Exploring Multi-Objective Hyper-Heuristics in the context of Sustainable Transformation

Summary

Sustainable transformation requires a comprehensive remodelling of our processes and systems to ensure environmental, social, and economic viability. However, solutions for each of these axes can sometimes conflict with one another. This presents a particular type of challenge known as multi-objective optimization problems (MOPs), where multiple, often conflicting, objective functions need to be optimized concurrently. A primary method for addressing complex MOPs is the use of multi-objective evolutionary algorithms (MOEAs). Despite their widespread success, MOEAs struggle with issues such as irregular geometries in the criteria space, diversity preservation, slow convergence, and efficiently handling more than three objectives. An alternative approach to dealing with these challenges involves combining the strengths of various multi-objective techniques into one framework through hyper-heuristic approaches.

This special session aims to explore novel integrations of hyper-heuristics and evolutionary multi-objective computation approaches, specifically focusing on applications for sustainable transformation. We aim to delve into the challenges and opportunities of leveraging hyper-heuristics and evolutionary multi-objective computation for solving complex multi-objective optimization problems in areas such as environmental engineering, transportation, energy, and smart cities. Researchers, academics, and practitioners at the intersection of hyper-heuristics, evolutionary computation, and sustainability are invited to contribute novel methodologies, applications, and theoretical advancements to this impactful research domain.

Call for Papers

We welcome original submissions on all aspects of novel designs, developments, or hybridizations of multi-objective hyper-heuristic approaches addressing the following sustainable transformation-related challenges:

• Electric Vehicle Fleet Optimization
• Water Distribution Optimization
• Waste Management Optimization
• Renewable Energy Planning
• Green Supply Chain Logistics
• Low-carbon Emission Routing
• Resource-efficient Manufacturing
• Urban Mobility Planning
• Telecommunication Network Design
• Healthcare Resource Allocation

[ IEEE WCCI 2024 – Call for Papers ]

Important Dates

• January 29, 2024 – Paper Submission Deadline
• March 15, 2024 – Paper Acceptance Notification
• May 1, 2024 – Camera-ready submission & Early Registration Deadline
• June 30 – July 5, 2024 – IEEE WCCI 2024

Organizers

Biographies

Julio Juárez is a Posdoctoral Research Fellow with the Research Group on Advanced Artificial Intelligence at Tecnologico de Monterrey. He obtained his bachelor of engineering at Universidad del Caribe, Cancún, in 2012, and his MSc and PhD in computer science at CICESE research center, in 2015 and 2022, respectively. He is a candidate member to the Mexican National System of Researchers. His research interests are algorithms for search and optimization, including evolutionary multi-objective optimization, and artificial intelligence. He is also interested in interdisciplinary research ranging from scheduling and routing problems in robotics, to team formation in management and engineering, to data science for oceanography and molecular biology.

Gerardo Ibarra-Vazquez is a Postdoctoral Researcher in the Research Group on Advanced Artificial Intelligence at the Tecnologico de Monterrey, Mexico. Ph.D in Computer Science from the Universidad Autónoma de San Luis Potosí. He is a candidate member to the Mexican National System of Researchers. His research interests are robustness evaluation of image classification models, adversarial attacks in deep learning, deep learning in image processing, evolutionary algorithms for image classification, saliency object detection, and interest point detectors.

Jesús Guillermo Falcón-Cardona received Ph.D. In Computer Science from CINVESTAV-IPN, Mexico in 2020. He is a Research Professor in the Research Group on Advanced Artificial Intelligence at Tecnológico de Monterrey, México. He is also a member of the Mexican National System of Researchers, IEEE, and the Mexican Academy of Computing. Dr. Falcón is passionate about conducting research on bio-inspired metaheuristics to address single- and multi-objective optimization problems. He specializes in designing indicator-based multi-objective evolutionary algorithms.

Jorge M. Cruz-Duarte is a Research Professor in the Research Group on Advanced Artificial Intelligence at the Tecnologico de Monterrey, Mexico. He is also a member of the Mexican National System of Researchers (SNI-CONACyT), IEEE, and the Mexican Academy of Computer Sciences (AMEXCOMP). Prof. Cruz-Duarte is also a reviewer of several scientific journals, including ASOC, SWEVO, ATE, IEEE Access, and Mathematical Reviews. His research interests include Automatic Design, Heuristic Methods, Fractional Calculus, Applied Thermodynamics, Data Science, and Artificial Intelligence.