Saturday, 17 March 2018

CFP: IEEE TETCI Special Issue on New Advances in Deep-Transfer Learning (Jun 30)


While Deep learning (DL) has achieved great success in big data applications, transfer learning (TL) is an important paradigm for small/insufficient data applications, which utilizes the data/knowledge in one task to facilitate the learning in another relevant task. How to integrate DL and TL to combine their advantages is an interesting and important research topic. Deep-Transfer Learning (DTL) is proposed to address this issue. Deep learning extracts knowledge from big data, which can then be used by TL for a new task/domain with small/insufficient data.

Computational intelligence techniques, mainly including neural networks, fuzzy logic, and evolutionary computation, can be valuable in DTL. For example:

  • Neural networks (NN) are the cornerstones of DL. 
  • Hierarchical/cascaded fuzzy logic systems (FLS) and fuzzy NNs may be viewed as fuzzy rule based DL models. FLSs can also capture interpretable knowledge, which may be easily transferrable to a new domain/task. Therefore, fuzzy logic is expected to play an important role in integrating DL and TL. 
  • Evolutionary computation (EC) has been widely used in optimizing shallow NNs and FLSs. TL can also be viewed as an evolutionary learning strategy because it adapts the model to the changing environment. It is interesting to see novel applications of EC in DTL. 
  • Other emerging forms of CI, such as (but not limited to) probabilistic computation, swarm intelligence, and artificial immune systems, can also contribute to DTL from different aspects. The aims of this special issue are: (1) present the state-of-theart research on novel CI based DTL methods and their applications, and (2) provide a forum for researchers to disseminate their views on future perspectives of the field.

Topics of interest for this special issue include, but are not limited to: 

Theory and Methods: 
  • DTL theory and algorithms 
  • Fuzzy logic and fuzzy set based DTL 
  • Neural networks based DTL 
  • Evolutionary computation for DTL 
  • Novel/emerging forms of CI (in addition to NN/FLS/EC) in DTL 
  • Uncertainty theory based DTL 
  • DTL for feature learning, classification, regression, and clustering 
  • DTL for multi-task modeling, multi-view modeling and co-learning 

  • CI based DTL for video analysis, text processing and natural language processing 
  • CI based DTL for brain-machine interfaces and medical signal analysis


Manuscripts should be prepared according to the “Information for Authors” section of the journal ( and submissions should be done through the journal submission website:, by selecting the Manuscript Type of “New Advances in Deep-Transfer Learning” and clearly marking “New Advances in Deep Transfer Learning Special Issue Paper” as comments to the Editor-in-Chief. Submitted papers will be reviewed by at least three different expert reviewers. Submission of a manuscript implies that it is the authors’ original unpublished work and is not being submitted for possible publication elsewhere.


Paper submission deadline: June 31, 2018 
Notice of the first round review results: September 15, 2018 
Revision due: November 15, 2018 
Final notice of acceptance/reject: December 15, 2018 


Zhaohong Deng, Jiangnan University, China; 
Jie Lu, University of Technology Sydney, Australia; 
Dongrui Wu, Huazhong University of Science and Technology, China; 
Kup-Sze Choi, Hong Kong Polytechnic University, Hong Kong, China; Shiliang Sun, East China Normal University, China; 
Yusuke Nojima, Osaka Prefecture University, Japan;

CFP: IEEE TETCI Special Issue on Computational Intelligence for Smart Energy Applications to Smart Cities (May 15)


By 2050, more than half the world’s population is expected to live in urban regions. This rapid expansion of population in the cities of the future will lead to increasing demands on various infrastructures; the urban economics will play a major role in national economics. Cities must be competitive by providing smart functions to support high quality of life. There is thus an urgent need to develop smart cities that possess a number of smart components. Among them, smart energy is arguably the first infrastructure to be established because almost all systems require energy to operate.

Smart energy refers to energy monitoring, prediction, use or management in a smart way. In smart cities, smart energy applications include smart grids, smart mobility, and smart communications. While realizing smart energy is promising to smart cities, it involves a number of challenges.

 By using smart grid technologies, distributed power supply is replacing conventional centralized schemes, leading to regional aggregation of energy that must consider the interests of many grid participants. With the increasing penetration of electric vehicles (EVs), EV charging stations must consider many parameters and objectives to optimize the charging schedule. To make transportation or communications infrastructures go green, renewable energy sources (RESs) are often integrated into the whole system as part of power supply; a robust prediction for both power load and energy production becomes necessary for later energy management in response to intermittent power supply from RESs.

Because of the uncertainty of environments, complexity of the problem of interest, or multiplicity of objectives that must be achieved, conventional optimization methods using deterministic search algorithms cannot well address these challenges. By contrast, stochastic optimization can be useful for handling uncertainty; adaptive learning based on, for example, human behaviors, available resources, network capacity, or collected data can be a solution to complex problems; evolutionary computation can be applied to solve problems with many objectives. Computational Intelligence (CI) thus serves as a useful tool for addressing aforementioned difficulties.


This Special Issue aims to provide in-depth CI technologies that enable smart energy applications to smart cities. Topics of interest include, but are not limited to:

  • Evolutionary computation for smart grids in consideration of many objectives, including energy management system, demand-side management, demand response, advanced metering infrastructure, and behind-the-meter applications.  
  • Stochastic optimization for smart mobility in consideration of system uncertainty, with a primary focus on power scheduling for Internet of EVs or green public transportation.  
  • Intelligent algorithms for smart communications pertaining to Internet of Things, machine-to-machine communications, vehicle-to-grid communications, and vehicle-to-infrastructure communications under the framework of green communications.  
  • Machine/deep learning for renewable energy forecasting or power load forecasting.  
  • Survey papers on CI for smart energy applications. 

Submission deadline: May 15, 2018.  
Notification due date: October 1, 2018.  
Final version due date: November 1, 2018. 


Manuscripts should be prepared according to the “Information for Authors” section of the journal ( and submissions should be done through the journal submission website:, by selecting the Manuscript Type of “Computational Intelligence for Smart Energy Applications to Smart Cities” and clearly marking “Special Issue on Computational Intelligence for Smart Energy Applications to Smart Cities” as comments to the Editor-in-Chief. 


Wei-Yu Chiu, National Tsing Hua University, Taiwan  
Hongjian Sun, Durham University, UK  
Chao Wang, Tongji University, China  

Athanasios V. Vasilakos, Lulea University of Technology, Sweden

CFP: IEEE TNNLS Special Issue on Recent Advances in Theory, Methodology and Applications of Imbalanced Learning (Apr 30)

Learning from imbalanced/unbalanced data (aka imbalanced learning or class-imbalance learning) is a challenging task faced by practitioners from a wide variety of communities. In the last two decades, researchers from various disciplines including data mining, machine learning, pattern recognition and statistics have intensively investigated this theme. However, as pointed out in the 2013 book “Imbalanced Learning: Foundations, Algorithms, and Applications” collectively authored by experts in this field, many if not the most approaches to imbalanced learning are very heuristic and ad hoc, and thus many open questions remain there: “What is the assurance that algorithms specifically designed for imbalanced learning could really help, and how and why?”; “Is there a way we could develop a theoretical guidance on which based learning algorithm is most appropriate for a particular type of imbalanced data?”; “What is the relationship between data-imbalanced ratio and learning model complexity?”, for example. Moreover, in recent years the datasets that practitioners are concerned have grown increasingly rapidly and complexly; many new applications, and thus new types of data and new learning paradigms, have emerged. Therefore, this special issue aims to call for the state-of-the-art research work in the theory, methodology and applications of imbalanced learning, and aims to demonstrate the recent efforts made by the relevant researchers from a wide range of disciplines.

We welcome all the original work on topics regarding new theory, methodology and applications of imbalanced learning, including but not limited to:

• Deep learning for large-scale imbalanced data
• Representation learning for imbalanced data
• Reinforcement learning for imbalanced data
• Active learning and passive learning for imbalanced data
• Transfer learning and concept drift for imbalanced data
• Imbalanced learning in non-stationary environments
• Online learning and incremental learning for imbalanced data
• Statistical modelling for (non-Gaussian) imbalanced data
• Statistical machine learning for imbalanced data
• Discriminative learning and generative learning for imbalanced data
• Similarity/metric learning for imbalanced data
• Ensemble learning for imbalanced data
• Related learning problems: one-class classification, novelty/outlier/anomaly detection
• Theoretical analysis of models and algorithms for imbalanced learning
• New evaluation metrics for imbalanced learning
• New applications of imbalanced learning: 1) Object detection, classification, recognition; 2) Image retrieval, segmentation, understanding; 3) Speech recognition, synthesis, anti-spoofing; 4) Document retrieval, categorization, topic model; 5) Biomedical signal processing, medical image analysis, bioinformatics; 6) fault detection/diagnosis, fraud detection, cyber-security; and 7) Other related novel applications


30 April 2018 -- Deadline for manuscript submission
31 July 2018 -- Notification of authors
30 September 2018 -- Deadline for submission of revised manuscripts
30 November 2018 -- Final decision of acceptance
January 2019 -- Tentative publication date


Jing-Hao Xue, University College London, UK
Zhanyu Ma, Beijing University of Posts and Telecommunications, China
Manuel Roveri, Politecnico di Milano, Italy
Nathalie Japkowicz, American University, US


1. Read the information for Authors at
2. Submit your manuscript at the TNNLS webpage ( and follow the submission procedure. Please, clearly indicate on the first page of the manuscript and in the cover letter that the manuscript is submitted to this special issue. Send an email to the leading editor Dr. Jing-Hao Xue ( with subject “TNNLS special issue submission” to notify about your submission.
3. Early submissions are welcome. We will start the review process as soon as we receive your contributions.

CFP: IEEE TEVC Special Issue on Theoretical Foundations of Evolutionary Computation (Oct 1)


Evolutionary computation (EC) methods such as
evolutionary algorithms, ant colony optimization and artificial
immune systems have been successfully applied to a wide
range of problems. These include classical combinatorial
optimization problems and a variety of continuous, discrete
and mixed integer real-world optimization problems that are
often hard to optimize by traditional methods (e.g., because
they are non-linear, highly constrained, multi-objective, etc.).
In contrast to the successful applications, there is still a need
to understand the behaviour of these algorithms. The
achievement and development of a solid theory of bio-inspired
computation techniques is important as it provides sound
knowledge on their working principles. In particular, it
explains the success or the failure of these methods in
practical applications. Theoretical analyses lead to the
understanding of which problems are optimized (or
approximated) efficiently by a given algorithm and which ones
are not. The benefits of theoretical understanding for
practitioners are threefold. 1) Aiding algorithm design, 2)
guiding the choice of the best algorithm for the problem at
hand and 3) determining optimal parameter settings.

The aim of this special issue is to advance the theoretical
understanding of evolutionary computation methods. We
solicit novel, high quality scientific contributions on
theoretical or foundational aspects of evolutionary
computation. A successful exchange between theory and
practice in evolutionary computation is very desirable and
papers bridging theory and practice are of particular interest.
In addition to strict mathematical investigations, experimental
studies strengthening the theoretical foundations of
evolutionary computation methods are very welcome.


This special issue will present novel results from different subareas
of the theory of bio-inspired algorithms. The scope of
this special issue includes (but is not limited to) the following

• Exact and approximation runtime analysis
• Black box complexity
• Self-adaptation
• Population dynamics
• Fitness landscape and problem difficulty analysis
• No free lunch theorems
• Theoretical Foundations of combining traditional optimization techniques with EC methods
• Statistical approaches for understanding the behaviour of bio-inspired heuristics
• Computational studies of a foundational nature

All classes of bio-inspired optimization algorithms will be
considered including (but not limited to) evolutionary
algorithms, ant colony optimization, artificial immune
systems, particle swarm optimization, differential evolution,
and estimation of distribution algorithms. All problem
domains will be considered including discrete and continuous
optimization, single-objective and multi-objective
optimization, constraint handling, dynamic and stochastic
optimization, co-evolution and evolutionary learning.


Manuscripts should be prepared according to the “Information
for Authors” section of the journal found at
and submissions should be made through the
journal submission website:,
by selecting the Manuscript Type of “TFoEC
Special Issue Papers” and clearly adding “TFoEC Special
Issue Paper” to the comments to the Editor-in-Chief.

Submitted papers will be reviewed by at least three different
expert reviewers. Submission of a manuscript implies that it is
the authors’ original unpublished work and is not being
submitted for possible publication elsewhere.

Each submission will contain at least one paragraph
explaining why the paper is (potentially) relevant to practice.


Submission open: February 1, 2018
Submission deadline: October 1, 2018
Tentative publication date: 2019

Papers will be assigned to reviewers as soon as they are
submitted. Papers will be published online as soon as they are

For further information, please contact one of the following
Guest Editors.


Pietro S. Oliveto
Department of Computer Science
University of Sheffield
United Kingdom

Anne Auger
Ecole Polytechnique Paris

Francisco Chicano
Department of Languages and Computing Sciences
University of Malaga

Carlos M. Fonseca
Department of Informatics Engineering
University of Coimbra

CFP: IEEE CIM Special Issue on Deep Reinforcement Learning and Games (Oct 1)

Aims and Scope
Recently, there has been tremendous progress in artificial intelligence (AI) and computational intelligence (CI) and games. In 2015, Google DeepMind published a paper “Human-level control through deep reinforcement learning” in Nature, showing the power of AI&CI in learning to play Atari video games directly from the screen capture. Furthermore, in Nature 2016, it published a cover paper “Mastering the game of Go with deep neural networks and tree search” and proposed the computer Go program, AlphaGo. In March 2016, AlphaGo beat the world’s top Go player Lee Sedol by 4:1. In early 2017, the Master, a variant of AlphaGo, won 60 matches against top Go players. In late 2017, AlphaGo Zero learned only from self-play and was able to beat the original AlphaGo without any losses (Nature 2017). This becomes a new milestone in the AI&CI history, the core of which is the algorithm of deep reinforcement learning (DRL). Moreover, the achievements on DRL and games are manifest. In 2017, the AIs beat the expert in Texas Hold’em poker (Science 2017). OpenAI developed an AI to outperform the champion in the 1V1 Dota 2 game. Facebook released a huge database of StarCraft I. Blizzard and DeepMind turned StarCraft II into an AI research lab with a more open interface. In these games, DRL also plays an important role.

Needless to say, the great achievements of DRL are first obtained in the domain of games, and it is timely to report major advances in a special issue of IEEE Computational Intelligence MagazineIEEE Trans. on Neural network and Learning Systems and IEEE Trans. on Computational Intelligence and AI in Games have organized similar ones in 2017.

DRL is able to output control signals directly based on input images, and integrates the capacity for perception of deep learning (DL) and the decision making of reinforcement learning (RL). This mechanism has many similarities to human modes of thinking. However, there is much work left to do. The theoretical analysis of DRL, e. g., the convergence, stability, and optimality, is still in early days. Learning efficiency needs to be improved by proposing new algorithms or combining with other methods. DRL algorithms still need to be demonstrated in more diverse practical settings. Therefore, the aim of this special issue is to publish the most advanced research and state-of-the-art contributions in the field of DRL and its application in games. We expect this special issue to provide a platform for international researchers to exchange ideas and to present their latest research in relevant topics. Specific topics of interest include but are not limited to:

·       Survey on DRL and games;
·       New AI&CI algorithms in games;
·       Learning forward models from experience;
·       New algorithms of DL, RL and DRL;
·       Theoretical foundation of DL, RL and DRL;
·       DRL combined with search algorithms or other learning methods;
·       Challenges of AI&CI games as limitations in strategy learning, etc.;
·       DRL or AI&CI Games based applications in realistic and complicated systems.
Important Dates
Submission Deadline: October 1st, 2018
Notification of Review Results: December 10th, 2018
Submission of Revised Manuscripts: January 31st, 2019
Submission of Final Manuscript: March 15th, 2019
Special Issue Publication: August 2019 Issue

Guest Editors
D. Zhao, Institute of Automation, Chinese Academy of Sciences, China,

Dr. Zhao is a professor at Institute of Automation, Chinese Academy of Sciences and also a professor with the University of Chinese Academy of Sciences, China. His current research interests are in the area of deep reinforcement learning, computational intelligence, adaptive dynamic programming, games, and robotics. Dr. Zhao is the Associate Editor of IEEE Transactions on Neural Networks and Learning Systems and IEEE Computation Intelligence Magazine, etc. He is the Chair of Beijing Chapter, and the past Chair of Adaptive Dynamic Programming and Reinforcement Learning Technical Committee of IEEE Computational Intelligence Society (CIS). He works as several guest editors of renowned international journals, including the leading guest editor of the IEEE Trans.on Neural Network and Learning Systems special issue on Deep Reinforcement Learning and Adaptive Dyanmic Programming.

S. Lucas, Queen Mary University of London, UK,

Dr. Lucas was a full professor of computer science, in the School of Computer Science and Electronic Engineering at the University of Essex until July 31, 2017, and now is the Professor and Head of School of Electronic Engineering and Computer Science at Queen Mary University of London. He was the Founding Editor-in-Chief of the IEEE Transactions on Computational Intelligence and AI in Games, and also co-founded the IEEE Conference on Computational Intelligence and Games, first held at the University of Essex in 2005.  He is the Vice President for Education of the IEEE Computational Intelligence Society. His research has gravitated toward Game AI: games provide an ideal arena for AI research, and also make an excellent application area.

J. Togelius, New York University, USA,

Julian Togelius is an Associate Professor in the Department of Computer Science and Engineering, New York University, USA. He works on all aspects of computational intelligence and games and on selected topics in evolutionary computation and evolutionary reinforcement learning. His current main research directions involve search-based procedural content generation in games, general video game playing, player modeling, and fair and relevant benchmarking of AI through game-based competitions. He is the Editor-in-Chief of IEEE Transactions on Computational Intelligence and AI in Games, and a past chair of the IEEE CIS Technical Committee on Games.

Submission Instructions
1.     The IEEE CIM requires all prospective authors to submit their manuscripts in electronic format, as a PDF file. The maximum length for Papers is typically 20 double-spaced typed pages with 12-point font, including figures and references. Submitted manuscript must be typewritten in English in single column format. Authors of Papers should specify on the first page of their submitted manuscript up to 5 keywords. Additional information about submission guidelines and information for authors is provided at the IEEE CIM website. Submission will be made via
2.     Send also an email to guest editor D. Zhao ( with subject “IEEE CIM special issue submission” to notify about your submission.
3.      Early submissions are welcome. We will start the review process as soon as we receive your contribution.

CFP: IEEE CIM Special Issue on Computational Intelligence for Affective Computing and Sentiment Analysis (Mar 31)


Submissions are invited for a special issue of IEEE Computational Intelligence Magazine (IEEE CIM) on Computational Intelligence for Affective Computing and Sentiment Analysis.

Emotions are intrinsically part of our mental activity and play a key role in communication and decision-making processes. Emotion is a chain of events made up of feedback loops. Feelings and behavior can affect cognition, just as cognition can influence feeling. Emotion, cognition, and action interact in feedback loops and emotion can be viewed in a structural model tied to adaptation. Besides being important for the advancement of AI, detecting and interpreting emotional information is key in multiple areas of computer science, e.g., human- agent, -computer, and -robot interaction, but also e-learning, e-health, domotics, automotive, security, user profiling and personalization.
In recent years, emotion and sentiment analysis has become increasingly popular also for processing social media data on social networks, online communities, blogs, Wikis, microblogging platforms, and other online collaborative media. The distillation of knowledge from such a big amount of unstructured information, however, is an extremely difficult task, as the contents of today's Web are perfectly suitable for human consumption, but remain hardly accessible to machines. The opportunity to capture the opinions of the general public about social events, political movements, company strategies, marketing campaigns, and product preferences has raised growing interest both within the scientific community, leading to many exciting open challenges, as well as in the business world, due to the remarkable benefits to be had from marketing and financial market prediction.

Most of existing approaches to affective computing and sentiment analysis are still based on the syntactic representation of text, a method that relies mainly on word co-occurrence frequencies. Such algorithms are limited by the fact that they can only process information they can 'see'. As human text processors, we do not have such limitations as every word we see activates a cascade of semantically related concepts, relevant episodes, emotions, and sensory experiences, all of which enable the completion of complex NLP tasks — such as word-sense disambiguation, textual entailment, and semantic role labeling — in a quick and effortless way. Computational intelligence can aid to mimic the way humans process and analyze text and, hence, overcome the limitations of standard approaches to affective computing and sentiment analysis.

Articles are thus invited in areas such as machine learning, active learning, transfer learning, deep neural networks, neural and cognitive models, fuzzy logic, evolutionary computation, natural language processing, commonsense reasoning, and big data computing. Topics include, but are not limited to:
• Context-dependent sentiment analysis
• Deep learning for personality detection
• Deep learning for sarcasm detection
• Tensor fusion networks for sentiment analysis
• Multi-level attention networks for sentiment analysis
• Affective commonsense reasoning
• Statistical learning theory for big social data analysis
• Concept-level sentiment analysis
• Social network modeling and analysis
• Multilingual emotion and sentiment analysis
• Multimodal emotion recognition and sentiment analysis
• Aspect extraction for opinion mining
• Sentic computing
• Conceptual primitives for sentiment analysis
• Affective human-agent, -computer, and -robot interaction
• User profiling and personalization
• Time-evolving sentiment tracking

Submission Deadline: March 31st, 2018
Notification of Review Results: June 15th, 2018
Submission of Revised Manuscripts: July 15th, 2018
Submission of Final Manuscript: September 15th, 2018
Special Issue Publication: Mid-January 2019 (February 2019 Issue)

The Special Issue will consist of 3 or 4 papers on novel computational intelligence techniques for mining and analyzing emotions and opinions in text, but also in other modalities. Some papers may survey various aspects of the topic. The balance between these will be adjusted to maximize the issue's impact. All articles are expected to successfully negotiate the standard review procedures for IEEE CIM and shall be submitted via EasyChair.

• Erik Cambria, Nanyang Technological University (Singapore)
• Soujanya Poria, Nanyang Technological University (Singapore)
• Amir Hussain, University of Stirling (UK)
• Bing Liu, University of Illinois at Chicago (USA)

Call for Proposals for IEEE CEC or FUZZ-IEEE in 2021

Proposals for the organization of IEEE CEC or FUZZ-IEEE in 2021 must be submitted as soon as possible, and no later than May 31. Policies, procedures and budget worksheet for such proposals are available. More detailed guidelines can be obtained upon request to Bernadette Bouchon-Meunier.