Home      Log In      Contacts      FAQs      INSTICC Portal


The purpose of workshops is to provide a more interactive and focused platform for presenting and discussing new and emerging ideas. The format of paper presentations may include oral presentations, poster presentations, keynote lectures and panels. Depending on the number of presentations, workshops can be scheduled for 1 day or 2 days. All accepted papers will be published in a special section of the conference proceedings book, under an ISBN reference, and on digital support. All papers presented at the conference venue will be available at the SCITEPRESS Digital Library. SCITEPRESS is a member of CrossRef and every paper is given a DOI (Digital Object Identifier). The proceedings are submitted for indexation by SCOPUS, Google Scholar, DBLP, Semantic Scholar, EI and Web of Science / Conference Proceedings Citation Index.


ECDL 2024Workshop on Exploring Evolutionary Computation and Deep Learning for Maritime Management Applications (IJCCI)
Chair(s): Youcef Djenouri, Ahmed Nabil Belbachir, Anis Yazidi and Gautam Srivastava

NIMO 2024Workshop on Nature-Inspired Mechanisms and Operators (IJCCI)
Chair(s): Alexandros Tzanetos and Jakub Kudela

Workshop on
Exploring Evolutionary Computation and Deep Learning for Maritime Management Applications
 - ECDL 2024

Paper Submission: September 20, 2024
Authors Notification: October 4, 2024
Camera Ready and Registration: October 14, 2024


Youcef Djenouri
University of South-Eastern Norway
Ahmed Nabil Belbachir
Norwegian Research Center
Anis Yazidi
Gautam Srivastava
Computer Science, Brandon University

This workshop aims to explore the intersection of evolutionary computation and deep learning within the context of maritime management. Participants will gain insights into how these advanced computational techniques can address complex challenges in the maritime industry, including optimization of shipping routes, predictive maintenance, and vessel tracking. Attendees will learn to apply evolutionary algorithms and deep learning models to real-world maritime problems, fostering innovation and efficiency in maritime operations.

Workshop on
Nature-Inspired Mechanisms and Operators
 - NIMO 2024

Paper Submission: September 20, 2024
Authors Notification: October 4, 2024
Camera Ready and Registration: October 14, 2024


Alexandros Tzanetos
Department of Computing, School of Engineering, Jonkoping University
Jakub Kudela
Brno University of Technology
Czech Republic

Evolutionary Computation (EC) and Swarm Intelligence (SI) offer a variety of approaches to deal with high-complexity real-world problems. Yet, not all algorithms from these fields constitute a novel search strategy. The majority of them replicate the ideas introduced in the established ones, i.e., Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), and Genetic Algorithm (GA) [6]. Moreover, several recently introduced algorithms contain a center-bias operator, making them unsuitable for optimization tasks [3]. Moreover, several other structural biases have been detected in such algorithms [7].

However, some algorithms contain promising mechanisms that can be used to overcome known limitations observed in stochastic nature-inspired algorithms. A recent work’s findings [5] support this idea. The Mine Explosion mechanism (found in the Mine Blast Algorithm) and the Big Bang - Big Crunch mechanism (from the homonymous algorithm) could be incorporated into algorithms with high exploitation ability to enhance their performance through exploration. And there are potentially more such mechanisms that can be found in the various nature-inspired algorithms and have beneficial effects for other methods.

Furthermore, novel operators have been proposed to enhance the algorithms’ performance. For example, fitness-distance balance is a recent selection method that enables the proper determination of candidates with the highest potential to improve the search process [2]. Also, a new set of evolutionary operators was presented in [4].

This Workshop focuses on the research of mechanisms that could be used to modify the algorithmic process of EC and SI algorithms. The aim is to enhance the performance of existing nature-inspired algorithms and overcome well-known drawbacks, such as premature convergence and structural bias. We encourage submissions that study the prospects of existing mechanisms and provide theoretical background on mechanisms or operators explicitly designed for EC and SI algorithms.

This Workshop fully seconds the call-for-action of [1]. Therefore, submissions proposing new metaphor-based algorithms are not encouraged. Meanwhile, the studied mechanisms and operators must be described and investigated using the normal, standard optimization terminology.


[1] Claus Aranha, Christian L Camacho Villalón, Felipe Campelo, Marco Dorigo, Rubén Ruiz, Marc Sevaux, Kenneth Sörensen, and Thomas Stützle. Metaphor-based metaheuristics, a call for action: the elephant in the room. Swarm Intelligence, 16(1):1–6, 2022.
[2] Hamdi Tolga Kahraman, Sefa Aras, and Eyüp Gedikli. Fitness-distance balance (fdb): a new selection method for meta-heuristic search algorithms. Knowledge-Based Systems, 190:105169, 2020.
[3] Jakub Kudela. A critical problem in benchmarking and analysis of evolutionary computation methods. Nature Machine Intelligence, 4(12):1238–1245, 2022.
[4] Bernardo Morales-Castaneda, Oscar Maciel-Castillo, Mario A Navarro, Itzel Aranguren, Arturo Valdivia, Alfonso Ramos-Michel, Diego Oliva, and Salvador Hinojosa. Handling stagnation through diversity analysis: A new set of operators for evolutionary algorithms. In 2022 IEEE Congress on Evolutionary Computation (CEC), pages 1–7. IEEE, 2022.
[5] Marios Thymianis and Alexandros Tzanetos. Is integration of mechanisms a way to enhance a nature-inspired algorithm? Natural Computing, pages 1–21, 2022.
[6] Alexandros Tzanetos. Does the field of nature-inspired computing contribute to achieving lifelike features? Artificial Life, pages 1–25.
[7] Diederick Vermetten, Bas van Stein, Fabio Caraffini, Leandro L Minku, and Anna V Kononova. Bias: a toolbox for benchmarking structural bias in the continuous domain. IEEE Transactions on Evolutionary Computation, 26(6):1380–1393, 2022