IEEE CIS  |  CIM  |  TNNLS  |  TEVC  |  TFS  |  TCDS  |  TETCI  |  TG  |  TAI
 
 
 
 
 
 
IEEE CIS Newsletter, Issue 100, May 2021
 
 
 
 
 
 
Announcements
 
 
 
 

IEEE CIS Bylaws and Constitution Update

On 7 April 2021, the CIS Administrative Committee approved a new version of the IEEE Computational Intelligence Society (CIS) Constitution and the IEEE CIS Bylaws. The goal of these revisions is to provide more effective governing documents for our expanding activities.

The changes with respect to the current versions mainly consist of editorial changes, which bring the documents into compliance with IEEE Technical Activities governance. The most significant modification is the addition of the Vice President for Industrial and Governmental Activities, its reporting structure, role, and responsibility.

According to our current Constitution, the above amendments to the Constitution, already approved by the Chair of the IEEE Technical Activities Board and posted on the CIS website since 13 April 2021, are now formally presented to the attention of all CIS Members. These Constitution amendments will go into effect unless ten percent of the CIS Members object in writing by 20 May 2021. Objections should be sent via email to the attention of the CIS President, at address [email protected] or via mail to IEEE Computational Intelligence Society, c/o Jo-Ellen Snyder, IEEE Operations Center, 445 Hoes Lane, Piscataway, NJ 08855-1331, USA.

In addition, the amended Bylaws are also presented to the attention of all CIS members for their information. 

 
 
 
 

Call for Nominations for Various Officers’ Positions and ADCOM Members-at-Large

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

Vice President for Conferences (2022-2023),

Vice President for Finances (2022-2023),

Vice President for Technical Activities (2022-2023), and

Five ADCOM Members-at-Large (2022-2024).

According to the CIS Bylaws, ARTICLE XI – GOVERNANCE AND ADMINISTRATION, Section 32 Schedule for ADCOM Elections:

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

"The election of Vice President for Conferences, Vice President for Finances, and Vice President for Technical Activities shall take place in odd-numbered years."

Eligibility requirements are defined in the CIS Bylaws, ARTICLE XIII – NOMINATIONS, ELECTIONS AND APPOINTMENTS. The nomination will close 15 May 2021.

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

 
 
 
 

Proposals to Organize CIS Flagship Conferences in 2024

We are looking for organizers for the IEEE CIS World Congress on Computational Intelligence (WCCI) and the IEEE CIS Symposium Series in Computational Intelligence (SSCI), both to take place in 2024. The proposals must be submitted by 31 May 2021. Please inform Marley Vellasco ([email protected]) and Gui DeSouza ([email protected]) of your intention to prepare a bid as soon as you decide to do so. Policies, procedures and budget worksheet for such proposals are available on our website.

Getting Involved in the Organization of CIS Conferences

Also, if you want to get involved in the organization of new or current CIS conferences, or if your industry wants to get involved in the CIS conferences in general or any particular one (e.g., co-sponsor, set booths, etc), please also contact Marley Vellasco ([email protected]) and Gui DeSouza ([email protected]). The CIS sponsors eleven small conferences and five mid-to-large conferences in topics ranging from CI in cyber security and defense, to smart world and robotics, not to mention the fundamentals of CI. For a list of past and upcoming CIS conferences, please check our conference calendar and keep in mind that the deadline for submitting proposals for small CIS conferences in 2023 is 30 September, 2021.

 
 
 
 
Research Frontier
 
 
 
 

A Survey on Learning-Based Approaches for Modeling and Classification of Human–Machine Dialog Systems

robot.JPGWith the rapid development from traditional machine learning (ML) to deep learning (DL) and reinforcement learning (RL), a dialog system equipped with a learning mechanism has become the most effective solution to address human–machine interaction problems. The purpose of this article is to provide a comprehensive survey on learning-based human–machine dialog systems with a focus on the various dialog models. More specifically, we first introduce the fundamental process of establishing a dialog model. Second, we examine the features and classifications of the system dialog model, expound some representative models, and also compare the advantages and disadvantages of different dialog models. Third, we comb the commonly used database and evaluation metrics of the dialog model. Furthermore, the evaluation metrics of these dialog models are analyzed in detail. Finally, we briefly analyze the existing issues and point out the potential future direction on the human–machine dialog systems. Read More

IEEE Transactions on Neural Networks and Learning Systems, April 2021

 
 
 
 

A Rapid Spiking Neural Network Approach With an Application on Hand Gesture Recognition


hands.JPGThe spiking neural network (SNN) is considered to be the third generation of neural networks featured by its low power consumption and high computing capability, which has great application potential in robotics. However, the present SNN has two limitations: 1) the neuron’s spike firing time is calculated based on the iterative approach, which dramatically slows down the calculation rate of the SNN and 2) the existing learning algorithm is more suitable for the single-layer structure, which can hardly train the network with “deep structure.” To this end, this paper proposes a novel spike firing time search algorithm that can narrow the search interval. In addition, a pretrained subnet SNN is designed, which makes the SNN have more hidden layers. This setting of the SNN can effectively improve its performance in pattern recognition tasks. Furthermore, by using the surface electromyography signal (sEMG), the proposed SNN is used to recognize the hand gestures. The experimental results show that: 1) the spike firing time search algorithm can significantly increase the forward propagation rate of the SNN and 2) the proposed SNN can reach a satisfactory recognition accuracy ratio 97.4%, which is 0.9% higher than that of the fully connected SNN. Read More


IEEE Transactions on Cognitive and Developmental Systems, March 2021

 
 
 
 

A Neural State Pushdown Automata


grammar-blocks.jpgTo learn complex formal grammars, recurrent neural networks (RNNs) require sufficient computational resources to ensure correct grammar recognition. One approach to expand model capacity is to couple an RNN to an external stack memory. Here, we introduce a "neural state" pushdown automaton (NSPDA), which consists of a discrete stack instead of an continuous one and is coupled to a neural network state machine. We empirically show its effectiveness in recognizing various context-free grammars (CFGs). First, we develop the underlying mechanics of the proposed higher order recurrent network and its manipulation of a stack as well as how to stably program its underlying pushdown automaton (PDA). We also introduce a noise regularization scheme for higher-order (tensor) networks and design an algorithm for improved incremental learning. Finally, we design a method for inserting grammar rules into a NSPDA and empirically show that this prior knowledge improves its training convergence time by an order of magnitude and, in some cases, leads to better generalization. The NSPDA is also compared to a classical analog stack neural network pushdown automaton (NNPDA) as well as a wide array of first and second-order RNNs with and without external memory, trained using different learning algorithms. Our results show that for the Dyck languages, prior rule-based knowledge is critical for optimization convergence and for ensuring generalization to longer sequences at test time. We observe that many RNNs with and without memory, but no prior knowledge, struggle to converge and generalize on complex and longer CFGs. Read More


IEEE Transactions on Artificial Intelligence, December 2020

 
 
 
 

From Prediction to Prescription: Evolutionary Optimization of Nonpharmaceutical Interventions in the COVID-19 Pandemic


covid-pills.jpgSeveral models have been developed to predict how the COVID-19 pandemic spreads, and how it could be contained with nonpharmaceutical interventions, such as social distancing restrictions and school and business closures. This article demonstrates how evolutionary AI can be used to facilitate the next step, i.e., determining most effective intervention strategies automatically. Through evolutionary surrogate-assisted prescription, it is possible to generate a large number of candidate strategies and evaluate them with predictive models. In principle, strategies can be customized for different countries and locales, and balance the need to contain the pandemic and the need to minimize their economic impact. Early experiments suggest that workplace and school restrictions are the most important and need to be designed carefully. They also demonstrate that results of lifting restrictions can be unreliable, and suggest creative ways in which restrictions can be implemented softly, e.g., by alternating them over time. As more data becomes available, the approach can be increasingly useful in dealing with COVID-19 as well as possible future pandemics. Read More


IEEE Transactions on Evolutionary Computation, April 2021

 
 
 
 

Evaluating Evolving Structure in Streaming Data With Modified Dunn's Indices


fiber-optics.JPGDunn's internal cluster validity index is used to assess partition quality and identify a “best” crisp c-partition of n objects built from static data sets. This index is quite sensitive to inliers and outliers in the input data, so a subsequent study developed a family of 17 generalized Dunn's indices that extend and improve the original measure in various ways. This paper presents online versions of two modified generalized Dunn's indices that can be used for the dynamic evaluation of an evolving (cluster) structure in streaming data. We argue that this method is a good way to monitor the ongoing performance of streaming clustering algorithms, and we illustrate several types of inferences that can be drawn from such indices. Streaming clustering algorithms are incremental, process incoming data points only once and then discard them, adapt as the data stream evolves, flag outliers, and most importantly, spawn new emerging structures. We compare the two new indices to the incremental Xie-Beni and Davies-Boudin indices, which to our knowledge offer the only comparable approach, with numerical examples on a variety of synthetic and real datasets. Read More


IEEE Transactions on Emerging Topics in Computational Intelligence, April 2021

 
 
 
 

Automated Video Game Testing Using Synthetic and Humanlike Agents


woman-glass.jpgIn this article, we present a new methodology that employs tester agents to automate video game testing. We introduce two types of agents—synthetic and humanlike—and two distinct approaches to create them. Our agents are derived from Sarsa and Monte Carlo tree search (MCTS) but focus on finding defects, while traditional game-playing agents focus on maximizing game scores. The synthetic agent uses test goals generated from game scenarios, and these goals are further modified to examine the effects of unintended game transitions. The humanlike agent uses test goals extracted by our proposed multiple greedy-policy inverse reinforcement learning (MGP-IRL) algorithm from tester trajectories. MGP-IRL captures multiple policies executed by human testers. We use our agents to produce test sequences, and run the game with these sequences. At each run, we use an automated test oracle to check for bugs. We analyze the proposed method in two parts—we compare the success of humanlike and synthetic agents in bug finding, and we evaluate the similarity between humanlike agents and human testers. We collected 427 trajectories from human testers using the General Video Game Artificial Intelligence (GVG-AI) framework and created three games with 12 levels that contain 45 bugs. Our experiments reveal that humanlike and synthetic agents compete with human testers’ bug finding performances. Moreover, we show that MGP-IRL increases the human likeness of agents while improving the bug finding performance. Read More


IEEE Transactions on Games, March 2021

 
 
 
 

TLPCM: Transfer Learning Possibilistic C-Means


word-cloud.JPGTraditional machine learning and data mining have made tremendous progress in many knowledge-based areas, such as clustering, classification, and regression. However, the primary assumption in all of these areas is that the training and testing data should be in the same domain and have the same distribution. This assumption is difficult to achieve in real-world applications due to the limited availability of labeled data. Associated data in different domains can be used to expand the availability of prior knowledge about future target data. In recent years, transfer learning has been used to address such cross-domain learning problems by using information from data in a related domain and transferring that data to the target task. In this article, a transfer-learning possibilistic c -means (TLPCM) algorithm is proposed to handle the PCM clustering problem in a domain that has insufficient data. Moreover, TLPCM overcomes the problem of differing numbers of clusters between the source and target domains. The proposed algorithm employs the historical cluster centers of the source data as a reference to guide the clustering of the target data. The experimental studies presented here were thoroughly evaluated, and they demonstrate the advantages of TLPCM in both synthetic and real-world transfer datasets. Read the paper and the errata and observations. Read more


IEEE Transactions on Fuzzy Systems, April 2021

 
 
 
 
Member Activities
 
 
 
 

IEEE CIS Pledges to Make Speaker Panels More Gender Balanced

WIE.jpg

IEEE Computational Intelligence Society pledges to work towards gender-diversified panels at all IEEE CIS meetings, conferences, and events. IEEE CIS supports the inclusion of a diverse set of speakers, which will lead to more creative, interesting and representative panels.

Bernadette Bouchon-Meunier, the IEEE Computational Intelligence Society’s 2020 and 2021 president, says the Society has a long tradition of supporting women in its field, and “is happy to take up the IEEE WIE pledge,” which the Society “has already put into practice in its own events and activities.” The Society’s Women in Computational Intelligence committee, for example, was created in 2004 to develop, promote, organize, and run activities directed to ensure equal opportunities to both genders in the Society as well as the computational intelligence arena. Since then, the WCI committee has organized receptions, talks, and panels at all the Society’s flagship conferences to highlight the achievements of women and to explain the problems they face in their professional lives, and to point out the necessity of having women involved in all aspects of the Society’s activities and conferences. Read More about the IEEE WIE Pledge.

 
 
 
 

Meet IEEE CIS Members



Meet: Sanaz Mostaghim, Vice President Member Activities



Wsanaz.JPGhat is your title, and place of work? (or Technical Field of Research)?


I am a professor of Computer Science and work at the Otto von Guericke University Magdeburg, Germany 


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


Since 2000, right after starting my PhD. Computational Intelligence is my research topic and it was very natural to join the CIS. 


What Computational Intelligence Society committee do you serve?


I have been working as a reviewer and a PC member for IEEE CIS conferences and Transactions since the early stages of my academic life. I am not lying if I say that so far I have reviewed several hundred papers. I have served and am serving several technical sub-committees, almost all of the member activity sub-committees and the conference committee. I was a member of the ADCOM for two terms. Currently I am VP for member activities.


What are some of the challenges you've faced as a volunteer?


Balancing the workload between the normal job life and the IEEE CIS activities. Usually as a volunteer we need to spend some of our free time in the evening or during the weekends and I do it with great pleasure. 



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


By being a reviewer, associate editor, and a committee member, I learned a lot about publishing, networking and scientific leadership. These experiences are really valuable for long term professional goals. Years ago when I was aiming for an academic career, all these activities helped to increase my visibility in national and international research communities.   


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


Networking, learning new research topics and supporting younger generations. 

I enjoy the Women in Computational Intelligence gatherings the most. 



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


An hour after I gave my first invited talk in Japan, a Tsunami warning was broadcasted and we had to evacuate the conference centre and the city!

 
 
 
 

Women in Computational Society (WCI) Corner

 

This month, Annabel Latham reports a conversation with one of our amazing Women in Computational Intelligence, Palina Bartashevich, who is a Doctoral Researcher at Otto-von-Guericke University Magdeburg, Germany.

 

Palina’s Mantra: “Never give up.”palina.JPG

Why did you choose to pursue a career in computational intelligence?

Everything started with my interest in physics, which transitioned into the profound study of mathematics for my bachelor's and master's degrees. During my studies, I did a semester abroad at Otto-von-Guericke University Magdeburg, Germany at the Faculty of Mathematics, where among other disciplines I studied Swarm Intelligence at the Faculty of Computer Science. I was fascinated by how taking inspiration from natural biological systems and using simple mathematical equations one can develop algorithms to solve optimisation problems that exact mathematical methods cannot, as well as how they can be applied in real-world applications such as robotics. It felt like the right place to put my skills as a mathematician to good use.

What is your research field, and why are you passionate about it?

My research is dedicated to the development of decentralised collective decision-making algorithms for artificial multi-agent systems. In particular, I study the consensus achievement problem and the problem of collective search in unknown environments with a lot of, even an infinite amount, of potential options, where environmental bias induces negative effects on the decision-making process by creating conflicting events to the agents' goals. The latter results in the eternal unsolved dilemma where one has to make sacrifices either in the quality or in the cost to achieve a desirable state, not knowing in advance what implications it can have on the global behaviour of the system.


What excites me researching these problems is seeing how, by acting together as a whole, the agents can jointly overcome challenges that seem to be unsolvable for a single individual. Even on the example of such artificial systems, one can see how each person’s decision and action in our society actually matters, such that everyone is important.

How have IEEE, CIS and WCI’s networks been valuable to you?

Thanks to these communities I was able to get traveling grants which helped me to publish my results in several international venues and to attend international conferences, allowing me to meet the pioneers in the field and to build up my professional network.


What does the future look like for your career and research?


I have always enjoyed studying new things and helping others, while academia provides a perfect environment for combining both. After my teaching experience and supervision of the students, I have also found out that explaining the scientific material can be even more enjoyable if it is based on your own works. Overall, answering the "new" questions was always much more interesting for me than the "old" ones. So in the future, I plan to continue further research of open problems in computer science and engineering.

What advice can you give to others looking to follow a similar path or field?

Research is an exciting roller coaster, it can be so rewarding to see when your idea is finally working and you have found something new which is, for that tiny moment, only known to you alone, or that feeling of seeing the journal paper that you have worked countless days and nights to finish, finally published. But the truth is that it all requires a lot of hard work and its own sacrifices even to get a small result while dealing most of the time with constant criticism and time pressure, which are inevitable parts of the academic system. So if you want to embrace this journey, choose a topic you are really passionate about, keep persistent and never give up!


Palina’s Webpage: https://ci.ovgu.de/Team/Palina+Bartashevich.html 

 
 
 
 

Live Webinar

Understanding the Complexity of Financial Systems of Systems

Date: Thursday, 20 May 2021
Time: 11:00 AM - 12:00 PM EDT

Abstract:

Why are the financial markets so problematical? One reason is that financial markets consist of many systems – having other complex systems as components – that interact in complicated ways. The focus of this webinar is to explain the complexity of several financial systems in terms of several properties that are characteristic of large, diverse, complex systems. We distill this framework for financial systems of systems to include properties describing interactions among other system components; properties relating to interactions within the system environment; and properties relating to interactions with time. In this webinar, we discuss how these properties impact financial systems involved with high frequency trading (connectivity vs. latency arbitrage); market fragmentation (autonomy vs. regulatory-induced feedback); and credit (model diversity vs. copula model risk).
 
 
 

Featured Speaker

 
Roy-Freedman.JPG
Prof. Roy S. Freedman

Dr. Freedman received a BS and MS in Mathematics, an MS in Electrical Engineering, and a PhD in Mathematics, all from the NYU Tandon School of Engineering (formerly Polytechnic University).

 
 
 
 
 
Educational  Activities
 
 
 
 


2021 Graduate Student Research Grant Winners


 

Research project title

Host institution and country

Aboutaib Brahim

Rigorous Analysis of Parallel Evolutionary Algorithms

University of Minnesota Duluth, USA

Yongwei Zhang

Adaptive dynamic programming for distributed consensus control of

nonlinear multi-agent systems

Politecnico di Milano, Italy

Najwa Kouka

EEG Channel Selection-based Binary Particle Swarm Optimization with Recurrent Convolutional Autoencoder for Emotion Recognition

UPEC – University PARIS-EST CRETEIL, LSSI (Laboratoire Images, Signaux et Systèmes Intelligents), France

Ziwei Wang

EEG-Based Children Epilepsy Prediction Using Transfer Learning

Huazhong University of Science and Technology, Wuhan, China

 
 
 
 

Kaggle Challenge: Telecom System Reconciliation on high dimensional datasets Predict the correct configuration of the Billing system based on CRM configuration. For more information please visit the Kaggle Website.

 
 
 
 

Summer School on Data-Driven Predictive Maintenance for Industry 4.0. For more information please visit the PM Summer School website

 
 
 
 
Journal Special Issues
 
 
 
 
 
 
 
 
CIS Conferences
 
 
 
 
Due to the outbreak of the COVID-19 pandemic, dates and details of CIS sponsored conferences should be monitored closely.

The situation is changing very quickly. Please consult the conference web pages frequently to obtain the latest information.

You can find the most recent announcements and updates from all of our Society’s conferences and events at https://cis.ieee.org/volunteer-resources/covid-19-notice as our organizers make decisions.
 
 

Call for Tutorials and Special Sessions


IEEE Symposium Series on Computational Intelligence (SSCI) 2021, 4 - 7 December 2021, Orlando, Florida

We would like to invite you to join the IEEE SSCI 2021 which will be held as a hybrid event. For more information regarding the calls for the tutorials and special sessions (Deadline 28 May 2021) please take a look at: 

Tutorials: https://attend.ieee.org/ssci-2021/tutorials/

Special Sessions: https://attend.ieee.org/ssci-2021/special-sessions/ 


SSCI2021.JPG


* Denotes a CIS-Sponsored Conference

∆ Denotes a CIS Technical Co-Sponsored Conference


* 2021 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (IEEE CIVEMSA 2021)

18-20 June 2021

Place: Virtual

General Co-Chairs: Yong Hu, Guanglin Li, Angelo Genovese 

Website: https://civemsa2021.ieee-ims.org/

 

* 2021 IEEE Congress on Evolutionary Computation (IEEE CEC 2021)

28 June - 1 July 2021

Place: Kraków, Poland

General Co-Chairs: Jacek Mańdziuk and Hussein Abbass

Website: https://cec2021.mini.pw.edu.pl

Will be a virtual conference

 

* 2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2021)

11-14 July 2021

Place: Luxembourg, Luxembourg

General Co-Chairs: Christian Wagner and Holger Voos

Website: https://attend.ieee.org/fuzzieee-2021/

Will be a virtual conference



* 2021 IEEE International Conference on Development and Learning (ICDL)

23-26 August 2021

Place: Beijing, China

General Co-Chairs: Dingsheng Luo and Angelo Cangelosi

Website: https://icdl-2021.org



* 2021 IEEE Conference on Games (IEEE CoG 2021)

17-20 August 2021

Place: Copenhagen, Denmark

General Co-Chairs: Miguel Sicart & Paolo Burelli

Website: https://ieee-cog.org/2021/index.html


∆ 2nd International Conference on Industrial Artifical Intelligence (IAI2021)

20-22 August 2021

Place: Shenyang, China

General Chair: Yaochu Jin

Website: TBC



∆ 2021 International Conference on Emerging Techniques in Computational Intelligence (ICETCI 2021)

25-27 August 2021

Place: Hyderabad, India

General Chair: Atul Negi, Naresh Mallenahalli, Akira Hirose

Website: http://ietcint.com


∆ 6th South-East Europe Design Automation, Computer Engineering, Computer Networks and Social Media Conference (SEEDA CECNSM 2021)

24-26 September 2021

Place: Preveza, Greece

General Co-Chairs: Markos G. Tsipouras, Alexandros T. Tzallas, Michael F. Dossis 

Full paper submission deadline: 31 May 2021


* 2021 IEEE International Conference on Data Science and Advanced Analytics (IEEE DSAA 2021)

6-9 October 2021

Place: Porto, Portugal

General Co-Chairs: João Gama & Francisco Herrera

Website: https://dsaa2021.dcc.fc.up.pt/

Full paper submission deadline: 23 May 2021


* 2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)

13-15 October 2021

Place: Melbourne, Australia

General Chairs: Madhu Chetty

 

* 2021 IEEE Smart World Conference (IEEE SWC 2021)

18-21 October 2021

Place: Atlanta, USA

General Co-Chairs: Yi Pan, Rajshekhar Sunderraman, Yanqing Zhang

Website: http://ieeesmartworld.org/


 

∆ 2021 International Conference on Process Mining (ICPM 2021)

31 October - 4 November 2021

Place: Campus of Eindhoven University of Technology, The Netherland

General Co-Chairs: Boudewijn van Dongen 

 

* 2021 IEEE Latin American Conference on Computational Intelligence (LA-CCI)

2-5 November 2021

Place: Temuco, Chile

General Co-Chairs: Millaray Curilem and Doris Saez

Website: http://la-cci.org/


  

* 2021 IEEE Symposium Series on Computational Intelligence (IEEE SSCI 2021)

5-8 December 2021

Place: Orlando, FL, USA

General Co-Chairs: Sanaz Mostaghim and Keeley Crockett

Website: https://attend.ieee.org/ssci-2021/

 
 
 
CIS sponsors and co-sponsors a number of conferences across the globe. 
 
 
 
 
 
 
Editor Bing Xue
Victoria University of Wellington, New Zealand
Email: [email protected]

 
 
 
 
 
 
If you have an IEEE Account, manage your IEEE communications preferences here. Users without an IEEE Account can access the Privacy Portal to view selected preferences and policies.