Please use this identifier to cite or link to this item:
Title: Temporal Action Analysis in Metaheuristics: A Machine Learning Approach
Authors: Kalatzantonakis, Panagiotis 
Sifaleras, Angelo 
Samaras, Nikolaos 
Author Department Affiliations: Department of Applied Informatics 
Department of Applied Informatics 
Author School Affiliations: School of Information Sciences 
School of Information Sciences 
Keywords: Intelligent Heuristic Decision-Making
Data-Driven Metaheuristic Strategies
Machine Learning Enhanced Combinatorial Optimization
Offline Metaheuristic Algorithm Configuration
Issue Date: 17-Jun-2024
Publisher: Springer
Series/Report no.: Lecture Notes in Computer Science
ISSN: 0302-9743
Volume: 14753
Start page: 365
End page: 370
This study explores the use of Autoregressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM) machine learning models in metaheuristic algorithms, with a focus on a modified General Variable Neighborhood Search (GVNS) for the Capacitated Vehicle Routing Problem (CVRP). We analyze the historical chain of actions in GVNS to demonstrate the predictive potential of these models for guiding future heuristic applications or parameter settings in metaheuristics such as Genetic Algorithms (GA) or Simulated Annealing (SA). This “optimizing the optimizer” approach reveals that, the history of actions in metaheuristics provides valuable insights for predicting and enhancing heuristic selections. Our preliminary findings suggest that machine learning models, using historical data, offer a pathway to more intelligent and data-driven optimization strategies in complex scenarios, marking a significant advancement in the field of combinatorial optimization.
ISBN: 978-3-031-62911-2
DOI: 10.1007/978-3-031-62912-9_34
Rights: Attribution-NonCommercial-NoDerivatives 4.0 Διεθνές
Corresponding Item Departments: Department of Applied Informatics
Department of Applied Informatics
Appears in Collections:Book chapters

Files in This Item:
Show full item record

Page view(s)

checked on Jul 25, 2024


checked on Jul 25, 2024

Google ScholarTM




This item is licensed under a Creative Commons License Creative Commons