Congratulations to Chang-Shing Lee, IEEE Educational Activities Board (EAB) Meritorious Achievement Award in Pre-University Education

IEEE CIS is proud to announce that IEEE Educational Activities has selected our 2022 High School Outreach Subcommittee Chair, Chang-Shing Lee, to receive the Meritorious Achievement Award in Pre-University Education "for sustained contributions in promoting Computational and Artificial Intelligence among pre-university students." The Meritorious Achievement Award in Pre-University Education recognizes individuals for work in a pre-university school, or those that influence school-based activities for pre-university students. These individuals should have inspired an appreciation and understanding of mathematics, science, technology, and the engineering process in pre-university students, and have encouraged them to pursue technical careers.

Professor Lee has been instrumental in exposing pre-university students in Taiwan to computational intelligence (CI) and artificial intelligence–fuzzy markup language (AI-FML) for human and machine co-learning. He successfully inspired and encouraged high school students to attend these courses, and those students have successfully applied to engineering-related university programs based on their experience studying CI&AI-FML. More than 2,700 participants from Taiwan, Japan, and Indonesia experienced and learned CI&AI-FML applications thanks to his efforts and contributions.

Click here for more information about the High School Outreach Subcommittee.

Call for IEEE CIS Distinguished Lecturers Nominations

The IEEE CIS Distinguished Lecturer Program (DLP) aims at serving the Computational Intelligence community by providing stimulating lectures given by distinguished IEEE CIS professionals and scholars. It also aims at helping young researchers (masters and doctoral students) providing suggestions/guidance on their research problems as well as promoting computational intelligence tools and techniques among undergraduate students to make them interested in CIS fields of interest.

Distinguished Lecturers present novel basic and/or applied research results in their CIS sub-field. Their lectures offer insights into the trends and challenges of their CIS sub-field and their vision for the given sub-field. In any given year, selected IEEE CIS Distinguished Lecturers (DLs) have a balanced representation of CIS sub-fields and include representatives from academia, industry and government while spanning different IEEE Regions. The program supports local CIS Chapters by enabling a major Chapter event which can considerably improve a Chapter’s visibility to their existing IEEE CIS members, other IEEE Society members and the wider CIS community in their area. It is expected that DLP events actively seek to recruit new CIS professionals to both the CIS field and to IEEE CIS.

It should be noted that this program is NOT intended as a means to finance speakers for conferences/workshops or symposia.

For more information please visit the organizing distinguished lecturers webpage. 

---

Call for the IEEE CIS Distinguished Lecturers Nomination

The IEEE CIS DLP Sub-Committee shall evaluate the relevant values and merits of each nominee using both qualitative and quantitative evidence. The quantitative measures indicated in section III.1 are part of the input to be considered by the committee. Other criteria include, but are not limited to, qualitative assessments of the nominees work, geographical lecturer distribution requirements, or the need to include lecture topics that would not be, otherwise, well represented. The committee may consider exceptions to these criteria on a case by case basis.

Deadline: 30 August 2022

For more information please visit the nomination and appointment distinguished lecturers webpage. 

Deadlines for 2024 IEEE CIS Financially-sponsored Conference Proposals

Chairing a conference is a great way of helping the community, building a network, and getting involved with IEEE CIS. CIS financially (co-) sponsors many conferences. These include:

• 2024 IEEE Conference on Games (IEEE CoG 2024) associated with the Games Technical Committee
• 2024 IEEE Conference on CI in Bioinformatics and Computational Biology (IEEE CIBCB 2024) associated with the Bioinformatics and Bioengineering Technical Committee
• 2024 IEEE Symposium on CI in Financial Engineering and Economics (IEEE CIFEr 2024) associated with the Computational Finance and Economics Technical Committee
• 2024 IEEE Latin American Conference on Computational Intelligence (IEEE LA-CCI 2024) associated with the Task Force on Computational Intelligence in Latin America
• 2024 IEEE Smart World Conference (IEEE SWC 2024) associated with the Smart World Technical Committee
• 2024 IEEE International Conference on Development and Learning (IEEE ICDL 2024) associated with the Cognitive and Developmental Systems Technical Committee
• 2024 IEEE International Conference on Data Science and Advanced Analytics (IEEE DSAA 2024) associated with the Data Mining and Big Data Analytics Technical Committee
• 2024 IEEE Evolving and Adaptive Intelligent Systems Conference (IEEE EAIS 2024) a co-sponsored event with IEEE Systems, Man, and Cybernetics Society and associated with the Adaptive and Evolving Fuzzy Systems Task Force of the Fuzzy Systems Technical Committee
• 2024 IEEE Conference on CI and Virtual Environments for Measurement Systems and Applications (IEEE CIVEMSA 2024), a co-sponsored event with IEEE Instrumentation and Measurement Society and associated with the CIVEMSA Steering Committee

Proposals for these conferences should be submitted by 30 August 2022 (hard deadline) to provide sufficient time for review and decision by IEEE CIS Confcom and Adcom. This also helps the society maintain its required two year horizon for approved conferences.

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. We look forward to receiving your proposals and appreciate your support and effort on behalf of our conferences.

Privacy-Preserving Deep Learning With Homomorphic Encryption: An Introduction

Privacy-preserving deep learning with homomorphic encryption (HE) is a novel and promising research area aimed at designing deep learning solutions that operate while guaranteeing the privacy of user data. Designing privacy-preserving deep learning solutions requires one to completely rethink and redesign deep learning models and algorithms to match the severe technological and algorithmic constraints of HE. This paper provides an introduction to this complex research area as well as a methodology for designing privacy-preserving convolutional neural networks (CNNs). This methodology was applied to the design of a privacy-preserving version of the well-known LeNet-1 CNN, which was successfully operated on two benchmark datasets for image classification. Read More

IEEE Computational Intelligence Magazine, July 2022

Reward-Reinforced Generative Adversarial Networks for Multi-Agent Systems

Multi-agent systems deliver highly resilient and adaptable solutions for common problems in telecommunications, aerospace, and industrial robotics. However, achieving an optimal global goal remains a persistent obstacle for collaborative multi-agent systems, where learning affects the behaviour of more than one agent. A number of nonlinear function approximation methods have been proposed for solving the Bellman equation, which describe a recursive format of an optimal policy. However, how to leverage the value distribution based on reinforcement learning, and how to improve the efficiency and efficacy of such systems remain a challenge. In this work, we developed a reward-reinforced generative adversarial network to represent the distribution of the value function, replacing the approximation of Bellman updates. We demonstrated our method is resilient and outperforms other conventional reinforcement learning methods. This method is also applied to a practical case study: maximising the number of user connections to autonomous airborne base stations in a mobile communication network. Read More

Transactions on Emerging Topics in Computational Intelligence, June 2022

Incremental Feature Selection Using a Conditional Entropy Based on Fuzzy Dominance Neighborhood Rough Sets

Incremental feature selection approaches can improve the efficiency of feature selection used for dynamic datasets, which has attracted increasing research attention. Nevertheless, there is currently no work on incremental feature selection approaches for dynamic ordered data. Moreover, the monotonic classification effect of ordered data is easily affected by noise, so a robust feature evaluation metric is needed for feature selection algorithm. Motivated by these two issues, we investigate incremental feature selection approaches using a new conditional entropy with robustness for dynamic ordered data in this study. First, we propose a new rough set model, i.e., fuzzy dominance neighborhood rough sets (FDNRS). Second, a conditional entropy with robustness is defined based on FDNRS model, which is used as evaluation metric for features and combined with a heuristic feature selection algorithm.  Read more

IEEE Transactions on Fuzzy Systems, June 2022

Generalized Zero-Shot Learning With Multiple Graph Adaptive Generative Networks

Generative adversarial networks (GANs) for (generalized) zero-shot learning (ZSL) aim to generate unseen image features when conditioned on unseen class embeddings, each of which corresponds to one unique category. Most existing works on GANs for ZSL generate features by merely feeding the seen image feature/class embedding (combined with random Gaussian noise) pairs into the generator/discriminator for a two-player minimax game. However, the structure consistency of the distributions among the real/fake image features, which may shift the generated features away from their real distribution to some extent, is seldom considered. In this paper, to align the weights of the generator for better structure consistency between real/fake features, we propose a novel multigraph adaptive GAN (MGA-GAN). Specifically, a Wasserstein GAN equipped with a classification loss is trained to generate discriminative features with structure consistency. Read More

IEEE Transactions on Neural Networks and Learning Systems, July 2022

PSO-X: A Component-Based Framework for the Automatic Design of Particle Swarm Optimization Algorithms

The particle swarm optimization (PSO) algorithm has been the object of many studies and modifications for more than 25 years. Ranging from small refinements to the incorporation of sophisticated novel ideas, the majority of modifications proposed to this algorithm have been the result of a manual process in which developers try new designs based on their own knowledge and expertise. However, manually introducing changes is very time consuming and makes the systematic exploration of all the possible algorithm configurations a difficult process. In this article, we propose to use automatic design to overcome the limitations of having to manually find performing PSO algorithms. We develop a flexible software framework for PSO, called PSO-X, which is specifically designed to integrate the use of automatic configuration tools into the process of generating PSO algorithms. Our framework embodies a large number of algorithm components developed over more than 25 years of research that have allowed PSO to deal with a large variety of problems, and uses irace, a state-of-the-art configuration tool, to automatize the task of selecting and configuring PSO algorithms starting from these components. Read More

IEEE Transactions on Evolutionary Computation, June 2022

• IEEE CIM Special Issue on Machine Learning Assisted Evolutionary Multi-objective Optimization (1 September 2022)
• IEEE TNNLS Special Issue on Explainable and Generalizable Deep Learning for Medical Imaging (1 September 2022)
• IEEE TNNLS Special Issue on Explainable Representation Learning-based Intelligent Inspection and Maintenance of Complex Systems (1 September 2022)
• IEEE TCDS Special Issue on Cognitive Learning of Multi-Agent Systems (30 September 2022)
• IEEE TNNLS Special Issue on Information Theoretic Methods for the Generalization, Robustness and Interpretability of Machine Learning (1 October 2022)
• IEEE TNNLS Special Issue on Deep Learning for Intelligent Media Computing and Applications (30 October 2022)
• IEEE TETCI Special Issue on Resource Sustainable Computational and Artificial Intelligence (1 February 2023)
• IEEE TCDS Special Issue on Movement Sciences in Cognitive Systems (6 January 2023)
• IEEE TCDS Special Issue on Advancing Machine Intelligence with Neuromorphic Computing (31 January 2023)