Pushing
Toward the Integration Of Artificial Neural Networks
With Genetic Algorithms For Solving Optimization And Control Challenges
Artificial neural networks are a
powerful tool for modeling nonlinear systems and learning from data. Genetic
algorithms have proven effective in various optimization problems, but their
computational complexity has limited the scope of their application in some
applications. This paper presents a hybrid approach to learning and control
that includes an artificial neural network and a genetic algorithm that operate
on different time scales. The network is applied to short-term constraints
while the genetic algorithm is optimized over long-term goals. Artificial
neural networks and genetic algorithms are two powerful computational
paradigms. Recent successes in combining them to solve complex problems have
attracted broad interest in this important topic. The strength of this book
lies in its interdisciplinary contributions from control, signal processing,
and systems perspectives.
Current machine learning techniques
and artificial neural networks, despite their large potential as teaching and
predicting systems, could not outperform when it comes to search and
optimization problems. More integration research between artificial neural
networks modified by genetic algorithms may be needed to solve the challenges
of optimization and control of future intelligent systems. There are still many
challenges that need to be addressed in the integration of artificial neural
networks with genetic algorithms for solving optimization and control
challenges. In particular, issues related to network training and selection, neural
network structure design, genetic algorithm parameterization, and selection are
unresolved. Combining the abilities of artificial neural networks with genetic
algorithms has been successfully used to solve several optimization and control
problems. Even though these two approaches are effective, more research is
needed to determine how well they perform concerning each other. We expect that
continued research on these topics will help us establish more efficient
multi-objective optimization/control frameworks incorporating artificial neural
networks and evolutionary computation approaches.
Artificial neural networks (ANNs)
and genetic algorithms (GA) are becoming increasingly popular tools in solving
complex optimization and control problems. Over the past few years, there has
been a significant effort to integrate artificial neural network techniques
with genetic algorithms for addressing challenging problems, leading to their
increasing interest in applying both methods. This special issue aims to bring
together researchers working on using ANNs and/or GA combined, regardless of
the specific application area or problem type. We welcome work on novel
applications, extensions of existing works, novel representations of existing
problems, and new approaches combining these powerful optimization paradigms.
The potential list of topics includes
but are not limited to:
● Adaptive genetic programming and its
application to multi-objective optimization problems
● Guided selection techniques for
accelerating convergence in GA with neural networks
● Hybridizing genetic algorithms and
neural networks for metaheuristic optimization
● Hybridizing artificial neural
network and metaheuristic methods for solving real-world problems
● Combining ANNs and GAs with other
paradigms such as evolutionary programming, swarm intelligence, or memetic
algorithms.
● New approaches to improve the
performance of both methods by applying them together in various settings.
● Applications of ANNs and GA on
challenging problems with real-world applications
● Decomposition approaches for complex
problems
● Designing appropriate
representations using ANNs, GA, or a combination of both methods
● Using ANNs to improve the efficiency
of genetic algorithms
● Innovative genetic algorithms to
improve the performance of artificial neural networks
● Novelty detection in text, image,
video, audio, and other data types through hybrid algorithms
Tentative Schedule for this Special
Issue:
●
First Submission Deadline 06
September 2024
●
Notification of First Round Decision 25
November 2024
●
Revised Paper Submission Deadline 30
January, 2025
●
Notification of Final Decision 25
March 2025
●
Final Paper Submission Deadline 07May, 2025
Guest Editor Credentials
and Biographical Sketches:
Dr. Alireza Sharifi
Department of Geomatics and Surveying
Engineering,
Faculty of Civil Engineering,
Shahid Rajaee Teacher Training University,
Tehran, Iran
Email ID: alirezsharif3@gmail.com, a_sharifi@sru.ac.ir
Google Scholar Page: https://scholar.google.com/citations?user=Tw2Y-bIAAAAJ&hl=en&oi=sra
---------------------------------------------------------------------------------------------------------------------
Biographical Sketch: Dr. Alireza Sharifi has 17 years of experience in scientific and
technical project development in commercial, academic, and governmental
settings. With graduate degrees in Remote Sensing Engineering, he specializes
in Earth Observation applications but find those methods and tools readily
applicable across a wide range of disciplines. His diverse portfolio of
successful projects and a client-focused problem-solving mindset enable rapid
delivery of cost-effective, targeted, and expandable solutions. Currently, He
is an Associate Professor of Remote Sensing at the Faculty of Civil
Engineering, Shahid Rajaee Teacher Training University, Tehran, Iran.
---------------------------------------------------------------------------------------------------------------------
Dr. Hadi
Mahdipour
Department of Electrical Engineering, Oviedo,
Asturias, Spain
Email ID: mahdipourhadi@uniovi.es
Google Scholar Page: https://scholar.google.com/citations?user=slWcDtoAAAAJ&hl=en
---------------------------------------------------------------------------------------------------------------------
Biographical Sketch: Dr. Hadi Mahdipour
is a Researcher at the University of Oviedo, Spain, specializing in concealed
objects detection through the utilization of AI- and ML-assisted
millimeter-wave systems. He received his Ph.D. in Electrical Engineering with a
focus on Communication-Systems from Ferdowsi University of Mashhad, Iran, in
2015. Following seven years of experience in the electrical and communication
industries, he served as an Assistant Professor in the Marine Electronics &
Communication Engineering Group within the Marine Engineering Department at Khoramshahr Marine Science and Technology University,
Khorramshahr, Iran, from 2015 to 2017. Subsequently, he assumed the role of
Assistant Professor in the Electrical Engineering Group at Esfarayen
University of Technology, Esfarayen, Iran, from 2017
to 2020. In 2020, Mahdipour transitioned to the role
of a Postdoctoral Researcher at the University of Carlos III Madrid, Spain,
where he contributed to cutting-edge research in his field. Following this, he
took on the position of Researcher Associate and Technical Manager at Sinenta Co., Spain, from 2021 to 2023. His research
interests encompass a broad spectrum, including Artificial Intelligence,
Machine Learning, Signal Processing, Image Processing, Audio and Video
Processing, Telecommunication, and Applied Machine Learning and Artificial
Intelligence in domains such as bioinformatics, remote sensing, and food
science. His professional trajectory includes extensive collaboration with
industry partners, and he has successfully executed numerous projects from 2008
to the present. Furthermore, he has authored and published numerous papers in
top-tier conferences and journals, contributing significantly to various areas
of interest within his field.
---------------------------------------------------------------------------------------------------------------------
Dr. Khilola
Amankulova
Department of Geoinformatics,
Physical and Environmental Geography,
University of Szeged, Szeged, Hungary
Email: amankulova.khilola@stud.u-szeged.hu
Researchgate: https://www.researchgate.net/profile/Khilola-Amankulova
---------------------------------------------------------------------------------------------------------------------
Biographical Sketch: Dr. Khilola Amankulova
received the B.S. degree in land management and land cadastre
from the Department of Land use and Land Cadastre, in
2018, and the M.S. degree in geodesy and geoinformations from the Department of
Geodesy and Geoinformatics, Tashkent Institute of Irrigation and Agricultural
Mechanization Engineers, Tashkent, Uzbekistan. She is currently working toward
the Ph.D. degree with the Department of Geo informatics, Physical and
Environmental Geography, University of Szeged, Szeged, Hungary. Her research
focuses on remote sensing, precision agriculture, and geoinformatics.
---------------------------------------------------------------------------------------------------------------------