### Evolutionary Algorithms and Algorithm Analysis

Research in the field of evolutionary algorithms represented, in a sense, the origin of the HEAL research group. The development of new hybrid evolutionary algorithms, their analysis as well as their application to academic benchmark problems as well as to real world problem situations have been the first main topics of the research group and still represent central interests of the group today.

The strong focus on algorithm development has generated the need for a sophisticated analysis of internal processes of evolutionary algorithms. In particular, for genetic algorithms and genetic programming which are both based primarily on recombination, the dynamics of genetic diversity during the run is essential for successful global convergence behavior by retarding premature convergence. This is accompanied by the desired ability of the algorithms to assemble the properties of very good or even globally optimal solutions, distributed over many candidate solutions, into longer and longer building block sequences that should finally cover an entire chromosome.

Even though new algorithmic flavors developed by HEAL, such as SEGA, SASEGASA, and Offspring Selection, are able to cover a broader range of problem characteristics than standard methods through adaptive behavior, the algorithm selection problem remains a key challenge. The approach mainly followed by the HEAL research group in this context is via fitness landscape analysis (FLA). With the help of FLA, the characteristics of problem instances are specified and, based on this, an assignment to particularly well-suited algorithm instances can be made.

#### Milestones in the Area of Evolutionary Algorithms and Algorithm Analysis

- 2021 and ongoing: Research on
**Secure Prescriptive Analytics** - 2020 and ongoing: Research on
**incremental evaluation**(based on parents) of crossover results in Genetic Algorithms - 2019 and ongoing: Research on
**online diversity control**in Symbolic Regression - 2018 and ongoing: Research on
**concept-drift detection**with Evolutionary Algorithms - 2017 and ongoing: Machine learning meets simulation-based optimization - focus on
**surrogate-assisted modeling** - 2017 and ongoing: Research on
**evolutionary**-based**predictive maintenance**algorithms - 2015 and ongoing: Research on
**Age-layered Population Structures (ALPS)**for global and dynamic optimization - 2015 and ongoing:
**Multi-objective Genetic Programming**for the optimization of interpretability and explainability - 2014 and ongoing: Research on holistic
**optimization networks** - 2013 and ongoing: Research on
**coefficient (constants) optimization**in Genetic Programming-based Symbolic Regression - 2012 and ongoing: Research on genetic lineages for
**genealogy**and building block**analysis**in Genetic Programming - 2011 and ongoing: Focus on
**interpretable**and**explainable AI**with GP-based Symbolic Regression - 2010 and ongoing: Research on
**fitness landscape analysis**(FLA) - 2009 and ongoing: Research on GP-based learning of dispatching rules for dynamic optimization
- 2008 and ongoing: Systematic and integrative research on
**population diversity**analysis - 2008 and ongoing: Research on
**integration of a-priori knowledge**in data-based modeling - 2007: Research on self-adaptive population size adjustment in GAs (
**RAPGA**) - 2007 and ongoing: Research in the field of
**simulation-based optimization** - 2007 and ongoing: Research on
**virtual sensors**with Genetic Programming - 2006 and ongoing: Research on
**Sliding Windows Genetic Programming** - 2005: Deeper analysis of
**Offspring Selection**for panmiptic GAs - 2004 and ongoing: Research on
**Genetic Programming**-based**Symbolic Regression** - 2004:
**HeuristicLab Grid**- HeuristicLab gets parallel - 2003: Development of the
**SASEGASA**algorithm - 2002 and ongoing: Development of the open-source optimization environment
**HeuristicLab** - 2001: Development of the Segregative Genetic Algorithm (
**SEGA**)

#### Selected Projects

- FTI project for
**Secure Prescriptive Analytics** - FWF doc.funds.connect for
**Human Centered AI** **FWF I5315**Machine Learning Methods for Identifying Features of Global Optimization- Josef Ressel Center for Adaptive Optimization in Dynamic Environments (
**adaptOp**) - Josef Ressel Center for Symbolic Regression (
**SymReg**) - Comet K project for Heuristic Optimization in Production and Logistics (
**HOPL**) - Josef Ressel Center for Heuristic Optimization (
**Heureka!**) **FWF L284**GP-based Techniques for the Design of Virtual Sensors

#### Selected Publications

M. Kommenda, B. Burlacu, G. Kronberger, and M. Affenzeller - Parameter identification for symbolic regression using nonlinear least squares - Genetic Programming and Evolvable Machines, vol. 21, no. 3, pp. 471–501, Sep. 2020, ISSN: 1573-7632. DOI: https://doi.org/10.1007/s10710-019-09371-3

B. Burlacu, M. Affenzeller, G. K. Kronberger, M. Kommenda - Online Diversity Control in Symbolic Regression via a Fast Hash-based Tree Similarity Measure - IEEE Transactions on Evolutionary Computation, Wellington, New Zealand, New Zealand, 2019, pp. 2175-2182, DOI: 10.1109/CEC.2019.8790162

A. Beham, S. Wagner, M. Affenzeller - Algorithm selection on generalized quadratic assignment problem landscapes - GECCO '18: Proceedings of the Genetic and Evolutionary Computation Conference, Kyoto, Japan, Japan, 2018, pp. 253-260, DOI: 10.1145/3205455.3205585

B. Burlacu, M. Affenzeller - Schema-based Diversification in Genetic Programming - GECCO '18: Proceedings of the Genetic and Evolutionary Computation Conference, Kyoto, Japan, Japan, 2018, pp. 1111-1118, DOI: 10.1145/3205455.3205594

S. M. Winkler, M. Affenzeller, S. Winkler, G. K. Kronberger, M. Kommenda, P. Fleck - Similarity-based Analysis of Population Dynamics in Genetic Programming Performing Symbolic Regression in Genetic Programming Theory and Practice XIV (Contributions to Book: Part/Chapter/Section 1), (Editors: R. Riolo, B. Worzel, B. Goldman, B. Tozier) - Springer Vieweg, 2018, pp. 1-17, DOI: 10.1007/978-3-319-97088-2_1

B. Burlacu, M. Affenzeller, M. Kommenda, G. K. Kronberger, S. M. Winkler - Schema Analysis in Tree- based Genetic Programming in Genetic Programming in Theory and Practice XV (Contributions to Book: Part/Chapter/Section 2), - Springer International Publishing, 2018, pp. 17-37, DOI: 10.1007/978-3-319-90512-9_2

M. Affenzeller, S. M. Winkler, B. Burlacu, G. K. Kronberger, M. Kommenda, S. Wagner - Dynamic Observation of Genotypic and Phenotypic Diversity for Different Symbolic Regression GP variants - GECCO '17: Proceedings of the Genetic and Evolutionary Computation Conference Companion, Berlin, Germany, Germany, 2017, pp. 1553-1558, DOI: 10.1145/3067695.3082530

A. Beham, M. Affenzeller, S. Wagner - Instance-based Algorithm Selection on Quadratic Assignment Problem Landscapes - GECCO '17: Proceedings of the Genetic and Evolutionary Computation Conference Companion, Berlin, Germany, Germany, 2017, pp. 1471-1478, DOI: 10.1145/3067695.3082513

B. Burlacu, M. Affenzeller, M. Kommenda, G. K. Kronberger, S. M. Winkler - Analysis of Schema Frequencies in Genetic Programming - Lecture Notes in Computer Science 10671, Las Palmas de Gran Canaria, Spain, 2017, pp. 432-438, DOI: 10.1007/978-3-319-74718-7_52

E. Pitzer, M. Affenzeller - Facilitating Evolutionary Algorithm Analysis with Persistent Data Structures - Lecture Notes in Computer Science 10671, Las Palmas de Gran Canaria, Spain, 2017, pp. 416-423, DOI: 10.1007/978-3-319-74718-7_50

A. Beham, E. Pitzer, S. Wagner, M. Affenzeller - Integrating Exploratory Landscape Analysis into Metaheuristic Algorithms - Lecture Notes in Computer Science 10671, Las Palmas de Gran Canaria, Spain, 2017, pp. 473-480, DOI: 10.1007/978-3-319-74718-7_57

M. Affenzeller, B. Burlacu, S. M. Winkler, M. Kommenda, G. K. Kronberger, S. Wagner - Offspring Selection Genetic Algorithm Revisited: Improvements in Efficiency by Early Stopping Criteria in the Evaluation of Unsuccessful Individuals - Lecture Notes in Computer Science 10671, Las Palmas de Gran Canaria, Spain, 2017, pp. 424-431, DOI: 10.1007/978-3-319-74718-7_51

A. Beham, S. Wagner, M. Affenzeller - Optimization Knowledge Center - Companion Publication of the 2016 Genetic and Evolutionary Computation Conference, GECCO'16 Companion, Denver, Colorado, United States of America, 2016, pp. 1331-1338, DOI: 10.1145/2908961.2931724

B. Burlacu, M. Kommenda, M. Affenzeller - Building Blocks Identification Based on Subtree Sample Counts for Genetic Programming - Proceedings of the 3rd Asia-Pacific Conference on Computer Aided System Engineering Conference (APCASE 2015), Quito, Ecuador, Ecuador, 2015, pp. 152-157, DOI: 10.1109/APCASE.2015.34

S. Wagner, M. Affenzeller, A. Scheibenpflug - Automatic Adaption of Operator Probabilities in Genetic Algorithms with Offspring Selection - Lecture Notes in Computer Science LNCS 9520, Las Palmas, Gran Canaria, Spain, 2015, pp. 433-438, DOI: 10.1007/978-3-319-27340-2_54

B. Burlacu, M. Affenzeller, M. Kommenda - On the Effectiveness of Genetic Operations in Symbolic Regression - Lecture Notes in Computer Science LNCS 9520, Las Palmas, Gran Canaria, Spain, 2015, pp. 367-374, DOI: 10.1007/978-3-319-27340-2_46

M. Kommenda, G. K. Kronberger, M. Affenzeller, S. M. Winkler, B. Burlacu - Evolving Simple Symbolic Regression Models by Multi-objective Genetic Programming in Genetic Programming Theory and Practice XIII (Editors: Rick Riolo, William P. Worzel, Mark Kotanchek, Arthur Kordon) - Springer, 2016, pp. 1-19, DOI: 10.1007/978-3-319-34223-8_1

A. Beham, M. Affenzeller, E. Pitzer - Metaheuristic Algorithms for the Quadratic Assignment Problem: Performance and Comparison in Innovative Technologies in Management and Science (Contributions to Book: Part/Chapter/Section 7), (Editors: R. Klempous, J. Nikodem) - Springer Verlag, 2015, pp. 171-190, DOI: 10.1007/978-3-319-12652-4_10

B. Burlacu, M. Affenzeller, S. M. Winkler, M. Kommenda, G. K. Kronberger - Methods for Genealogy and Building Blocks Analysis in Genetic Programming in Computational Intelligence and Efficiency in Engineering Systems (Contributions to Book: Part/Chapter/Section 5), (Editors: G. Borowik, Z. Chaczko, L.G. Ford, W. Jacak, T. Luba) - Springer, 2015, pp. 61-74, DOI: 10.1007/978-3-319-15720-7_5

M. Kommenda, M. Affenzeller, G. K. Kronberger, B. Burlacu, S. M. Winkler - Multi-Population Genetic Programming with Data Migration for Symbolic Regression in Computational Intelligence and Efficiency in Engineering Systems (Contributions to Book: Part/Chapter/Section 6), (Editors: G. Borowik, Z. Chaczko, L.G. Ford, W. Jacak, T. Luba) - Springer, 2015, pp. 75-87, DOI: 10.1007/978-3-319-15720-7_6

S. M. Winkler, M. Affenzeller, G. K. Kronberger, M. Kommenda, B. Burlacu, S. Wagner - Sliding Window Symbolic Regression for Detecting Changes of System Dynamics in Genetic Programming Theory and Practice XII (Contributions to Book: Part/Chapter/Section 6), (Editors: Rick Riolo, William P. Worzel, Mark Kotanchek ) - Springer, 2015, pp. 91-107, DOI: 10.1007/978-3-319-16030-6_6

M. Affenzeller, S. M. Winkler, G. K. Kronberger, M. Kommenda, B. Burlacu, S. Wagner - Gaining Deeper Insights in Symbolic Regression in Genetic Programming Theory and Practice XI (Contributions to Book: Part/Chapter/Section 10), (Editors: Rick Riolo, Jason H. Moore, Mark Kotanchek) - Springer, 2014, pp. 175-190, DOI: 10.1007/978-1-4939-0375-7_10

E. Pitzer, M. Affenzeller - A Comprehensive Survey on Fitness Landscape, In: Recent Advances in Intelligent Engineering Systems (Contributions to Book: Part/Chapter/Section 378), (Editors: János Fodor, Ryszard Klempous, Carmen Paz Suárez Araujo) - Springer Verlag, 2011, pp. 161-191, DOI: 10.1007/978-3-642-23229-9_8

M. Affenzeller, S. Wagner, S. M. Winkler - Self-Adaptive Population Size Adjustment for Genetic Algorithms - LECTURE NOTES IN COMPUTER SCIENCE, Vol. 4739, No. 4739, 2007, pp. 820-828, DOI: 10.1007/978-3-540-75867-9_103

M. Affenzeller, S. Wagner - Offspring Selection: A New Self-Adaptive Selection Scheme for Genetic Algorithms - Adaptive and Natural Computing Algorithms, Coimbra, Portugal, 2005, pp. 218-221, DOI: 10.1007/3-211-27389-1_52

M. Affenzeller, S. Wagner - SASEGASA: A New Generic Parallel Evolutionary Algorithm for Achieving Highest Quality Results - Journal of Heuristics, Vol. 10, No. 3, 2004, pp. 239-263, DOI: 10.1023/B:HEUR.0000026895.72657.a2

Wagner, M. Affenzeller - SexualGA: Gender-Specifc Selection for Genetic Algorithms - Proceedings of the 9th World Multi-Conference on Systemics, Cybernetics and Informatics (WMSCI) 2005, Orlando, United States of America, 2005, pp. 76-81

M. Affenzeller - Segregative Genetic Algorithms (SEGA): A Hybrid Superstructure Upwards Compatible to Genetic Algorithms for Retarding Premature Convergence - The International Journal of Computers, Systems and Signals, Vol. 2, No. 1, 2001, pp. 18-32