CFP: IEEE CIM Special Issue on CI for Internet of Things in the Big Data Era (Dec 31)

 AIMS AND SCOPE

Emerging Internet of Things (IoT) applications in various fields, including smart city, smart home, smart grid, e-health, smart transportation, computer vision applications, etc., critically require trustworthy networking solutions that are resilient against disturbances and disruptions, including high mobility, high density, disasters, infrastructure failures, cyberattacks, and other disruptions. The networking framework should be capable of providing more secure, reliable and efficient communications in various network environments, especially for the performance-sensitive and mission-critical applications such as remote surgery and autonomous driving.

Two main challenges exist in enforcing trustworthy IoT. The first challenge comes from the spatial diversity of the entities involved in communications, such as the high mobility of the devices, and the limitations of propagation media and other resources. The second challenge is due to the varying temporal features of the environment. Due to the spatial challenges, the connectivity between network nodes could be unreliable, and therefore the information maintained at each node could be inaccurate, which requires trustworthy solutions that are able to handle the dynamic, imprecise and uncertain information. This can be solved by using computational intelligence (CI) technologies such as fuzzy logic and evolutionary computation. On the other hand, Big Data-based approaches, including deep neural networks, could facilitate data-driven prediction and performance improvement by capturing time-dependent properties of network elements such as user traffic and behaviors. However, the IoT data can be highly dimensional, heterogeneous, complex, unstructured and unpredictable. The integration of two new technologies, namely IoT and Big Data, gives birth to a novel ecosystem, conveniently called IoT Big Data, which calls for novel CI technologies to provide efficient and powerful tools that scale well with massive data volume analytics and processes, while addressing the challenges brought by the massive amount of data. In short, while CI technologies can achieve a flexible and self-evolving system design, Big Data can facilitate the use of deep neural networks through which learning the best strategy from complex data becomes possible.

This special issue will focus on the technical challenges and the synergistic effect of Big Data and CI for trustworthy IoT. It is envisioned that the combination of Big Data with a large collection of CI algorithms will reach the level of true artificial intelligence in IoT. We invite researchers to contribute their original research articles that will facilitate the development of IoT based on CI and big data technologies, including (but not limited to):

• Artificial neural networks for IoT Big Data
• CI for trustworthy IoT
• CI for mobile edge computing
• CI for wireless networking
• CI for security in IoT systems
• CI for sensor and actuator networks
• CI for IoT applications
• Convolutional neural networks for IoT
• Crowdsourced learning for IoT
• Data-driven IoT with CI
• Deep neural networks for trustworthy IoT
• Deep reinforcement learning for IoT
• Development of CI for IoT environments
• Domain adaptation for IoT Big Data
• Evolutionary computing for IoT Big Data
• Evolutionary models for IoT Big Data
• Fuzzy logic for IoT Big Data
• Learning theory for IoT Big Data
• Machine learning for IoT Big Data
• Probabilistic methods for IoT Big Data
• Recurrent neural networks for IoT
• Sequence-to-sequence learning for IoT Big Data 

IMPORTANT DATES

Submission Deadline: December 31st, 2018

Notification of the First Review Results: March 15th, 2019

Submission of Revised Manuscripts: April 15th, 2019

Notification of Second Review Results: May 15th, 2019

Submission of Final Manuscript: June 15th, 2019

Special Issue Publication: November 2019 Issue

GUEST EDITORS

Dr. Celimuge Wu, The University of Electro-Communications, Japan, celimuge@uec.ac.jp

Dr. Guoliang Xue, Arizona State University, USA, xue@asu.edu

Dr. Jie Li, University of Tsukuba, Japan, lijie@cs.tsukuba.ac.jp

Dr. Kok-Lim Alvin Yau, Sunway University, Malaysia, koklimy@sunway.edu.my

Dr. Junaid Qadir, Information Technology University, Pakistan, junaid.qadir@itu.edu.pk

SUBMISSION INSTRUCTIONS

1. The IEEE Computational Intelligence Magazine requires all prospective authors to submit their manuscripts in electronic format, as a PDF file. The created PDF file must be a single file for the complete submitted paper, including figures and bibliography. Before the manuscript is submitted, prospective authors should make sure that the PDF file is (1) printable, and (2) its first page contains the title, authors' names and the corresponding author's email address, abstract, and up to 5 keywords. Additional information about submission guidelines and information for authors is provided at the IEEE CIM website. Submission should be made via https://easychair.org/conferences/?conf=ieeecimsiiot2019.

2. Send also an email to guest editor C. Wu (celimuge@uec.ac.jp) 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 TETCI Special Issue on Privacy and Security in Computational Intelligence (Nov 30)

I. AIM AND SCOPE

  The advance in the state-of-the-art computing paradigms and infrastructure such as cloud computing, Internet of Things (IoT) and their fusion fog computing, has enabled a variety of large-scale applications where big data are collected, transmitted, stored, processed and mined. Unlocking the value of the data plays the key role in the data lifecycle. Computational intelligence (CI) technologies are an effective and important way to extract the intelligence and knowledge from datasets for data-driven decision-makings. Given that CI methods are usually both data- and computation-intensive, leveraging the large-scale computing paradigms and infrastructure empowers CI methods to handle data at a very large scale for deeper or personalized intelligence and insights. A typical example is the recent boom of deep learning research which is significantly enhanced by the development of massive computational power.

  However, the characteristics of the state-of-the-art computing paradigms and infrastructural platforms, such as ubiquitous access and multi-tenancy, pose unprecedented privacy and security threats on the computing infrastructure for CI and the application of CI in real problems, rendering users more vulnerable to privacy leakage and security attacks. It is necessary to keep privacy and security concerns in mind when implementing hardware (e.g., Intel’s neural networks processor instructions) and platforms for CI, designing CI algorithms, and deploying CI applications. Hence, it is the high time to investigate the privacy and security issues related to CI in the era of big data and cloud/fog computing.

  This special issue aims to present the most recent advances in the privacy and security research related to CI, particularly in (1) secure and privacy hardware and platforms to support CI technologies, (2) innovative secure and privacy CI algorithms for data mining and knowledge discovery, as well as (3) novel CI methods that strengthen privacy and security technologies.

II. TOPICS

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

• Secure and large-scale systems and platforms supporting computational intelligence paradigms
• Privacy-preserving and anonymization technologies for computational intelligence
• Computational intelligence paradigm implementation across private/public computing systems/platforms
• Information security and privacy theories from computational intelligence perspectives
• Computational intelligence techniques for cyberspace intrusion detection systems
• Computational intelligence for digital forensics
• Computational intelligence for risk management
• Computational intelligence for data-driven cyberspace security and information privacy
• Real-world applications of computational intelligence for privacy and security

III. SUBMISSIONS

Manuscripts should be prepared according to the“Information for Authors” section of the journal(http://cis.ieee.org/ieee-transactions-on-emerging-topics-in-computational-intelligence.html) and submissions should be done through the journal submission website: https://mc.manuscriptcentral.com/tetci-ieee, by selecting the Manuscript Type of “Privacy and Security in Computational Intelligence” and clearly marking “Privacy and Security in Computational Intelligence Special Issue Paper” as commentsto the Editor-in-Chief. Submitted papers will be reviewed by at least three different reviewers. Submission of a manuscript implies that it is the authors’ original unpublished work and is not being submitted for possible publication elsewhere.

IV. IMPORTANT DATE

• Paper submission deadline: November 30, 2018
• Notice of the 1st round review results: March 01, 2019
• Revision due: May 31, 2019
• Final notice of acceptance/reject: August 30, 2019

V. GUEST EDITORS

• Yuan Yuan, Michigan State University, US, yyuan@msu.edu; yyxhdy@gmail.com
• Xuyun Zhang, University of Auckland, New Zealand, xuyun.zhang@auckland.ac.nz
• Jie Tang, Tsinghua University, China, jietang@tsinghua.edu.cn

CFP: IEEE TETCI Special Issue on Big Data and Computational Intelligence for Agile Wireless IoT (Oct 15)

I. AIM AND SCOPE

  Wireless networking technology is one of the main components that could empower a wide range of Internet-of- Things (IoT) applications including smart city, smart home, smart grid, e-health, smart transportation, etc. While providing an easily extensible solution for information exchange, wireless networks also have brought some crucial challenges due to the unstable characteristics of wireless communications.

  The first challenge, namely the spatial challenge, comes from the massive number of spatially-spread connected static or mobile devices affected by the limitations and disruptions of the operating environment, including propagation media, disasters, infrastructure failures, and so on. The second challenge, namely the temporal challenge, is due to the time evolution of the temporal features, such as the varying traffic rates, different quality-of-service requirements, and the state changes of the operating environment. Both spatial and temporal challenges can possibly be solved by using Computational intelligence (CI) technologies such as fuzzy logic, artificial neural networks, evolutionary computation, learning theory, probabilistic methods, and so on. On the other hand, big data-based approaches, including deep neural networks and Long Short- Term Memory networks, could facilitate data-driven prediction and performance improvement by capturing time-dependent properties of network elements such as user traffics and behaviors. Meanwhile, new CI technologies should be discussed in order to handle the large volume of IoT big data from various types of devices with different generation speeds and characteristics.

  The design and the operation of a wireless network can benefit from data collected from widely deployed sensors, network devices, social networks, and other sources to address the spatial and temporal challenges. We refer collectively to these data sources as “IoT big data” for convenience. These data can be highly dimensional, heterogeneous, complex, unstructured and unpredictable. The ready availability of IoT big data and the immense dividends on offer motivate a strong interest both in academia and in industry towards solving some of the vexing challenges that stand in the way of leveraging IoT big data to advance the state of the art in wireless network operations and applications.

  CI technologies are expected to provide efficient and powerful tools that scale well with data volume for IoT big data analytics and process, while addressing the challenges brought by the massive amount of data. While CI technologies can achieve a flexible and self-evolving system design, big data can facilitate the use of deep neural networks which is possible to learn the best strategy from complex data. It is envisioned that the combination of IoT big data with a large collection of CI algorithms will reach the level of true agility in wireless IoT.

II. TOPICS

  This special issue focuses on solutions that can synergistically leverage techniques and insights from the domains of big data and CI to resolve the spatial and temporal challenges in wireless IoT, thereby significantly advancing the state of the art in design, operation, and analysis of data-driven wireless IoT. Topics of interest include, but are not limited to:

• CI-based solutions for spatial & temporal challenges in wireless IoT, including propagation challenges, MAC & routing problems, mobile edge computing issues, disasters, and infrastructure failures.
• Data-driven prediction and performance improvement for wireless IoT including deep neural networks, Long Short-Term Memory networks, etc.
• Joint neural networks and learning approaches, such as deep reinforcement learning, for addressing challenges in wireless IoT.
• CI technologies for handling a large volume of wireless IoT big data.
• Learning new flexible and self-evolving strategies for resource allocation, network management and planning by analyzing wireless IoT big data with CI.

III. IMPORTANT DATES

• Manuscript submission: October15,2018.
• Notification of authors:  January 15, 2019.
• Revised manuscripts due: March 15, 2019.
• Final editorial decision: May15,2019.

IV. SUBMISSION GUIDELINES

  Manuscripts should be prepared according to the “Information for Authors” section of the journal and submissions should be done through the journal manuscript submission system https://mc.manuscriptcentral.com/tetci-ieee, by selecting the Manuscript Type of “Big Data and Computational Intelligence for Agile Wireless IoT” and clearly marking “Special Issue on Big Data and Computational Intelligence for Agile Wireless IoT” as comments to the Editor-in-Chief.

V. GUEST EDITORS

• Celimuge Wu,  The University of Electro-Communications, Japan, celimuge@uec.ac.jp
• Yaochu Jin, University of Surrey, United Kingdom, yaochu.jin@surrey.ac.uk
• Jie Li, University of Tsukuba, Japan, lijie@cs.tsukuba.ac.jp
• Kok-Lim Alvin Yau, Sunway University, Malaysia, koklimy@sunway.edu.my
• Junaid Qadir, Information Technology University, Pakistan, junaid.qadir@itu.edu.pk

CFP: IEEE TEVC Special Issue on Parallel Evolution for Large Scale Optimization (Nov 1)

I. AIM AND SCOPE

Human societies have entered a new era of intelligent tech- nology, where machines, information, and humans are tightly coupled in the large scale cyber-physical-social spaces (CPSS). As a result, a lot of large-scale problems, such as optimization and learning, are emerging with the aim to explore and exploit of the physical world, mental world and virtual world. With the dramatic advances in big data analytics, communications, computing and data storage, it is expected that Evolutionary Computation (EC), as a powerful approach to complex prob- lems, would play an even more important role in CPSS. This could be achieved through advances in several aspects, such as developing more powerful EC techniques for large-scale optimization problems, bridging EC and emergent techniques in CPSS (e.g., the theory and methods of parallel systems) to offer new mechanisms for managing and controlling complex systems that involve complexity issues of both engineering and social dimensions, and building large-scale evolution systems that are capable of describing, predicting and prescribing the evolution of real-world complex systems. This special issue aims at promoting the development of EC in the above aspects.

II. THEMES

Researchers are encouraged to submit their latest inves- tigations on EC, either fundamental advances or practical cases, for large-scale problems as well as systems to the special issue. In addition to advancements of EC for large- scale optimization, learning and other challenging problems that arise in complex systems, research on building large-scale evolutionary systems for simulation, management and control of cyber-physical-social systems are most welcome as well.

Topics of interest include (but are not limited to):

• Evolutionary Computation for Large-Scale Optimization Problems;
• Evolutionary Computation for Large-Scale Learning Problems;
• Evolutionary Computation for Complex Systems;
• Evolutionary Computation for Optimal Management and
• Control in CPSS;
• Theoretical Analysis on Evolutionary Computation for
• Large-Scale Problems and Systems;
• Adaptation and Learning Mechanisms for large-scale
• evolutionary systems;
• Parallel Evolutionary Computation Techniques;
• New Implementation Technologies of Evolutionary Computation for Emerging Large-Scale problems;
• New Trends for Evolutionary Computation in Large Scale Optimization.

III. SUBMISSION

  Manuscripts should be prepared according to the “In- formation for Authors” section of the journal found at http://cis.ieee.org/ieee-transactions-on-evolutionary-computation/.

  Please submit your manuscript in electronic form through: http://mc.manuscriptcentral.com/tevc-ieee/, by selecting “PEforLSO Special Issue Papers” as theManuscript Type. Also, please indicate “PEforLSO Special Issue Paper” in the comments to the Editor-in-Chief.

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

IV. IMPORTANT DATES

Submission open: May 15, 2018

Submission deadline: November 1, 2018

Tentative publication date: 2019

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

V. GUEST EDITORS

• Fei-Yue Wang, The State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences, China, and Qingdao Academy of Intelligent Industries, China

feiyue.wang@ia.ac.cn

• Qinglai Wei, The State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences, China

qinglai.wei@ia.ac.cn

• Ke Tang, Department of Computer Science and Engineering, Southern University of Science and Technology, China tangk3@sustc.edu.cn

• Carlos A. Coello Coello, Department of Computer Science, CINVESTAV-IPN, Mexico

ccoello@cs.cinvestav.mx

CFP: IEEE TETCI Special Issue on Computational Intelligence for Cellular/Wireless Communications and Sensing (Oct 1)

I. AIM AND SCOPE

  As billions of phones, appliances, drones, traffic lights, security systems, environmental sensors, radars, and other radio-connected sensing and communication devices sum into a rapidly growing Internet of Things (IoT), many challenges such as spectrum allocation and efficiency, energy efficiency, security, have emerged as urgent topics to be solved. For example, 5G wireless communications will be deployed in the 28GHz, 37GHz, 39GHz frequency band, which may co-exist with radars and other sensing devices. Quite often, researchers often handle these challenges using traditional approaches such as game theory, convex optimization, etc. Computational intelligences techniques such as fuzzy systems, evolutionary computing, neural networks and learning systems are capable of handling resources allocation, decision making, where uncertainties abound, so it is very natural to apply computational intelligence to the above challenges in cellular/wireless communications and sensing.  There are four important differences that make the emerging topics in Computational Intelligence for Cellular/Wireless Communications and Sensing (CICCS) unique.

1. 1)  Compared to traditional communication and sensing problems, the RF data rate is much higher in the emerging area of communication and sensing which means real-time decision such as resource allocation or signal detection should be made much faster based on computational intelligence.
2. 2)  The operating frequencies are much higher and users are heterogeneous.
3. 3)  RF waveforms are typically captured and represented as complex numbers, underscoring the importance of both amplitude and phase of the signal. Although there has been interest recently in complex-valued neural networks, the technology for learning naturally in the complex plane is not fully developed and relies on treating complex variables as two real numbers.
4. 4)  The integration of communication and sensing is highly desirable because the communication and sensing modules are often co-located such as in smart phones, and they may be operated in the same frequency band.

II. TOPICS

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

• New computational intelligence models for communications and sensing
• Computational intelligence for 5G Communications Wireless
• Computational intelligence for IoT
• Computational intelligence for sensor networks
• Computational intelligence for remote sensing
• Computational intelligence for spectrum efficiency
• Computational intelligence for energy efficiency
• Computational intelligence for radars
• Computation intelligence for radar and communications co-existence
• Computational intelligence for integration of communications and sensing

III. SUBMISSIONS

Manuscripts should be prepared according to the “Information for Authors” section of the journal (http://cis.ieee.org/ieee-transactions-on-emerging-topics-in-computational-intelligence.html) and submissions should be done through the journal submission website: https://mc.manuscriptcentral.com/tetci-ieee, by selecting the Manuscript Type of “Computational Intelligence for Cellular/Wireless Communications and Sensing (SI:CICCS)” and clearly marking “Computational Intelligence for Cellular/Wireless Communications and Sensing (SI: CICCS) 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.

IV. IMPORTANT DATES

Paper submission deadline: October 1, 2018

Final notice of acceptance/reject: February 1, 2019

V. GUEST EDITORS

Qilian Liang, University of Texas at Arlington, USA;

liang@uta.edu

Gary Yen, Oklahoma State University, USA;

gyen@okstate.edu

Tariq S. Durrani, University of Strathclyde, UK;

durrani@strath.ac.uk

Wei Wang, Tianjin Normal University, China;

weiwang@tjnu.edu.cn

Xin Wang, Qualcomm Inc, USA;

xinwng@qca.qualcomm.com

CFP: IEEE TFS Special Issue on Deep Fuzzy Models (Oct 1)

1. AIMS AND SCOPE

Deep learning has gained significant attention within the computational intelligence community over the recent years. Its success has been mainly due to the increased capability of modern computers to collect, store and process large volumes of data. This has led to a substantial increase in the effectiveness and efficiency of data management. As a result, it has become possible to achieve high accuracy for some benchmark learning tasks such as object classification and image recognition within a short time frame. The most common implementation of deep learning has been through neural networks due to the ability of their layers to perform multiple functional composition as part of a multistage learning process.

In spite of the significant recent advances in deep learning discussed above, there are still some open problems and serious limitations. In particular, effectiveness is usually adversely affected when the data is not well defined due to inherent noise, uncertainty, ambiguity, vagueness and incompleteness. This has an adverse impact on efficiency due to the necessity to define the data better by means of additional collection, analysis and cleaning. The reduced effectiveness and efficiency undermines the ability of deep learning to address real life tasks that are safety critical or time critical. Besides this, deep leaning has been used mainly in a passive manner for the purpose of observing the environment but it almost has not been used in an active manner for the purpose of changing the environment. Finally, deep learning models often have poor transparency which makes them difficult for understanding and interpretation by non-technical users.

The aim of this special issue is to address the problems and limitations discussed above with the help of deep fuzzy models. The latter have been around in different forms and under different names such as hierarchical fuzzy systems and fuzzy networks. These models are well suited for performing multiple functional composition at both crisp and linguistic level. Moreover, they have the potential of handling effectively and efficiently data that is not well defined due to the use of a fuzzy approach. Also, deep fuzzy models can be used in both passive and active manner with regard to the environment due to their generic structure. Finally, these models have a high level of transparency due to their rule base nature.

The special issue will feature the most recent developments in and the state-of-the-art of deep fuzzy models. The target audience includes both researchers from academia and practitioners from industry who are interested in the theory and applications of these models. Papers for the special issue are invited on but not limited to any of the topics listed below.

2. TOPICS COVERED

The topics include but are not limited to:

Theoretical methods ·       Hierarchical Fuzzy Systems ·       Fuzzy Networks ·       Chained Fuzzy Systems ·       Multilevel Fuzzy Systems  ·       Multilayer Fuzzy Systems  ·       Multistage Fuzzy Systems ·       Fuzzy Neuro Systems ·       Evolving Fuzzy Systems  ·       Fuzzy Learning Systems

Application areas ·       Object Classification ·       Image Recognition ·       Process Modelling ·       Process Simulation ·       Process Control ·       Fault Detection  ·       Fault Diagnosis ·       Decision Making ·       Time Series Forecasting

Case studies ·       Engineering ·       Finance ·       Transport ·       Robotics ·       Business ·       Environment ·       Healthcare ·       Security ·       Energy

3. SUBMISSION GUIDELINES 

All authors should read ‘Information for Authors’ before submitting a manuscript http://cis.ieee.org/ieee-transactions-on-fuzzy-systems.html

Submissions should be through the IEEE TFS journal website http://mc.manuscriptcentral.com/tfs-ieee.  Submissions should also be in the correct format http://ieeeauthorcenter.ieee.org/create-your-ieee-article/use-authoring-tools-and-ieee-article-templates/ieee-article-templates/templates-for-transactions/

It is essential that your manuscript is identified as a Special Issue contribution:

·       Ensure you choose ‘Special Issue’ when submitting.

·      A cover letter must be included which includes the title ‘Special Issue on Deep Fuzzy Models’

4. IMPORTANT DATES 

1 October 2018 – Submission Deadline

January 2019 – notification of the first round reviews

April 2019 – revised submissions due

July 2019 – final notice of acceptance/reject 

Dates in 2019 are for guidance only at this point.

5. GUEST EDITORS

Dr Alexander Gegov

University of Portsmouth, United Kingdom

Email: alexander.gegov@port.ac.uk

Prof Uzay Kaymak

Eindhoven University of Technology, Netherlands

Email: u.kaymak@ieee.org

Prof João M. C. Sousa

IDMEC, Instituto Superior Técnico, Universidade de Lisboa, Portugal

Email: jmsousa@tecnico.ulisboa.pt