IEEE CIS  |  CIM  |  TNNLS  |  TEVC  |  TFS  |  TCDS  |  TETCI  |  TG  |  TAI
IEEE CIS Newsletter, Issue 110, March 2022 (1/2)


Dear Member,

The IEEE Computational Intelligence Society (CIS) is seeking nominations for the following key leadership positions (terms are in parentheses):

President-Elect (2023)

Vice President for Education (2023-2024)

Vice President for Member Activities (2023-2024)

Vice President for Publications (2023-2024)

Five ADCOM Members-at-Large (2023-2025)


Section 35 Schedule for ADCOM Elections:

"Five ADCOM Members-at-Large are elected each year, plus any vacated positions."

"The election of President-Elect, Vice President for Education, Vice President for Member Activities, and Vice President for Publications shall take place in even-numbered years."

Eligibility requirements are defined in the CIS Bylaws, ARTICLE XIV – NOMINATIONS, ELECTIONS AND APPOINTMENTS.

The nomination will close on 15 May 2022.

For more information on eligibility, submission requirements, and deadlines please visit our website for the official call for nominations.

Bernadette Bouchon-Meunier, Chair
CIS Nominations Committee

Proposal Deadlines for IEEE SSCI 2024 and IEEE CAI 2024

The IEEE Computational Intelligence Society sponsors many conferences each year with varying levels of financial sponsorship. We are currently looking for proposals for both the 2024 IEEE Symposium Series in Computational Intelligence (IEEE SSCI 2024) as well as the 2024 IEEE Conference on Artificial Intelligence (IEEE CAI 2024). The former is a collection of smaller symposia all collocated under one roof. Given SSCI’s in 2021 through 2023 will be held in North America or Asia, we are hopeful that a proposal for IEEE SSCI 2024 could come from another region. IEEE CAI is a new conference series being arranged with the cooperation of four IEEE Societies including IEEE CIS. The intent of this series is an industry-focused event to highlight broad applications of AI. The first IEEE CAI will be held in June 2023 in Santa Clara, California and we are looking for two IEEE CIS members who would like to run this in 2024.

Proposals for these two conferences should be submitted by 15 May 2022 (hard deadline) to provide sufficient time for review and decision by IEEE CIS Confcom and Adcom. Please inform VP Conferences Marley Vellasco ([email protected]) and Gary Fogel ([email protected]) as Chair of the Confcom Subcommittee on Future Conferences of your intention to provide a proposal or if you would like further information. The process for generating such a proposal can be found on our website.

Research Frontier

Difficulties in Fair Performance Comparison of Multi-Objective Evolutionary Algorithms

many orange targets in a row plus seven arrows, each arrows hit the center of one target, image over white backgroundThe performance of a newly designed evolutionary algorithm is usually evaluated by computational experiments in comparison with existing algorithms. However, comparison results depend on experimental setting; thus, fair comparison is difficult. Fair comparison of multi-objective evolutionary algorithms is even more difficult since solution sets instead of solutions are evaluated. In this paper, the following four issues are discussed for fair comparison of multi-objective evolutionary algorithms: (i) termination condition, (ii) population size, (iii) performance indicators, and (iv) test problems. Whereas many other issues related to computational experiments such as the choice of a crossover operator and the specification of its probability can be discussed for each algorithm separately, all the above four issues should be addressed for all algorithms simultaneously. For each issue, its strong effects on comparison results are first clearly demonstrated. Then, the handling of each issue for fair comparison is discussed. Finally, future research topics related to each issue are suggested. Read More

IEEE Computational Intelligence Magazine, February 2022


Regulated Morphogen Gradients for Target Surrounding and Adaptive Shape Formation

3d rendering group of friendly robots on white backgroundIn swarm robotics, developing algorithms for self-organizing minimalistic robots has become a popular research topic. Unlike others, minimalistic robots may not be able to self-localize themselves, making it very challenging to accomplish missions such as surrounding a target, whose position is typically unknown. In target surroundings, reaching a target and joining the swarm do not always lead to a satisfactory enclosure of the target. Furthermore, it is impossible for individual minimalistic robots to figure out what a global shape of the swarm should be without a collective decision making. In this article, we make use of diffusion and reaction of two morphogens for target surrounding and formation of a circular shape swarm. We show that the proposed method is able to adaptively form shapes surrounding multiple targets. Computer simulations and physical experiments using Kilobots are performed to assess the performance of the proposed algorithm. Read More

IEEE Transactions on Cognitive and Developmental Systems, December 2021


Human-in-the-Loop-Aided Privacy-Preserving Scheme for Smart Healthcare

Medical technology concept.
 Remote medicine.
 Electronic medical record.Nowadays, artificial intelligence (AI) has become the core technology for numerous application fields ranging from self-driving cars to smart cities. Smart healthcare, as an important part of smart cities, constitutes one of the most essential pillars of social and economic stability. Despite all the possibilities offered by smart healthcare, how to handle the dark aspects of smart healthcare such as security, privacy and trust issues, and so on remains unsolved. In this paper, we focus on designing a human-in-the-loop-aided (HitL-aided) scheme to preserve privacy in smart healthcare. On the one hand, a block design technique is employed to obfuscate various health indicators from the hospitals and the smart wearable devices. On the other hand, human-in-the-loop (HitL) is introduced to enable privacy access of the health reports from the smart healthcare platform. In addition, the performance analysis and case study indicate that the proposed HitL-aided scheme is effective in preserving privacy for smart healthcare. Read More

IEEE Transactions on Emerging Topics in Computational Intelligence, February 2022


Win Prediction in Multiplayer Esports: Live Professional Match Prediction

Team of four professional cybersport gamers wearing headphones participating in eSport tournament, playing online video games while sitting in gaming club or internet cafe, selective focusEsports are competitive video games watched by audiences. Most esports generate detailed data for each match that are publicly available. Esports analytics research is focused on predicting match outcomes. Previous research has emphasized prematch prediction and used data from amateur games, which are more easily available than those from professional level. However, the commercial value of win prediction exists at the professional level. Furthermore, predicting real-time data is unexplored, as is its potential for informing audiences. Here, we present the first comprehensive case study on live win prediction in a professional esport. We provide a literature review for win prediction in a multiplayer online battle arena (MOBA) esport. This article evaluates the first professional-level prediction models for live DotA 2 matches, one of the most popular MOBA games, and trials it at a major international esports tournament. Using standard machine learning models, feature engineering and optimization, our model is up to 85% accurate after five minutes of gameplay. Our analyses highlight the need for algorithm evaluation and optimization. Finally, we present implications for the esports/game analytics domains, describe commercial opportunities and practical challenges, and propose a set of evaluation criteria for research on esports win prediction. Read more

IEEE Transactions on Games, December 2021


A Review of Single-Source Deep Unsupervised Visual Domain Adaptation

ooking at the DOMAIN text on yellow background with a magnifying glass.
 Business Research Concept.Large-scale labeled training datasets have enabled deep neural networks to excel across a wide range of benchmark vision tasks. However, in many applications, it is prohibitively expensive and time-consuming to obtain large quantities of labeled data. To cope with limited labeled training data, many have attempted to directly apply models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain. Unfortunately, direct transfer across domains often performs poorly due to the presence of domain shift or dataset bias. Domain adaptation (DA) is a machine learning paradigm that aims to learn a model from a source domain that can perform well on a different (but related) target domain. In this article, we review the latest single-source deep unsupervised DA methods focused on visual tasks and discuss new perspectives for future research. We begin with the definitions of different DA strategies and the descriptions of existing benchmark datasets. We then summarize and compare different categories of single-source unsupervised DA methods, including discrepancy-based methods, adversarial discriminative methods, adversarial generative methods, and self-supervision-based methods. Finally, we discuss future research directions with challenges and possible solutions. Read more

IEEE Transactions on Neural Networks and Learning Systems, February 2022

Member Activities

Meet: Nikhil R. Pal, Chair of the IEEE CIS History Committee.

Nikhil Pal

What is your title, and place of work? (or Technical Field of Research)?

I am a professor at the Electronics and Communication Sciences Unit and also the Head of the Centre for Artificial Intelligence and Machine Learning, Indian Statistical Institute, Calcutta. 

How long have you been a member of CIS and what was the reason you chose to join IEEE CIS?

I do not remember exactly when I joined CIS, but it has been for many years. I have been an IEEE member for 32 years. Most likely I joined CIS at its inception or very close to that. I became interested in fuzzy sets and neural networks in the late eighties and within a short time I fell in love with them. Soon I realized that CIS is my professional home within the IEEE family.  

What Computational Intelligence society committee do you serve?

At present, I am serving as the Chair of the CIS History Committee and as a member on the CIS Fellow Committee. In the past, I served on many committees of CIS. I served as an elected member of the CIS Administrative Committee (AdCom) during 2010-2012 and then as the Vice President for Publications (2013-2016),  I served on both CIS Executive Committee (ExCom) and AdCom. As the President-Elect (2017), President (2018-2019), and the Past President (2020),  I continued to serve on both AdCom and ExCom for four more years. During this long journey, I was involved in many other committees of CIS including Fuzzy Systems Technical Committee, Nominations Committee, and Steering Committees of some CIS Co-sponsored publications. Apart from these, I have been very actively engaged in organizing CIS conferences and related activities.

What have you learned from your experience and how has it helped you professionally?

My association with CIS has been very enriching and rewarding professionally and beyond. CIS has given me opportunities to serve the scientific community in many ways beginning from a reviewer to an Associate editor of the IEEE Transactions on Fuzzy Systems to its Editor-in-Chief followed by the Vice President for Publications of CIS. This gave me a unique opportunity to learn every aspect of publications. I got the freedom to directly interact and learn from young researchers, top leaders in computational intelligence, as well as, from practitioners. CIS gave me ample opportunities to sharpen my skill in organizing events including conferences. Overall, CIS helped to make myself a more complete person.


What has been the most fun/rewarding thing about being a volunteer for the IEEE Computational Intelligence Society? What have you enjoyed the most?

The most fun and enjoyable part is the interaction with the CIS community, particularly with the volunteers. In our meetings, we argue on issues, sometimes we disagree or agree to disagree on issues, but once the meetings are over, we are again great friends. They are always there to stand by me in my crisis irrespective of whether it is a CIS one or a personal one. Without such nice people around, I could not have continued as an active volunteer of CIS for such a log time. Being a CIS volunteer, I am blessed with a fantastic set of friends.

Tell us something about you that we don’t know.

Most people “tag” me a “fuzzy researcher” but my living comes equally both from fuzzy sets and neural networks – interestingly, my first journal paper in the area of CI was on neural networks!

Whether I am sad or happy, listening to songs makes me happier, particularly the songs by my most favourite singer, Manna Dey. I like to watch cricket matches when India plays. And I still love watching old movies with Amitabh Bachchan, the mega star, as the hero.


Live Webinar

Generation Hyper-Heuristics for Automated Design, Configuration and Selection

Date: Tuesday, 22 March 2022
Time: 7:00 AM - 9:00 AM EDT


Automated algorithm design, configuration and selection of machine learning and search algorithms (AutoDes) has made an impact on computational intelligence contributing to the advancement of the field. Generation hyper-heuristics, while in some ways still in their infancy, have proven to be effective for AutoDes. The application of generation hyper-heuristics in AutoDes range from creating new heuristics and operators to generating components of algorithms. The webinar will present an overview of generation hyper-heuristics in AutoDes, highlighting the advances and challenges. The webinar will also highlight future research directions in this field. Read more


Featured Speaker

Prof. Nelishia Pillay
Prof. Nelishia Pillay

Nelishia Pillay is a Professor at the University of Pretoria, South Africa. She holds the Multichoice Joint-Chair in Machine Learning and SARChI Chair in Artificial Intelligence. She is chair of the IEEE Technical Committee on Intelligent Systems Applications, IEEE Task Force on Hyper-Heuristics and the IEEE Task Force on Automated Algorithm Design, Configuration and Selection.

Educational Activities

Call for 2022 Summer Schools Proposals

Important Dates

  • Eligible period: April 2022 to December 2022
  • Deadline for submitting the proposal: 1 April 2022 (late submissions may also be considered, but subject to the availability of the budget balance)
  • Notification of the outcome of the review process: 15 April 2022

You are encouraged to submit a proposal to hold a CIS summer school in Computational Intelligence from April to December 2022. If the proposal is approved, and upon request, CIS will provide a financial contribution to support the initiative. The amount of the financial support from CIS depends on the available budget, the number of financed proposals and the soundness of the school budget. We recall that organizers can take advantage of other initiatives, e.g., the CIS Distinguished Lecture Program to further support the school (related regulations apply). We encourage proposals to collocate summer schools with our CIS conferences.

The CIS Summer schools subcommittee will review received proposals based on the
following criteria:
1. The quality of the proposed technical program and topic balance;
2. The length of the school;
3. The geographical balance of the proposals.

In writing your proposal, please address the following aspects:
1. Aim and target.
2. Courses and lecturers.
3. Tentative program.
4. Local organizer(s).
5. Registration and accommodation.
6. School budget, financial sponsor(s) and requested co-finance from CIS.

A template for the proposals and more details can be found at the Summer School Subcommittee website.

Please send your completed documents to the Summer Schools Subcommittee Chair, Alexander Dockhorn, at [email protected], by the deadline.

2022 Graduate Student Research Grants: Call for Applications


The IEEE Computational Intelligence Society (CIS) funds scholarships for deserving undergraduate, graduate and PhD students who need financial support to carry out their research during an academic break period. The primary intent of these scholarships is to cover the expenses related to a visit to another university, institute, or research agency for collaboration with an identified researcher in the field of interest of the applicant. Funds can be used to cover travel expenses as well as certain living expenses (such as housing). The field of interest of applicants is open but should be connected with an identifiable component of the CIS (neural networks, fuzzy systems, or evolutionary computation). The call for the next round of applications will be announced soon and will have a deadline for submission of 15 March 2022.

More information on the scheme can be found on the CIS Graduate Student Research Grants webpage.

Editor Bing Xue
Victoria University of Wellington, New Zealand
Email: [email protected]

{{my.Comm Preferences:default=edit me}}