Supported by IEEE CIS ISATC Task Force on Transfer Learning and Transfer Optimization
Memetic Computing (MC) represents a broad generic framework using the notion of meme(s) as units of
information encoded in computational representations for the purpose of problem-solving. In the
literature, MC has been successfully manifested as memetic algorithm, where meme has been typically
perceived as individual learning procedures, adaptive improvement procedures or local search
operators that enhance the capability of population based search algorithms. More recently, novel
manifestations of meme in the forms such as knowledge building-block, decision tree, artificial
neural works, fuzzy system, graphs, etc., have also been proposed for efficient problem-solving.
These meme-inspired algorithms, frameworks and paradigms have demonstrated with considerable success
in various real-world applications.
The aim of this special session on memetic computing is to provide a forum for researchers in this field to exchange the latest advances in theories, technologies, and practice of memetic computing. The scope of this special session covers, but is not limited to:
Supported by IEEE CIS ECTC Task Force on Data-Driven Evolutionary Optimization of Expensive Problems
Meta-heuristic algorithms, including evolutionary algorithms and swarm optimization, face challenges
when solving time-consuming problems, as typically these approaches require thousands of function
evaluations to arrive at solutions that are of reasonable quality. Surrogate models, which are
computationally cheap, have in recent years gained in popularity in assisting meta-heuristic
optimization, by replacing the compute-expense/time-expensive problem during phases of the heuristic
search. However, due to the curse of dimensionality, it is very difficult, if not impossible to
train accurate surrogate models. Thus, appropriate model management techniques, memetic strategies
and other schemes are often indispensable. In addition, modern data analytics involving advance
sampling techniques and learning techniques such as semi-supervised learning, transfer learning and
active learning are highly beneficial for speeding up evolutionary search while bringing new
insights into the problems of interest. This special session aims at bringing together researchers
from both academia and industry to explore future directions in this field.
The topics of this special issue include but are not limited to the following topics:
Supported by IEEE CIS ISATC Task Force on Hyper-Heuristics
Computational intelligence systems play an imperative role in solving real world complex problems in
industry. These systems have contributed to many facets of industry including data mining,
transportation, health systems, computer vision, computer security, robotics, software engineering
scheduling, and amongst others. Computational intelligence systems employ one or more computational
intelligence techniques such as neural networks, fuzzy logic, genetic algorithms, multi-agent
approaches and rule-based systems. Implementation of these techniques require a number of design
decisions to be made, e.g. what architecture to use, what parameter values to use, and derivation of
problem specific operators. It may also be necessary to employ a hybrid system combining techniques
to solve a problem. This makes the development of computational systems time consuming, requiring
extensive expertise, and many man hours. Consequently, there have been a number of initiatives to
automate these processes.
There has been a fair amount of research into parameter tuning and control, automating neural network architecture design, inducing fuzzy functions, rule-based systems and multi-agent architectures, amongst others. The aim of this special session is to examine recent developments in the field and future directions including the challenges and how these can be overcome.
The topics covered include, but are not limited to, the use of EC for the following:
Supported by IEEE CIS Games Technical Committee
Games are an ideal domain to study computational intelligence (CI) methods because they provide
affordable, competitive, dynamic, reproducible environments suitable for testing new search
algorithms, pattern-based evaluation methods, or learning concepts. Games scale from simple problems
for developing algorithms to incredibly hard problems for testing algorithms to the limit. They are
also interesting to observe, fun to play, and very attractive to students. Additionally, there is
great potential for CI methods to improve the design and development of both computer games as well
as tabletop games, board games, and puzzles. This special session aims at gathering leaders and
neophytes in games research as well as practitioners in this field who research applications of
computational intelligence methods to computer games.
In general, papers are welcome that consider all kinds of applications of methods (evolutionary computation, supervised learning, unsupervised learning, fuzzy systems, game-tree search, rolling horizon algorithms, MCTS, etc.) to games (card games, board games, mathematical games, action games, strategy games, role-playing games, arcade games, serious games, etc.).
Examples include but are not limited to:
Supported by IEEE CIS ETTC Task Force on Creative Intelligence
Evolutionary computation (EC) techniques, including genetic algorithm, evolution strategies, genetic
programming, particle swarm optimization, ant colony optimization, differential evolution, and
memetic algorithms have shown to be effective for search and optimization problems. Recently, EC and
deep neural networks gained several promising results and become important tools in computational
creativity, such as in music, visual art, literature, architecture, and industrial design.
The aim of this special session is to reflect the most recent advances of EC for Music, Art, and Creativity, with the goal to enhance autonomous creative systems as well as human creativity. This session will allow researchers to share experiences and present their new ways for taking advantage of CI techniques in computational creativity. Topics of interest include, but are not limited to, EC in the following aspects:
In multiobjective optimization problems, there may exist two or more distinct Pareto optimal sets
(PSs) corresponding to the same Pareto Front (PF). These problems are defined as multimodal
multiobjective optimization problems (MMOPs). Arguably, finding one of these multiple PSs may be
sufficient to obtain an acceptable solution for some problems. However, failing to identify more
than one of the PSs may prevent the decision maker from considering solution options that could
bring about improved performance.
The aim of this special session is to promote the research on MMO and hence motivate researchers to formulate real-world practical problems. Given that the study of multimodal multiobjective optimization (MMO) is still in its emerging stages, although many real-word applications are likely to be amenable to treatment as a MMOP, to date the researchers have ignored such formulations.
This special session is devoted to the novel approaches, algorithms and techniques for solving MMOPs. The main topics of the special session are:
The Brain Storm Optimization (BSO) algorithm is a new kind of swarm intelligence algorithm, which is
based on the collective behavior of human being, that is, the brainstorming process. There are two
major operations involved in BSO, i.e., convergent operation and divergent operation. A “good
enough” solution could be obtained through recursive solution divergence and convergence in the
search space. The designed optimization algorithm will naturally have the capability of both
convergence and divergence. The BSO algorithm can be seen as a combination of swarm intelligence and
data mining techniques. Every individual in the brain storm optimization algorithm is not only a
solution to the problem to be optimized, but also a data point to reveal the landscapes of the
problem. The swarm intelligence and data mining techniques can be combined to produce benefits above
and beyond what either method could achieve alone.
This special session aims at presenting the latest developments of BSO algorithm, as well as exchanging new ideas and discussing the future directions of developmental swarm intelligence. Original contributions that provide novel theories, frameworks, and applications to algorithms are very welcome for this Special session. Potential topics include, but are not limited to:
The volume of cybercrime is increasing daily with increasing use of the internet for email and social
media purposes. The use of neural networks for tackling cybercrime is an active area of research.
For example, conventional neural network-based solutions have been proposed to detect image
tampering, source camera attribution of an anonymous crime image, explicit content detection, virus
detection, etc. Recently, researchers are focusing more on unsupervised solutions. New types of
cybercrimes are also emerging (e.g., deepfake video) which may, in turn, require new approaches.
Interestingly, the role of evolutionary computing in tackling cybercrime is relatively
This special session aims to bring together researchers from both academia and industry in the application of evolutionary computation and neural networks for combating cybercrime. This session also will welcome research which focuses on the risk of a neural network for spreading new kind of cybercrimes (e.g., deepfake videos) and evolutionary computing for creating new types of malware (e.g., polymorphic and metamorphic viruses). The session will attract researchers working in cybersecurity, evolutionary computation, and neural networks. Of particular interest will be research that combines evolutionary computing with neural network approaches. The main topics of this special session include, but are not limited to, the following:
Biomedical data contains several challenges in data analysis, including high dimensionality, class
imbalance and low numbers of samples. There is also a need to explore big data in biomedical and
healthcare research. An increasing flood of data characterises human health care and biomedical
research. Healthcare data are available in different formats, including numeric, textual reports,
signals and images, and the data are available from different sources. An interesting aspect is to
integrate different data sources in the data analysis process which requires exploiting the existing
domain knowledge from available sources. The data sources can be ontologies, annotation
repositories, and domain experts’ reports.
This special session aims to bring together the current research progress (from both academia and industry) on data analysis for biomedical and healthcare applications. It will attract healthcare practitioners who have access to interesting sources of data but lack the expertise in using the data mining effectively. Special attention will be devoted to handle feature selection, class imbalance, and data fusion in biomedical and healthcare applications.
The main topics of this special session include, but are not limited to, the following:
With the explosion of data generation, getting optimal solutions to data driven problems is
increasingly becoming a challenge, if not impossible. Pigeon Inspired Optimization (PIO) is a
recently developed intelligent bio-inspired algorithm and become popular to deal with a variety of
optimization problems. It is capable of addressing highly complex problems to provide working
solutions in time, especially with dynamic problem definitions, fluctuations in constraints,
incomplete or imperfect information and limited computation capacity.
This special session aims at presenting the latest developments of PIO algorithm, as well as exchanging new ideas and discussing the future directions of developmental swarm intelligence. Original contributions that provide novel theories, frameworks, and applications to algorithms are very welcome for this Special Session. Potential topics include, but are not limited to:
Supported by IEEE CIS ETTC
This special session focuses on both practical and theoretical aspects of Evolutionary Scheduling and
Combinatorial Optimization. Examples of evolutionary methods include genetic algorithm, genetic
programming, evolutionary strategies, ant colony optimization, particle swarm optimization, evolutionary
based hyper-heuristics, memetic algorithms. Novel hybrid approaches that combine machine learning and
evolutionary computation to solve difficult ESCO problems are highly encouraged. Examples include using
machine learning to improve surrogate-assisted evolutionary algorithms, and designing evolutionary
algorithms for reinforcement learning and transfer learning.
We welcome the submissions of quality papers that effectively use the power of EC techniques to solve hard and practical scheduling and combinatorial optimization problems. Papers with rigorous analyses of EC techniques and innovative solutions to handle challenging issues in scheduling and combinatorial optimisation problems are also highly encouraged.
Topics of interest include, but not limited to:
Supported by IEEE CIS ETTC Task Force on Operations Research and Management Sciences
The field of evolutionary multi-objective optimization has developed rapidly over the last 20 years, but
the design of effective algorithms for addressing problems with more than three objectives (called
many-objective optimization problems, MaOPs) remains a great challenge. First, the ineffectiveness of
the Pareto dominance relation, which is the most important criterion in multi-objective optimization,
results in the underperformance of traditional Pareto-based algorithms. Also, the aggravation of the
conflict between convergence and diversity, along with increasing time or space requirement as well as
parameter sensitivity, has become key barriers to the design of effective many-objective optimization
algorithms. Furthermore, the infeasibility of solutions' direct observation can lead to serious
difficulties in algorithms' performance investigation and comparison. All of these suggest the pressing
need of new methodologies designed for dealing with MaOPs, new performance metrics and test functions
tailored for experimental and comparative studies of evolutionary many-objective optimization (EMaO)
List of topics, but are not limited to:
Supported by IEEE CIS ISATC Task Force on Intelligence Systems for Health
Worldwide, the healthcare industry would continue to thrive and grow, because diagnosis, treatment,
disease prevention, medicine, and service affect the mortal rates and life quality of human beings. Two
key issues of the modern healthcare industry are improving healthcare quality as well as reducing
economic and human costs. The problems in the healthcare industry can be formulated as scheduling,
planning, predicting, and optimization problems, where evolutionary computation methods can play an
important role. Although evolutionary computation has been applied to scheduling and planning for trauma
system and pharmaceutical manufacturing, other problems in the healthcare industry like decision making
in computer-aided diagnosis and predicting for disease prevention have not properly formulated for
evolutionary computation techniques, and many evolutionary computation techniques are not well-known to
the healthcare community. This special session aims to promote the research on evolutionary computation
methods for their application to the healthcare industry.
The topics of this special session include but are not limited to the following topics:
Supported by IEEE CIS ETTC
Services computing is becoming more and more prominent in the Internet environment with the rapid growth
of services available on the internet. Cloud computing has become a scalable services consumption and
delivery platform in the field of Services Computing. This raises issues for service providers such as
Web service composition and service location allocation, resource allocation and scheduling, etc.
Computational Intelligence (CI) has been successfully applied to many challenging real-world problems.
This special session aims to solve the service and cloud computing problems with CI techniques, covering
all different evolutionary computation paradigms such as GA, GP, EP, ES, MA, LCS, PSO, ACO, DE, and EMO.
The scope of this special session includes both new theories and methods on how to solve the challenging services computing and cloud computing problems. Topics of interest include, but not limited to:
Evolutionary Machine Learning (EML) explores technologies that integrate machine learning (e.g., neural networks, decision trees, fuzzy systems, reinforcement learning) with evolutionary computation for tasks including optimization, classification, regression, and clustering. Since machine learning contributes to parameter learning while evolutionary computation contributes to model/parameter optimization, one of the fundamental interests in EML is a management of interactions between learning and evolution to produce a system performance that cannot be achieved by either of these approaches alone. Historically, this research area was called Genetics-Based Machine Learning (GBML) and it was concerned with learning classifier systems (LCS) with its numerous implementations. More recently, EML has emerged as a more general field than GBML. It is consequently a broader, more flexible and more capable paradigm than GBML. From this viewpoint, the aim of this special session is to explore potential EML technologies and clarify new directions for EML to show its prospects. For this purpose, this special session focuses on, but is not limited to, the following areas in EML:
Many of the tasks carried out in data mining and machine learning, such as feature subset selection,
associate rule mining, model building, etc., can be transformed as optimization problems. Thus it is
very natural that Evolutionary Computation (EC), has been widely applied to these tasks in the fields of
data mining (DM) and machine learning (ML), as an optimization technique. On the other hand, EC is a
class of population-based iterative algorithms, which generate abundant data about the search space,
problem feature and population information during the optimization process. Therefore, the data mining
and machine learning techniques can also be used to analyze these data for improving the performance of
The aim of this special session is to serve as a forum for scientists in this field to exchange the latest advantages in theories, technologies, and practice. We invite researchers to submit their original and unpublished work related to, but not limited to, the following topics:
To shape a low carbon energy future has been a crucial and urgent task under Paris Global Agreement.
Numerous optimisation problems have been formulated and solved to effectively save the fossil fuel cost
and relief energy waste from power system and energy application side. However, some key problems are of
strong non-convex, non-smooth or mixed integer characteristics, leading to significant challenging
issues for system operators and energy users. Evolutionary computation is immune from complex problem
modeling formulation, and is therefore promising to provide powerful optimisation tools for
intelligently and efficiently solving problems such as smart grid and various energy systems scheduling
to reduce carbon consumptions.
This special session intends to reflect the state-of-the-art advances of evolutionary optimisation approaches for solving emerging problems in complex modern power and energy system. The submissions are encouraged to be focus on smart grid scheduling with integration of new participants such as renewable generations, plug-in electric vehicles, distribution generations and energy storages, multiple time-spacial energy reductions and other energy optimisation topics. Potential submission topics include:
Supported by IEEE CIS ETTC Task Force on Evolutionary Computation for Feature Selection and Construction
In machine learning and data mining, the quality of the input data, i.e. feature space, is a key for
success of any algorithm. Feature selection, feature extraction or construction and dimensionality
reduction are important and necessary data pre-processing techniques to increase the quality of the
feature space. However, they are challenging tasks due to the large search space and feature
interactions. This special session aims to use Evolutionary Computation for feature reduction, covering
ALL different evolutionary computation paradigms. Authors are invited to submit their original and
unpublished work to this special session.
Topics of interest include but are not limited to:
Supported by IEEE CIS ISATC Task Force on Transfer Learning & Transfer Optimization
Transfer learning aims to transfer knowledge acquired in one problem domain, i.e. the source domain, onto
another domain, i.e. the target domain. Transfer learning has recently emerged as a popular learning
framework in data mining and machine learning. Evolutionary computation techniques have been
successfully applied to many real-world problems, and started to be used to solve transfer learning and
transfer optimisation tasks.
The aim of this special session is to investigate in both the new theories and methods on how transfer learning and optimisation can be achieved with evolutionary computation, and how transfer learning can be adopted in evolutionary computation. Authors are invited to submit their original and unpublished work to this special session.
Topics of interest include but are not limited to:
Supported by IEEE CIS ECTC Task Force on Nature-Inspired Constrained Optimization
In their original versions, nature-inspired algorithms for optimization such as evolutionary algorithms (EAs) and swarm intelligence algorithms (SIAs) are designed to sample unconstrained search spaces. Therefore, a considerable amount of research has been dedicated to adapt them to deal with constrained search spaces. The objective of the session is to present the most recent advances in constrained optimization using different nature-inspired algorithms. The session seeks to promote the discussion and presentation of novel works related with (but not limited to) the following issues:
Supported by IEEE CIS Task Force on Theory of Bio-inspired Computing
The area of runtime analysis for bio-inspired computing techniques provides new insights into the working
behaviour of these methods for solving optimization problems. The theoretical analysis of these
algorithms includes studying the runtime complexity with respect to the input size and/or other
parameters of the instance of the problem until reaching an optimal or approximate solution of the
problem. Rigorous analysis of these algorithms helps us in designing more efficient algorithms.
Moreover, investigating the effect of different parameters of the studied algorithms lead to more
efficient parameter tuning for these algorithms. Furthermore, studying the theoretical behaviour of
bio-inspired algorithms with respect to the characteristics of the studied problem is beneficial in
choosing the right algorithm for solving each instance of the problem.
The purpose of this special session is to bring together people working on theoretical analysis of bio-inspired computing techniques. We aim to provide a forum for the researchers in this field to discuss the latest outcomes and new directions in the theory of bio-inspired algorithms. Topics of interest include, but are not limited to:
Supported by IEEE CIS Task Force on Optimization Methods in Bioinformatics and Bioengineering
Bioinformatics and Bioengineering (BB) are interdisciplinary scientific fields involving many branches of
computer science, engineering, mathematics, and statistics. Bioinformatics is concerned with the
development and application of computational methods for the modeling, retrieving and analysis of
biological data, whilst Bioengineering is the application of engineering techniques to biology so as to
create usable and economically viable products.
Bioinformatics and Bioengineering are relatively new fields in which many challenges and issues can be formulated as (single and multiobjective) optimization problems. These problems span from traditional problems, such as the optimization of biochemical processes, construction of gene regulatory networks, protein structure alignment and prediction, to more modern problems, such as directed evolution, drug design, experimental design, and optimization of manufacturing processes, material and equipment.
The main aim of this special session is to bring together both experts and new-comers working on Optimization, Learning and Decision-Making in Bioinformatics and Bioengineering to discuss new and exciting issues in this area. The topics are, but not limited to, the following
Evolutionary Computation (EC) techniques are widely used in Internet of Everything (IoEt) applications
such as Internet of Things, Fog Computing, Edge Computing, and Cloud Computing towards sustainable
computing infrastructure at different levels. A large amount of effort is being put toward achieving
distributed artificial intelligence. Distributed Artificial Intelligence is a method to enable complex
learning, planning, and decision-making problems in a decentralized fashion. It is able to execute large
scale computation through distributed computing resources. These properties allow it to solve problems
that require the processing of very large data sets. This approach, when put together with the idea of
Internet of Everything, opens up a new world of applications of artificial intelligence in a localised
It is clear that EC is going to play a huge role in the lives of the average human being. With the ongoing research in fields like distributive computing, fuzzy logic, neural networks etc, we can also be sure that the intelligence that will run the world will be far more advanced and heuristic than the kind we have today.
The main topics of this special session include, but are not limited to, the following:
Symbolic modeling is the process of developing symbolic descriptions/mathematical models to capture the
structure of the data and make an accurate prediction. In evolutionary computation, symbolic modeling
can be achieved by a set of techniques including but not only limited to genetic programming and
learning classifier systems.
The theme of this special session is to promote evolutionary computation for symbolic modelling. This involves contributions to the state-of-the-art symbolic modelling techniques through either theoretical or algorithmic work investigating and enhancing the learning, the generalisation, the interpretability, the efficiency and the robustness of the techniques. This also involves methods to handle complex large-scale datasets and high-dimensional datasets, e.g. instance sampling, feature selection and feature construction. Novel applications are also important and interesting to explore. Authors are invited to submit their original and unpublished work to this special session. Topics of interest include but are not limited to:
Numerous industries and service sections are now striving to embrace the latest AI technologies. As a result, research in scheduling and network design problems is getting increasingly popular. Most of these problems, unfortunately, are NP-Hard and cannot usually be solved by exact approaches. Therefore, significant research attention has been attracted on exploring techniques in hybridizing Computational Intelligence (including evolutionary computation, neural networks, swarm intelligence, fuzzy logic) with classic integer programming techniques like branch and bound, column generations, branch and pricing, etc. This special session aims to explore recent advances in this area. Topics include, but are not limited to, the following:
Many of industrial and research databases suffer from an unavoidable problem of data incompleteness. In
big data era, data is generated almost everywhere; therefore, the more data is collected, the more
frequent the data suffers from missing values. Missing values not only cause the non-applicability, but
also cause the loss of effectiveness and efficiency of almost all data mining algorithms.
Evolutionary computation (EC) techniques have been successfully applied to solve and improve data mining tasks. However, EC techniques have been mainly used for data mining with complete data and also, but with less effort with missing data. Hence, this special session aims to encourage information exchange and discussion between researchers with an interest in the use of any EC technique for handling missing data in data mining and machine learning. Topics of interest include but are not limited to, the use of any EC technique for handling missing data in data mining:
The application of complex networks to evolutionary computation (EC) has received considerable attention
from the EC community in recent years. The most well-known study should be the attempt of using complex
networks, such as small-world networks and scale-free networks, as the potential population structures
in evolutionary algorithms (EAs). Structured populations have been proposed to as a means for improving
the search properties because several researchers have suggested that EAs populations might have
structures endowed with spatial features, like many natural populations. Moreover, empirical results
suggest that using structured populations is often beneficial owing to better diversity maintenance,
formation of niches, and lower selection pressures in the population favouring the slow spreading of
solutions and relieving premature convergence and stagnation. Moreover, the study of using complex
networks to analyse fitness landscapes and designing predictive problem difficulty measures is also
attracting increasing attentions. On the other hand, using EAs to solve problems related to complex
networks, such as community detection, is also a popular topic.
This special session seeks to bring together the researchers from around the globe for a creative discussion on recent advances and challenges in combining complex networks and EAs. The special session will focus on, but not limited to, the following topics:
Supported by IEEE CIS TF on Evolutionary Computation in Dynamic and Uncertain Environments
Many real-world optimization problems are subject to dynamism and uncertainties that are often impossible
to avoid in practice. For instance, the fitness function is uncertain or noisy as a result of
simulation/ measurement errors or approximation errors (in the case where surrogates are used in place
of the computationally expensive high-fidelity fitness function). In addition, the design variables or
environmental conditions can be perturbed, or they change over time. The tools to solve these dynamic
and uncertain optimization problems (DOP) should be flexible, able to tolerate uncertainties, fast to
allow reaction to changes and adaptation. Moreover, the objective of such tools is no longer to simply
locate the global optimum solution, but to continuously track the optimum in dynamic environments, or to
find a robust solution that operates properly in the presence of uncertainties.
This special session aims at bringing together researchers from both academia and industry to review the latest advances and explore future directions in this field. Topics of interest include, but are not limited to:
Supported by IEEE CIS ETTC Task Force on Artificial Immune Systems
The biological immune system is a powerful defense system that protects an organism itself from diseases
and danger. The biological immune system is a kind of complex, adaptive, dynamic and distributive
systems with abilities of learning, memory, self-organization, feature extraction and pattern
recognition. The Artificial Immune System, also known as Immune Computation, is a relatively new branch
in the computational intelligence community, which is inspired by the structure, functions, models and
information processing mechanism of biological immune system. The Artificial Immune System is a fast
developing research area. Nowadays, the scope of this research area ranges from modeling to simulation
of the biological immune system, to the development of novel engineering solutions to complex problems.
This special session aims to focus on the state-of-the-art research on immune-inspired algorithms and the new conceptual models for understanding the dynamics that underlie the immune system. Topics of interest include, but are not limited to:
Supported by IEEE CIS Task Force on the Ethical and Social Implications of Computational Intelligence
Computational Intelligence (CI) can provide great benefits to society but also will introduce some
challenges. For example, are CI systems used for marking student assignments capable of bias? Moreover,
is the current legal framework capable of dealing with the repercussions of decisions made by CI systems
on matters such as finance, medical treatments or autonomous vehicle collision avoidance. This special
session aims to discuss solutions to some of these challenges, what safeguards might be required (both
technologically and legally) and how we can better present the benefits of CI to the wider community.
Topics of interest include, but are not limited to:
A Smart City is an urban area that uses different types of electronic data collection sensors to supply
information which is used to manage assets and resources efficiently. It integrates information and
communication technology (ICT), and various physical devices connected to the network (the Internet of
things or IoT) to optimize the efficiency of city operations and services. A smart city is powered by
“smart connections” for various items such as street lighting, smart buildings, distributed energy
resources (DER), data analytics, and smart transportation.
There are various complex optimization problems in Smart City. The aim of this special session is to bring together researchers from both academia and industry in the application of evolutionary computation for solving various optimization problems in smart city. The main topics of this special session include, but are not limited to, the following:
Cooperative Evolutionary Computation refers to the area of having multiple evolutionary algorithmic
instances cooperating with each other to solve an optimization problem. Cooperation could be classified
as implicit or explicit. In implicit decomposition, multiple instances implicitly tackle different areas
of the search domain due to different initialization, parameter settings, etc. In explicit
decomposition, each instance operates in a dedicated subdomain either by dividing the entire domain
between instances or dividing the problem variables (i.e. cooperative coevolution). Moreover,
cooperative algorithms could be classified as homogeneous (multiple instances of the same evolutionary
algorithm) or heterogeneous (instances of different evolutionary algorithms). Many cooperative search
algorithms have produced remarkably effective solutions, with a faster speed of convergence, to
continuous, large-scale, discrete, combinatorial and multi-objective problems in many fields.
This special session aims at presenting the latest developments of cooperative evolutionary computation techniques, exchanging new ideas and discussing open research questions and future directions. Original contributions that provide novel theories, frameworks, and applications to this topic are very welcome. Potential topics include, but are not limited to:
Supported by IEEE CIS Computational Finance and Economics TC
Computational Finance and Economics covers a wide area of topics and techniques. The arrival of new computational methods, especially from Evolutionary Computation (EC), continually pushes the boundaries of the field outwards. That, together with the advances in available hardware, have contributed to a growing interest in applying EC techniques to solve different financial and economic problems. This Special Session is dedicated to the application of Evolutionary Computation methodologies to such problems. We welcome papers from any algorithm from the EC field, as well as hybrid EC methods. Applications include (but not limited to):
The smart city concept integrates information and communication technology, and various physical devices
connected to the cloud network to optimize the efficiency of city operations and services and connect to
citizens. Therefore, most of real-world problems in the smart city are multimodal interface problems
and/or multi-objective optimization problems involving several conflicting objectives. On the other
hand, cloud systems may even offer tens of thousands of virtual machines, terabytes of memories and
exa-bytes of storage capacity. Current trend toward many-core architecture increases the number of cores
even more dramatically.
In this special session, we will discuss new parallel and distributed evolutionary computation (EC) in the smart city era, in term of both reduction in execution time and improvements in accuracy of the achieved solutions. Topics of interest include, but are not limited to, EC in the following aspects:
Supported by IEEE CIS FSTC Task Force on Adaptive and Evolving Fuzzy Systems
Granular computing (GC) focuses on the knowledge representation and reasoning with information granules,
and fuzzy sets and rough sets are two crucial branches of GC. Evolutionary computation for granular
computing emphasizes the utility of different evolutionary algorithms to various facets of granular
computing, ranging from theoretical analysis to real-life applications. The main motivation for applying
evolutionary algorithms to granular computing tasks in the knowledge reasoning is that they are robust
and adaptive search methods, which can perform a global search in the space of candidate solutions. The
benefits of exploring the combination of granular computing and evolutionary computation will have an
impact in multiple research disciplines and industry domains, including transportation, communications,
social network, medical health, and so on.
The goal of this special section aims at providing a specific opportunity to review the state-of-the-art of evolutionary computation for granular computing. We invite researchers to submit their original and unpublished work related to, but not limited to, the following topics:
Deep learning has shown significantly promising performance in addressing real-world problems. The
achievements of such algorithms owe to its deep structures. However, designing an optimal deep structure
requires rich domain knowledge on both the investigated data and the general data analysis domain, which
is not necessarily held by the end-users. In addition, the problem of searching for the optimal
structure could be non-convex and non-differentiable, and existing accurate methods are incapable of
well addressing it.
Evolutionary computation (EC) approaches have shown superiority in addressing real-world problems due largely to their powerful abilities in searching for global optima, and requiring no rich domain knowledge. However, most of the existing EC methods currently work only on relatively shallow structures, and cannot provide satisfactory results in searching for deep structures. In this regard, evolutionary deep learning, would be a great research topic.
The theme of this special session aims to bring together researchers investigating methods and applications in evolutionary deep learning.
Many real-world engineering optimization problems not only require the simultaneous optimization of a
number of objective functions, but also need to track the changing optimal solutions. These problems are
called: Dynamic multi-objective optimization (DMOO) problems. Here, where either the objective functions
or the constraints change over time, an optimization algorithm should be able to find, and track the
changing set of optimal solutions and approximate the time-varying true Pareto front. Therefore, the
DMOO algorithm also has to deal with the problems of a lack of diversity and outdated memory.
EThe main goal of this session is to emphasize the newest techniques in solving dynamic multi-objective optimization problems and handling current issues. Due to the novelty of DMOO, the session more concentrates on combining DMOO with other hot topics, such as deep learning. Therefore, session aims at providing a forum for researchers in the area of DMOO to exchange new ideas and submit their original and unpublished work. Topics of interest include, but are not limited to:
This special session is concerned about the Self-Organizing Migrating Algorithm (SOMA), belonging to the
class of swarm intelligence techniques. Compare to other prominent swarm intelligence paradigms, as for
example Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Firefly, and so on, SOMA is
distinguished by competitive-cooperative phases, inherent self-adaptation of movement over the search
space, as well as by discrete perturbation mimicking the mutation process known from the classical
evolutionary computing techniques. The SOMA perform significantly well in both continuous as well as
discrete domains. The SOMA has been used successfully on various tasks as the real-time plasma reactor
control, aircraft wings optimisation, chaos control, large scale, combinatorial and permutative
This special session is concern about original research papers discussing new results on and with SOMA, as well as its novel improvements tested on widely accepted benchmark tests. This session aims to bring together people from fundamental research, experts from various applications of SOMA to develop mutual intersections and fusion. Also, a discussion of possible hybridisation amongst them as well as real-life experiences with computer applications will be carried out to define new open problems in this interesting and fast-growing field of research. The special session will focus on, but not limited to, the following topics: