic algorithms, evolution strategies and genetic programming;
• Hybrid approaches to real-world applications;
• Surrogate-assisted optimization and Bayesian optimization
• Multi-fidelity optimization;
• Simulation-based and evolutionary optimization;
• Application of simulation-based soft computing;
• Applications in combinatorial optimization, bio- and medical informatics, networks and telecommunications, logistics, scheduling, and transportation prescriptive analytics.

Dr. Michael Affenzeller
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. Applied Sciences 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 2400 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.

Title: Symbolic Regression on Dynamic Training Data with Genetic Programming Variants
Authors: Philipp Fleck; Michael Affenzeller
Affiliation: Heuristic and Evolutionary Algorithms Laboratory (HEAL), University of Applied Sciences Upper Austria—Campus Hagenberg, Softwarepark 11, 4232 Hagenberg, Austria
Abstract: In real-world applications, data is generated dynamically, requiring monitoring and regular retraining of machine learning models over the lifetime of an application. Frequent retraining can be costly, especially if the training algorithm starts from scratch. Genetic programming (GP) may be able to maintain the necessary diversity in its population to continuously evolve new models on the changing data without a complete reset. Therefore, we evaluate how well standard GP copes with dynamically changing training data and investigate which variants of GP may be better suited for continuous training on dynamic data, for example by using an age-layered population structure (ALPS).

Title: Data Driven Modelling of Differential Equations for Dynamical Systems: An Overview
Authors: David Jödicke
Affiliation: University of Applied Sciences Upper Austria, School of Informatics, Communications and Media, Hagenberg, Austria
Abstract: The paper elucidates the nature of dynamical problems, characterized by complex and evolving systems through differential equations. It introduces a comprehensive benchmark problem database, facilitating rigorous evaluation and comparison of algorithms designed to tackle such dynamic challenges. Preliminary findings showcase the performance of state-of-the-art algorithms, showing their efficacy in finding solutions of dynamical systems.

Title: Evolutionary Grid Optimization and Deep Learning for Improved In Vitro Cellular Spheroid Localization
Authors: Andreas Haghofer; Jonas Schurr*; Hannah Janout; Marian Fürsatz; Josef Scharinger; and Stephan Winkler; Sylvia Nürnberger
Affiliation: University of Applied Sciences Upper Austria, School of Informatics, Communications and Media