Call for Participation in IJCNN 2015, Killarney, Ireland on July 12 - 17, 2015

We are pleased to announce that the 2015 International Joint Conference on Neural Networks (IJCNN 2015) will be held in Killarney, Ireland on July 12 - 17, 2015. This is the premiere international conference in the area of neural networks, which will be organized by the International Neural Network Society (INNS), and sponsored jointly by INNS and the IEEE Computational Intelligence Society - the two leading professional organizations for researchers working in neural networks.

You are kindly invited to attend this great conference in beautiful Killarney, Ireland on July 12 - 17, 2015.

For more details for this IJCNN 2015, you can visit http://www.ijcnn.org/ or http://www.ic-ic.org/ijcnn2015/

De-Shuang Huang,
dshuang@tongji.edu.cn
Tongji University, China
IJCNN 2015 General Chair

Call for Papers: Special Session at IJCNN 2015 on Neuro-Adaptive Systems for Big Data and Social Media Analysis

The ever increasing aspect of social networking and deployment of advanced digital sensors, to gather data particularly with high social content has interesting dimensions to be explored. The content variation in the data/media streams poses a challenging task to the data scientists in terms of adaptability required to capture the sense and context of the problem being addressed. The adaptability thus required has to cater multi-faceted issues. These issues pertain to considerations related to the 4V’s of Big Data (Volume, Variety, Velocity and Veracity).

The neuro-adaptive systems have been used in the past to capture the variation and to incorporate adaptiveness within the systems. The aim of this special session is to solicit contributions that are based on statistical learning, lazy learning, artificial neural networks, fuzzy logic based, evolutionary, genetic, knowledge system and adaptive algorithms designed to focus on Big Data, Social Media Analytics especially in the context of the topics listed for the special session.

Topics of interest include, but are not limited to:

• Data Science and Social Analytics
• Emerging Technologies and their Complexities
• Modelling and Visualization
• Parallelization and Distributed Processing
• Personalized Digital Activities
• Opinion Mining and Sentiment Analysis
• Author Profiling, Personality and Behavioral Predictions 
• Ontology Analysis
• Web Content Mining
• Community Structure Prediction
• Trust Recommendation Modeling

Important Dates:

Paper submission: February 5, 2015
Paper decision notification: March 25, 2015
Camera-ready submission: April 25, 2015
Conference days: July 12-17, 2015

Submission:

Authors are invited to submit their papers through the main IJCNN 2015 conference submission system at: http://ieee-cis.org/conferences/ijcnn2015/upload.php

Please make sure to select the Special Session (SS24) under "S. SPECIAL SESSION TOPICS" in the "Main Research topic" drop-down list. Templates and detailed instructions for authors can be found at http://www.ijcnn.org/paper-submission. All papers submitted to the special session will be subject to the same peer-review procedure as regular papers. Accepted papers will be published in the conference proceedings.

Programme Committee:

• Amir Hussain, University of Stirling, UK
• Andrea Bolioli, CELI, Italy
• Arturo Montero, University of Jaen, Spain
• Asim Karim, Lahore University of Management Sciences, LUMS, Pakistan
• Basit Shafiq, Lahore University of Management Sciences, LUMS, Pakistan
• Beatriz Aguilar Cortés, Socialancer, SL., Spain
• Benet María Marcos Casanovas, Socialancer, SL., Spain
• Francisco Casacuberta, PRHLT, Universitat Politècnica de Valencia, Spain
• Francisco Marco-Serrano, GSM London Ltd, United Kingdom
• Giancarlo Ruffo, Netatlas, Italy
• Hai Dong, Royal Melbourne Institute of Technology, Australia
• Jon Ander Gómez, PRHLT Research Center, Universitat Politècnica de València, Spain
• Jon Atle Gulla, Norwegian University of Science and Technology, Norway
• Juan Ramos Balaguer, Money Mate R&D Lab, Spain
• Liaqat Majeed, University of Central Punjab, Pakistan
• Luis Belloch Gómez, Money Mate R&D Lab, Spain
• Mário J. Gaspar da Silva, INESC-ID, Portugal
• Matthew Williams, Cardiff University
• Muhammad Younas, Oxford Brookes University, UK
• Naveed Arshad, Lahore University of Management Sciences, LUMS, Pakistan
• Omar Khadeer Hussain, University of New South Wales Canberra, Australia
• Peter Burnap, Cardiff University
• Rafael Banchs, Institute for Infocomm Research, Singapore
• Roberto Paredes, PRHLT, Universitat Politècnica de Valencia, Spain
• Roman Kern, Know Center, Austria
• Shady Mohammad, Deakin University, Australia
• Shafay Shamail, Lahore University of Management Sciences, LUMS, Pakistan
• Simon Caton, NCC, Dublin, Ireland

Organisers:

Mian M. Awais
Department of Computer Science, Syed Babar Ali School of Science and Engineering, LUMS, Pakistan
Email: awais@lums.edu.pk
http://lums.edu.pk/faculty-details.php/awais

El-Sayed M. El-Alfy
Intelligent Systems Research Group, College of Computer Sciences and Engineering, King Fahd University of Petroleum and Minerals, Saudi Arabia.
Email: alfy@kfupm.edu.sa
http://faculty.kfupm.edu.sa/ics/alfy/ 

Paolo Rosso
Natural Language Engineering Lab, PRHLT Research Center, Universitat
Politècnica de València, Spain.
Email: prosso@dsic.upv.es
http://users.dsic.upv.es/~prosso/

Farookh K. Hussain
Associate Professor,Centre for Quantum Computation and Intelligent Systems, University of Technology Sydney, Australia
Email: farookh.hussain@uts.edu.au
www.uts.edu.au

Omer F Rana
Professor, Computer Science & Informatics,
Cardiff University, Queen's Buildings,5 The Parade, Roath,
Cardiff CF24 3AA, UK
Email: O.F.Rana@cs.cardiff.ac.uk

Francisco Rangel
CTO at Autoritas Consulting
Personal site: http://www.kicorangel.com
Company site: http://www.autoritas.net
Email: francisco.rangel@autoritas.es

IJCNN 2015 Deadline Extension

The paper submission deadline for the International Joint Conference on Neural Networks (IJCNN) 2015 has been extended to February 5, 2015. This extension also applies to submissions to the special sessions.

CEMiSG 2015 2nd International Workshop on Computational Energy Management in Smart Grids 12-17 July 2015, Killarney, Ireland

Scope

The exploitation of natural resources by the increasing world population represents an urgent issue to face for humanity. Electrical Energy represents a relevant example from this perspective and the strong demand coming from developed and developing countries shoved the scientists worldwide to intensify their studies on renewable energy resources, especially in the last two decades. At the same time, we have also registered a remarkable increment of the complexity of the electrical grid at diverse levels in order to include variegated and distributed generation and storage sites.

As a consequence of these aspects, a growing interest has been oriented in the last few years to the development of smart systems able to optimally manage the usage and the distribution of energy among the population with the objective of minimizing wasting and the economic impact, considering the different needs of the heterogeneous grid costumers and the different peculiarities of energy sources. Several ways of intervention are feasible, as the ones indicated in the US Energy Independence and Security Act of 2007.

This motivated the recent spread of advanced technological solutions developed with the objective to introduce intelligence within the energy grid, both at academic and commercial levels. However, the social relevance of the topic makes the need of deepening the studies and providing more and more performing solutions always lively, thus asking for a constant multidisciplinary coordinated action to the scientific communities operating in the Electrical and Electronic Engineering, Computational Intelligence, Digital Signal Processing and Communications research fields.

Narrowing the focus to the interests of our scientific community, the organizers of this Workshop, as inside the IJCNN2015 conference, wants to explore the new frontiers and challenges within the Computational Intelligence research area for the optimal usage and management of energy resources in Smart Grid applicative scenarios.

Topics

• Computational Intelligence for Smart Grids
• Neural Networks based algorithms for Complex Energy Systems
• Deep Learning strategies for Energy Efficiency
• Soft Computing based Algorithms in Energy Applications
• Learning Systems for Smart Grid Optimization
• Learning-based Control of Renewable Energy Generators
• Fast Optimization at diverse Grid levels
• Smart Home Energy Management
• Energy Resource Allocation and Task Scheduling
• Building Energy Consumption Forecasting
• Demand-side Management
• Short-term Load Forecasting
• Neural Networks for Time Series Prediction in Smart Grids
• Non-Intrusive Load Monitoring
• Hybrid Battery Management

Organizers

Stefano Squartini
Università Politecnica delle Marche, Italy
s.squartini@univpm.it

Derong Liu
Chinese Academy of Sciences, China
derongliu@gmail.com
www.cemisg2015.org

Francesco Piazza
Università Politecnica delle Marche, Italy
f.piazza@univpm.it

Dongbin Zhao
Chinese Academy of Sciences, China
dongbin.zhao@ia.ac.cn

Haibo He
University of Rhode Island, USA
he@ele.uri.edu

Technical Program Committee

• Giacomo Boracchi, Italy
• Nelson Kagan, Brazil
• Paul Kaufmann, Germany
• Elias Kyriadikes, Cyprus
• Andrew Kusiak, USA
• Ginaluca Ippoliti Italy
• Chengdong Li, China
• Kang Li, UK
• Danilo Mandic, UK
• Stephen Matthews, UK
• Salman Mohagheghi, USA
• Hugo Morais, France
• Peter Palensky, Austria
• Dianwei Qian, China
• Wei Qiao, USA
• Marco Raugi, Italy
• Pierluigi Siano, Italy
• Gerard Smit, Netherlands
• Dipti Srinivasan, Singapore
• Kumar Venayagamoorthy, USA
• Markus Wagner, Australia
• Qinglai Wei, China

Submission Guidelines

Prospective authors are invited to submit papers according to the IEEE format. All submissions should be according to the specifications of IJCNN2015. Accepted contributions will be part of the IJCNN2015 conference proceedings.

Important Dates

• 15th January 2015: Due date for paper submission
• 15th March 2015: Notification to authors
• 15th April 2016: Camera-ready deadline for accepted papers
• 12th - 17th July 2014: Workshop Days

Call for Papers IJCNN 2015 Special Session "Emerging Methodologies for Big Data Integration"

Over the years, huge quantities of data have been generated by large-scale scientific experiments (biomedical, “omic”, imaging, astronomical, etc.), big industrial companies and on the web. One of the main characteristics of such Big Data is that they are multi-view, i.e. there are multiple sources (in the “omics” sciences, experiments related to mRNA, miRNA etc.), relate the same patterns (in this case patients) or multi-domain (in biomedical applications for examples, “omics, imaging and clinical data).

As a consequence, new methodologies based on neural networks, machine and statistical learning, computation Intelligence and others, have been proposed to integrate these kinds of big data and to elicit relevant information to infer novel models and correlations.

The aim of the special session is to solicit new approaches to real world scientific and industrial big data integration, as well as applications of above mentioned Big Data methodologies.

Topics

Papers must present original work or review the state-of-the-art in the following non-exhaustive list of topics:

• Multi-view learning
• Multi-view clustering
• data fusion
• data integration 
• multi-view data applications 
• multi domain data applications

THE DEADLINE FOR THE PAPER SUBMISSION TO THE SPECIAL SESSION IS THE SAME OF IJCNN 2015, January 15th 2015.

All the submissions will be peer-reviewed with the same criteria used for other contributed papers.

Perspective authors will submit their papers through the IJCNN2015 conference submission system at http://www.ijcnn.org/

Please make sure to select the Special Session "Emerging Methodologies for Big Data Integration " from the "S. SPECIAL SESSION TOPICS" name in the "Main Research topic" dropdown list;

Templates and instructions for authors will be provided on the IJCNN webpage http://www.ijcnn.org/

All papers submitted to the special sessions will be subject to the same peer-review procedure as regular papers, accepted papers will be published in the conference proceedings.

Further information about IJCNN 2015 can be found at http://www.ijcnn.org/
and about the special session at
http://neuronelab.unisa.it/emerging-methodologies-for-big-data-integration/

Organizers

• Amir Hussain Professor of Computing Science and founding Director of the Cognitive Signal-Image Processing and Control Systems Research (COSIPRA) Laboratory,  University of Stirling, UK
• Giovanni Montana Professor and Chair in Biostatistics and Bioinformatics, Biomedical Engineering Department, King’s College, London, UK
• Francesco Carlo MorabitoProfessor and Chair of the Neurolab, Dipartimento DICEAM, Università Mediterranea di Reggio Calabria, Italy
• Roberto TAGLIAFERRIProfessor and Chair of the Neuronelab, Dipartimento di Informatica, Università di Salerno, Italy

Technical Program Committee

• Elia Mario Biganzoli, Università di Milano, Italy
• Erik Cambria, NTU, Singapore
• Ciro Donalek, Caltech, CA, USA
• Anna Esposito, Seconda Università di Napoli, Italy
• Marcos Faundez-Zanuy, Escola Universitaria Politecnica de Mataro (Tecnocampus), Spain
• Alexander Gelbukh, National Polytechnic Institute, Mexico
• Dario Greco, FIOH, Finland
• Newton Howard, MIT Media Lab, USA
• Pietro Liò, University of Cambridge, UK
• Bin Luo, Anhui University, China
• Mufti Mahmud, Antwerp University, Belgium
• Riccardo Rizzo, CNR, Italy
• Domenico Ursino, Università Mediterranea di Reggio Calabria, Italy
• Alfredo Vellido, Universidad Politécnica de Cataluña, Spain
• Pierangelo Veltri, Università "Magna Graecia" di Catanzaro, Italy
• Jonathan Wu, University of Windsor, Canada
• Yunqing Xia, Tsinghua University, China
• Erfu Yang, University of Strathclyde, UK

Call for Papers IJCNN 2015 Special Session "Distributed Learning Algorithms, Techniques, and Implementations for Internet-of-Things"

Updated:  New submission deadline February 5th, 2015.

Aim and Motivation:

Many learning algorithms and techniques were developed with the requirements of single application in mind, such as e-commerce, search, and vision. Internet-of-Things (IoT) presents a great challenge to existing computational intelligence schemes such as machine learning and neural networks due to its data and compute complexity. IoT devices, such as sensors, cameras, and actuators commonly produce distributed, sparse and highly complex data representations that require these intelligent schemes to adapt and adjust, with limited resource availability. The ability to perform learning in distributed manner will enable better resource coordination and utilisation in handling complex computations in such resource-constrained environment.

This special session aims at presenting novel approaches to distributed learning for Internet-of-Things, both from the theoretical and practical perspectives of computational intelligence schemes.

Topics:

This includes but is not restricted to the following topics:

• Parallel and distributed computational intelligence algorithms and techniques:
• Deep learning
• Hierarchical learning
• Associative memory
• Sparse distributed memory
• Machine learning
• Neural networks
• Hybrid approaches
• IoT Analytics
• Autonomous IoT
• Resource utilisation and coordination
• Control and communication systems
• Intelligent IoT applications and services

Paper Submission:

The format of paper and submission procedure should be followed as specified on the IJCNN 2015 website. Accepted special session papers will be included in the conference proceedings. Submissions to this special session should follow the following instructions:

1. Go to http://ieee-cis.org/conferences/ijcnn2015/upload.php to submit your paper to IJCNN 2015.
2. Be sure to set the "Main research topic" to "SS35 - Distributed Learning Algorithms, Techniques, and Implementations for Internet-of-Things".

For more information, please visit IJCNN'2015 CFP website: http://www.ijcnn.org/call-for-papers, or our Special Session CFP: https://sites.google.com/site/ijcnn2015distlearniot/ . All submissions will be peer-reviewed with the same criteria used for other contributed papers.

IMPORTANT DATES

Paper submission UPDATED:  February 5th, 2015
Paper Decision notification: March 15th, 2015 
Camera-ready submission: April 15th, 2015
Conference Dates: July 12 - 17th, 2015

Organizers:

Anang Hudaya Muhamad Amin
Thundercloud Research Lab
Faculty of Information Science and Technology (FIST)
Multimedia University
Melaka, Malaysia
Email: anang.amin@mmu.edu.my

Asad I. Khan
Faculty of Information Technology
Monash University
Clayton, VIC, Australia
Email: Asad.Khan@monash.edu

Benny B. Nasution
Politeknik Negeri Medan
Medan, Indonesia
Email: benny.nasution@polmed.ac.id

Call for Papers IJCNN 2015 Special Session "Biologically Inspired Computational Vision"

Introduction:

Constructive understanding of computational principles of visual information processing, perception and cognition is one of the most fundamental challenges of contemporary science. Deeper insight into biological vision helps to advance intelligent systems research to achieve robust performance similar to biological systems. Biological inspiration indicates that sensory processing, perception, and action are intimately linked at various levels in animal vision. Implementing such integrated principles in artificial systems may help us achieve better, faster and more efficient intelligent systems. This session provides an integrated platform to present original ideas, theory, design, and applications of computational vision.

• Topics of interest include, but are not limited to the following:Theoretical approaches and modeling in computational vision
• Neuronal mechanisms of visual processing
• Low level vision and its relationship to biological machinery
• Artificial learning systems for image and information processing and evidential reasoning for recognition
• Intelligent search in communications networks
• Modeling issues in ATM networks, agent-oriented computing architectures
• Perception of shape, shadows, poses, color and illumination in object recognition
• Tracking for inferring shapes and 3D motions
• Active visual perception, attention and robot vision
• Functional Magnetic Resonance Imaging (fMRI) studies of visual segmentation and perception
• Application of computational vision in areas of
• Automated target identification and acquisition systems in defense and industry
• Biomedical imaging
• 3D photography
• Face recognition
• Learning to segment camouflaged objects
• Motor actions and robotics
• Image databases and indexing
• Hardware implementation of computational vision
• Any other topics related to biological approaches in computer vision

Organizer:

Khan M. Iftekharuddin, Old Dominion University, USA
Professor and Chair, Department of Electrical and Computer Engineering
http://www.eng.odu.edu/visionlab/

Program Committee:

• Vijayan Asari, University of Dayton, USA
• Azzedine Beghdadi, University Paris, 13, France
• Salim Bouzerdoum, University of Wollongong, Australia
• Ke Chen, University of Manchester, UK
• Yoonsuck Choe, Texas A&M University, USA
• Robert Kozma, University of Memphis, USA
• Minho Lee, Kyungpook National University, Korea
• Zicheng Liu, Microsoft Research, USA
• Bertram Shi, Hong Kong University of Science and Technology, Hong Kong
• Rufin VanRullen, CNRS, Toulouse, France

Submission instructions:

1. Go to http://ieee-cis.org/conferences/ijcnn2015/upload.php to submit a paper to IJCNN 2015.
2. Be sure to set the "Main research topic" to this special session. (The special sessions are found at the bottom of the list.)

Call for Papers IJCNN 2015 Special Session "Models of Cognitive-Emotional Interactions"

Special Session for IEEE IJCNN 2015. Updated submission deadline 5th February 2015

Website: http://ieee-cis.blogspot.com/2014/11/call-for-papers-ijcnn-2015-special_64.html

Scope:

Recent brain imaging studies have highlighted the interrelationship between cognitive and emotional processes.  Emotion helps the cognitive system decide allocations of attention among a large, heterogeneous, and confusing set of stimuli in the environment.  Conversely, satisfaction or dissatisfaction of the drive to understand the environment generates positive or negative emotions.  Hence, it has become increasingly difficult to categorize brain regions as primarily “cognitive” or “emotional.”  Rather, a complex network of interconnected regions including amygdala, hypothalamus, ventral and dorsal striatum, anterior cingulate cortex, insula, and several regions of prefrontal cortex is involved in the interplay of cognition and emotions in human and animal decision making.

Furthermore, a number of researchers have found it advantageous to add emotion-like capabilities to robots and other artificial neural systems.  As the work of Antonio Damasio and many others points out, emotions can be of aid in classifying objects within a robot’s environment.  In particular, emotions like joy and interest can generate approach to specific objects, whereas emotions like fear and disgust can generate avoidance of specific objects.

Topics:

We particularly encourage submissions related to the following non-exhaustive list of topics:

• Emotional influences on decision making
• Normal and abnormal affect
• Cognitive and emotional effects of the psychotherapeutic process
• Computational psychiatry
• Differences between primary biological emotions and aesthetic emotions 
• Emotional robots
• Emotional representations in artificial neural systems.

Dates and submissions:

The deadlines for submissions, author feedback, etc. are bound to the normal IJCNN 2015 deadlines (and, thus, are also subject to the same changes and extensions).

The current schedule is:

• Paper submission due UPDATED: February 5, 2015
• Paper review feedback: March 15, 2015
• Final papers due: April 15, 2015

For details on the submission process, formats, etc., please refer to the IJCNN 2015 Call for Papers ( http://www.ijcnn.org/call-for-papers ) and the IJCNN 2015 submission guidelines ( http://www.ijcnn.org/paper-submission ).
When submitting to the special session, please make sure to select the corresponding session topic during the submission process.

Session Co-Chairs:

Daniel S. Levine, University of Texas at Arlington (Levine@uta.edu)
Leonid Perlovsky, Northeastern University (lperl@rcn.com)
Abbas Edalat, Imperial College London (a.edalat@imperial.ac.uk)

Call for Papers IJCNN 2015 Special Session "Ensemble Systems and Machine Learning"

Special Session for IEEE IJCNN 2015. 

Scope

Ensembles are essential tools for classification and prediction tasks in many real-world applications.  The past decade has witnessed a vast growth of the amount of machine learning methods using ensemble, becoming a popular approach due to their capabilities in handling many real world complex problems and to the good results and analysis presented in many recently published papers. Results show that ensembles of classifiers and forecasting models can achieve better accuracy than single ones. However, ensembles face many challenges in obtaining diverse and optimized base models, as well as obtaining good fusion algorithms.

This special session of IJCNN 2015 will cover all aspects of the latest achievements in ensemble systems particularly machine learning based ensembles and their applications.

Topics for submission include, but are not limited to:

• Ensemble techniques and algorithms
• Multiple experts
• Committee of experts
• Fusion of classifiers
• Fusion of forecasting models
• Optimization techniques for multiple classifiers
• Applications of ensemble and fusion techniques

etc.

Biographic Information:

Marley Vellasco received the BSc and MSc degrees in Electrical Engineering from the Pontifical Catholic University of Rio de Janeiro (PUC-Rio), Brazil, in 1984 and 1987, respectively, and the PhD degree in Computer Science from the University College London (UCL) in 1992. Dr. Vellasco is currently Head of the Electrical Engineering Department of PUC-Rio and of the Computational Intelligence and Robotics Laboratory (LIRA) of PUC-Rio. She is the author of four books and more than 45 papers in professional journals, 300 papers in conference proceedings and 15 book chapters in the area of soft computing and machine learning. Her research interests include Neural Networks, Fuzzy Logic, Neuro-Fuzzy Systems, Neuro-Evolutionary models, Robotics and Intelligent Agents, applied to decision support systems, pattern classification, time-series forecasting, control, optimization and Data Mining.

Teresa B. Ludermir received the Ph.D. degree in Artificial Neural Networks in 1990 from Imperial College, University of London, UK. She is a Full Professor at the Center of Informatics, Universidade Federal de Pernambuco, Brazil. She has published over a 200 articles in scientific journals and conferences, three books in Neural Networks and organized two of the Brazilian Symposium on Neural Networks. She is one of the editors-in-Chief of the International Journal of Computation Intelligence and Applications. Her main interests are Machine Learning, Meta-Learning, Hybrid Intelligent Systems, and Time Series Forecasting.

Call for Papers IJCNN 2015 Special Session "Modeling and Forecasting Financial and Commodity Markets by Neural Networks"

Special Session for IEEE IJCNN 2015.Updated submission deadline: 5th February, 2015.

Aim and scope

Behaviors of stock price changes in financial and commodity markets have long been a focus of economic research for a more clear understanding of mechanism and characteristics of markets. In the empirical research, some statistical properties for the market fluctuations are uncovered by the high frequency financial time series, such as fat tails distribution of price changes, power-law of logarithmic returns and volumes, volatility clustering, multifractality of volatility, etc. The applications of neural networks in time series forecasting for financial applications have gained enormous popularity in the recent years. In fact, the analysis of financial time series is of primary importance in the economic world; by using a data driven empirical analysis, the goal is to obtain insights into the dynamics of series and out-of-sample forecasting. If one were able to forecast tomorrow’s returns on an asset with some degree of precision, one could use this information in an investment today.

The aim of this special session, which stems by the excellent success obtained during the 2014 IEEE WCCI Conference held in Beijing, is to promote research and reflect the most recent advances of neural networks, including their hybridization with evolutionary computation, fuzzy systems, metaheuristic techniques and other intelligent methods, in a series of practical problems relevant to the interactions between machine learning and financial modeling and forecasting, the main interest being finalized for searching optimal relationships in the area of financial engineering, energy commodity trading, risk management, portfolio optimization, industrial organization, auctions, searching equilibriums, financial forecasting, market simulation, agent-based computational economics, and many other areas.

Topics

The topics of interest to be covered by this Special Session include, but are not limited to:

• Financial data mining
• Time series analysis and forecasting
• Soft computing applications
• Dynamics of commodity markets
• Decision support systems
• Risk analysis and credit scoring
• Portfolio management
• Automated trading systems
• Agent-based computational economics
• Economic modeling and finance
• Stock volatility prediction
• Investment strategy
• Artificial economics
• Simulation of social processes

Important Dates

Paper submission UPDATED: February 5, 2015
Paper decision notification: March 15, 2015
Camera-ready submission: April 15, 2015
Conference days: July 12-17, 2015

Submission

Manuscripts submitted to special sessions should be done through the paper submission website of IJCNN 2015. All papers submitted to special sessions will be subject to the same peer-review procedure as the regular papers. If a sufficient number of papers are accepted to fill a special session, then it will be included in the final program. If not enough papers are accepted for this special session, then the accepted papers will be automatically moved to regular sessions.

The authors intended to contribute to this special session are kindly recommended to follow the manuscript style information and templates of regular IJCNN 2015 papers, as described here.

When submitting their manuscripts, authors are recommended to follow these steps:

1. select the Special Session ID and Name in the “Main research topic” dropdown list, that is SS29 - Modeling and Forecasting Financial and Commodity Markets by Neural Networks 
2. fill out the input fields, upload the PDF file and finalize the submission by January 15, 2015.

Special Session Organizer

MASSIMO PANELLA, Ph.D.
Dept. of Information Engineering, Electronics and Telecommunications
University of Rome “La Sapienza”
Via Eudossiana 18, 00184 Rome, Italy
Tel.: +39-0644585496; Skype: m.panella
E-mail: massimo.panella@uniroma1.it
Web: http://massimopanella.site.uniroma1.it
LinkedIn: http://it.linkedin.com/in/massimopanella

Call for Papers IJCNN 2015 Special Session "Unsupervised Neural Network Clustering"

Special Session for IEEE IJCNN 2015.

IMPORTANT DATES

Paper submission UPDATED:  February 5, 2015
Paper Decision notification: March 15, 2015
Camera-ready submission: April 15, 2015
Conference: July 12-17, 2015

SCOPE AND MOTIVATION

Generally, unsupervised learning or self-organized learning finds regularities in the data represented by the examples. Clustering methods such as model-based, density based and user guided methods are often applied for data reduction such as summarization like preprocessing of classification; compression like vector quantization; and finding the nearest neighbors. Specifically, a feed-forward neural network is a software version of the human brain and have their roots in Hebbian and competitive learning such as Kohonen’s self-organizing map and growing neural gas. In this network, data processing has only one forward direction from the input layer to the output layer without any cycle or backward movement; and generally exhibits several advantages such as an inherent distributed parallel processing architectures, as well as capabilities to adjust the interconnection weights to learn and describe suitable clusters, process vector quantization prototypes and distribute similar data without class labels to describe the clusters, control noisy data, cluster unknown data, and learn the types of input values on the basis of their weights and properties. The current online dynamic unsupervised feed-forward neural network clustering methods such as evolving self-organizing map and dynamic self-organizing map inherit some of the advantages and disadvantages of static unsupervised feed-forward neural network clustering methods; which are suitable to be applied in different research areas such as email logs, networks, credit card transactions, astronomy and satellite communications. Generally, the critical issues of clustering are data losing, definition of clustering principles, number and Unsupervised clustering is a valuable subject to research, however, their critical issues are data losing, definition of clustering principles, number and densities of clusters. Specially, the main problems in dynamic feed-forward neural network clustering are low speed, high memory usage and memory complexity through using random weights and parameters, and relearning. The goal of this research is an investigation of current unsupervised clustering and identify their limitations and problems through a literature review and experience.

TOPICS

The topics of the special session include, but are not limited to:

• Learning and Neural Network
• Unsupervised Feed Forward Neural Network clustering
• Static Unsupervised Neural Network clustering
• Dynamic Unsupervised Neural Network clustering
• Semi-supervised Neural Network clustering

ORGANIZERS

Roya Asadi, Department of Artificial Intelligence, Faculty of Computer Science and Information Technology, University of Malaya, Kuala Lumpur, Selangor, 50603, Malaysia, (royaasadi@siswa.um.edu.my).

Sameem Abdul Kareem, Department of Artificial Intelligence, Faculty of Computer Science and Information Technology, University of Malaya, Kuala Lumpur, Selangor, 50603, Malaysia. (sameem@um.edu.my).

Shokoofeh Asadi, Department of Agreecultural Management Engineering, Faculty of Ebne-Sina, University of Sciece and Research Branch, Tehran, 930277941, Iran, (shokoofeh.ame@gmail.com).

SUBMISSION

All papers are to be submitted through the conference website: http://www.ijcnn.org/

Call for Papers IJCNN 2015 Special Session "Mind, Brain, and Cognitive Algorithms"

Organizers: Leonid Perlovsky (Harvard University and Northeastern University, MA; lperl@rcn.com), José F. Fontanari, Asim Roy, Angelo Cangelosi, Daniel Levine.

Recent progress opens new directions for modeling the mind and brain and developing cognitive algorithms for engineering applications. Cognitive algorithms solve traditional engineering problems much better than before, and new areas of engineering are opened modeling human abilities in cognition, emotion, language, art, music, cultures. Cognitive dissonances and behavioral economics is another new active area of research. A wealth of data are available about the ways humans perform different cognitive tasks (e.g., scene and object recognition, language acquisition, interaction of cognition and language, music cognition, cognitive dissonance) as well as about the biases involved in human judgment and decision making (e.g., the prospect theory and the fuzzy-trace theory). A wealth of data on the web can be exploited for extracting cognitive data. Explaining these laws and biases using realistic neural networks architectures, including neural modeling fields, as well as more traditional learning algorithms requires a multidisciplinary effort.

The aim of this special session is to provide a forum for the presentation of the latest data, results, and future research directions on the mathematical modeling of higher cognitive functions using neural networks, neural modeling fields, as well as cognitive algorithms exploiting web data and solving traditional and new emerging engineering problems, including genetic association studies, medical applications, Deep Learning, and Big Data.

The special session invites submissions in any of the following areas:

• Neural network models of higher cognitive function
• Neural mechanisms of emotions, cognition
• Embodied cognition modeling
• Neural modeling fields (NMF) 
• Perceptual processing
• Language learning 
• Cognitive and emotional processing
• Cognitive models of decision-making
• Models of emotional mechanisms
• Models of cognitive dissonances
• Cognitive, language, and emotional models of cultures
• Cognitive functions of art, music, and spiritual emotions.
• Emotions in cognition (affective cognition)
• Cognitive dissonance, neural models
• Cognition and cultures
• Medical applications 
• Genome association studies
• Big Data

Keywords:

Cognition, Emotions, Decision-Making, Language Acquisition, Language Emotionality, Cognitive Dissonance, Music Cognition, Models of Cultures, Neural Modeling Fields, ART Neural Network, Fuzzy-Trace Theory, Prospect Theory, Deep Learning, Genome Associations, Big Data   

Program Committee:

M. Cabanac (Canada)
A. Cangelosi (UK)
J. F. Fontanari (Brazil)
R. Illin (USA)
B. Kovalerchuk  (USA)
R. Kozma (USA)
D. Levine (USA)
D. Marocco  (UK)
A. Minai
L. I. Perlovsky (USA)
S. Petrov (USA)
A. Roy
J. Weng

Call for Papers IJCNN 2015 Special Session "Big Data in Smart Industry"

Submissions are invited for IJCNN 2015 Special Session on “Big Data in Smart Industry”

Updated submission deadline 5th February, 2015.

Webpage: http://www.cpdee.ufmg.br/~apbraga/Paginas2014/SSIJCNN2015.html

ABSTRACT

Industry is experiencing worldwide the beginning of a new era of innovation and change. Sensors, actuators, supervision and control elements are increasingly endowed with autonomy, flexibility, communication capability and interoperability. The new generation of devices, which is capable of data collection and processing, has been gradually incorporated into several levels of the industrial production chain. The synergy of these physical and computational elements forms the base for a profound transformation of the global industry with a perspective of a dramatic increase of productivity and reliability, and significant benefits for the society. Within this new scenario, the availability of a large amount of high dimensional data reveals itself as a dilemma for the induction of data models. On the one hand, there is an expectation that a greater ability of sampling might improve performance and reliability. Nevertheless, the reality is that most current methods and models are not able to deal with problems of such high dimension and volume. Many current problems involve terabytes of data with hundreds of variables and dimensions that tend to rise continuously if the expected industrial growth rate in the sector is maintained. Prognostics are for an exponential growth of the data storage capacity in the worldwide network of devices during the next years. In addition to the increased internal connectivity of the industry, an improved integration and enhanced synergy with consumer markets and inputs through networking appears to be an inevitable path. Current trend suggests worldwide industry will highly demand data models and processing capabilities to handle time-varying, massive and high dimensional data. This is where Big Data in Smart Industry problems become relevant, and it is crucial that academia and industry are prepared from scientific and technological points of view to face the new challenges.

TOPICS:

We would like to encourage the submission of papers within the general scope of the Special Session (Big data in Smart Industry) in the following topics:

• Modeling of large datasets
• Dimensionality reduction of very large datasets
• Learning from large industrial datasets
• Data analysis and visualization
• Online modeling, optimization, and autonomous control of industrial processes
• Embedded intelligence in cyber-physical systems
• Computational intelligence for smart energy management
• Data stream processing for water, transportation, agriculture, and sustainability
• Internet of things and smart resources management
• Data-driven optimization and control of dynamical systems
• Cyber-physical system units (CPSU) with embedded autonomy
• Data acquisition and storage in distributed industrial environments

ORGANIZERS:

Antônio Pádua Braga
Federal University of Minas Gerais, Brazil
apbraga@ufmg.br
http://www.ppgee.ufmg.br/~apbraga

Fernando Gomide
University of Campinas, Brazil
gomide@dca.fee.unicamp.br
http://www.dca.fee.unicamp.br/~gomide

SUBMISSION & IMPORTANT DATES

Special session papers will undergo the same review process as regular papers and follow the same schedule of the conference. Paper submission should be done directly to IJCNN submissions page found at http://ijcnn.org. Be sure to set the "Main research topic" to your special session. The special sessions are found at the bottom of the list.

Paper submission deadline : February 5, 2015
Paper decision notification: March 15, 2015
Camera-ready submission: April 15, 2015

Call for Papers IJCNN 2015 Special Session "Autonomous Learning from Big Data"

Special Session for IEEE IJCNN 2015.

Updated submission deadline: 5 February, 2015.

Organizers: 

P. Angelov (www.lancs.ac.uk/staff/angelov)
A. Roy (ASIM.ROY@asu.edu)

The aim of the special session is to present latest results in this fast expanding area of Autonomous Learning Systems and Big Data Analytics and to give a forum to discuss the challenges for the future.
It is organised by the new Special Interest Group on Autonomous Learning Systems and the Section on Big Data Analytics within INNS and by the Technical Committee on Evolving Intelligent Systems, SMC Society, IEEE and aims to be a focal point of the latest research in this emerging area.

One of the important research challenges today is to cope effectively and efficiently with the ever growing amount of data that is being exponentially produced by sensors, Internet activity, nature and society. To deal with this ocean of zeta-bytes of data, data streams and navigate to the small islands of human-interpretable knowledge and information requires new types of analytics approaches and autonomous learning systems and processes.

Traditionally, for decades or even centuries machine learning, AI, cognitive science were developed with the assumption that the data available to test and validate the hypotheses is a small, finite volume and can be processed iteratively and offline. The realities of dynamically evolving big data streams and big data sets (e.g. pentabytes of data from retail industry, high frequency trading, genomics or other areas) become more prominent only during the last decade or so. This poses new challenges and requires new, revolutionary approaches.

Topics of interest 

(include but not limited to):

Methodology

• Autonomous, online, incremental learning – theory, algorithms and applications in big data
• High dimensional data, feature selection, feature transformation – theory, algorithms and applications for big data
• Scalable algorithms for big data
• Learning algorithms for high-velocity streaming data
• Kernel methods and statistical learning theory
• Big data streams analytics
• Deep neural network learning
• Machine vision and big data
• Brain-machine interfaces and big data
• Cognitive modeling and big data
• Embodied robotics and big data
• Fuzzy systems and big data
• Evolutionary systems and big data
• Evolving systems for big data analytics
• Neuromorphic hardware for scalable machine learning
• Parallel and distributed computing for big data analytics (cloud, map-reduce, etc.)
• New Adaptive and Evolving Learning Methods
• Autonomous Learning Systems
• Stability, Robustness, Unlearning Effects
• Structure Flexibility and Robustness in Evolving Systems
• Evolving in Dynamic Environments
• Drift and Shift in Data Streams
• Self-monitoring Evolving Systems
• Evolving Decision Systems
• Evolving Perceptions
• Self-organising Systems
• Neural Networks with Evolving Structure
• Non-stationary Time Series Prediction with Evolving Systems
• Automatic Novelty Detection in Evolving Systems
• On-Line Identification of Fuzzy Systems
• Evolving Neuro-fuzzy Systems
• Evolving Clustering Methods
• Evolving Fuzzy Rule-based Classifiers
• Evolving Regression-based Classifiers
• Evolving Intelligent Systems for Time Series Prediction
• Evolving Intelligent System State Monitoring and Prognostics Methods
• Evolving Intelligent Controllers
• Evolving Fuzzy Decision Support Systems
• Evolving Probabilistic Models
• Big data and collective intelligence/collaborative learning
• Big data and hybrid systems
• Big data and self-aware systems
• Big Data and infrastructure
• Big data analytics and healthcare/medical applications
• Big data analytics and energy systems/smart grids
• Big data analytics and transportation systems
• Big data analytics in large sensor networks
• Big data and machine learning in computational biology, bioinformatics
• Recommendation systems/collaborative filtering for big data
• Big data visualization
• Online multimedia/ stream/ text analytics
• Link and graph mining
• Big data and cloud computing, large scale stream processing on the cloud

Real-life applications

• Robotics
• Defence
• Intelligent Transport
• Bio-Informatics
• Industrial Applications
• Data Mining and Knowledge Discovery
• Control Systems
• Evolving Consumer Behaviour
• Evolving Activities Recognition
• Evolving Self-localisation Systems

Dates:

• Send Title & Abstract to p.angelov@lancaster.ac.uk or ASIM.ROY@asu.edu as soon as possible
• Deadline for Paper Submission Updated 5 February, 2015
• Notification of Acceptance 15 March, 2015
• Final Paper Submission 15 April, 2015

Selected authors will be invited to submit extended papers for a special issue of the Springer journal Evolving Systems

Call for Papers IJCNN 2015 Special Session "Digital Audio Applications"

Special Session for IEEE IJCNN 2015.

Updated submission deadline: 5 February, 2015.

THEME AND SCOPE

Neural Networks (NN) based techniques, and Computational Intelligence (CI) ones from a wider perspective, are largely used to face complex modelling, prediction, and recognition tasks in different research fields. One of these is represented by Digital Audio, which finds application in contexts like entertainment, security, and health. Scientists and technicians worldwide actively cooperate to develop new services and products, and they typically employ advanced NN and CI techniques, in combination with suitable Digital Signal Processing algorithms.

In particular, this is typically accomplished with the aim of extracting and manipulating useful information from the audio stream to pilot the execution of automatized services, also in an interactive fashion. Several are the Digital Audio topics touched by such a paradigm, involving different kinds of audible signals. In the “music” case study we have the music information retrieval with many diverse sub-topics therein; for “speech” we can mention speech/speaker recognition, speaker diarization, speaker localization; in the case of “sound”, acoustic monitoring and sound detection and identification have lately registered a big interest among the scientists working in the field. Moreover, also cross-domain approaches to exploit the information contained in diverse signals in the acoustic range have been also recently developed. In many applicative contexts, this happens in conjunction with data coming from other media, like textual and visual, for which specific fusion techniques are required. 

In dealing with the problems correlated to these topics, the adoption of data-driven learning systems is often a ``must'', and the recent success encountered by deep neural architectures comes just in confirmation of that. This is not, however, immune to technological issues, due to the presence of non-stationary operating conditions and hard real-time constraints (made often harder by the big amount of data to process).

It is indeed of great interest for the scientific community to understand how and to what extent novel CI based techniques (with special attention to the NN ones) can be efficiently employed in Digital Audio, in the light of all aforementioned aspects. The aim of the session is therefore to focus on the most recent advancements in the CI field and on their applicability to Digital Audio problems.

TOPICS

Potential topics include, but are not limited to:

• Computational Audio Analysis
• Deep Learning algorithms in Digital Audio
• Neural Architectures for Audio Processing
• Music Information Retrieval
• Speech/Speaker Analysis and Classification
• Sound Detection and Identification
• Acoustic Source Separation
• Brain inspired auditory scene analysis
• Cross-domain Audio Analysis
• Speech and Audio Forensics
• Audio-based Security Systems
• Intelligent Audio Interfaces

IMPORTANT DATES

• UPDATED February 5, 2015: Paper submission deadline
• March 15, 2015: Notification of paper acceptance
• April 15, 2015: Camera-ready deadline
• July 11-16, 2015: Conference days

ORGANIZERS

Stefano Squartini, Università Politecnica delle Marche, Italy, s.squartini@univpm.it      
Aurelio Uncini, Università La Sapienza, Italy, aurel@ieee.org
Björn Schuller, University of Passau, Germany/Imperial College London, UK, schuller@ieee.org
Francesco Piazza, Università Politecnica delle Marche, Italy, f.piazza@univpm.it

http://a3lab.dii.univpm.it/news/ijcnn2015-special-session

Call for Papers IJCNN 2015 Special Session "Intelligence for cyber-physical, embedded and pervasive systems"

Special Session for IEEE IJCNN 2015.

Overview

The emergence of nontrivial embedded units mounting a rich sensor and actuator platform, sensor networks, the Internet of Things (IoT), pervasive and cyber-physical systems has made possible the design of sophisticated applications where large amounts of real-time data are collected to constitute a “big data” picture as time passes. Intelligence, adaptation through learning, neural and neuromorphic systems, cognitive fault tolerance and healing abilities constitute some key mechanisms needed to boost the future generation of intelligent systems and derived applications.

Topics

The special session aims at gathering scholars and practitioners addressing those research topics and applied problems that the interaction of intelligent systems with the real world is requesting.

Papers must present original work, applications or review the state-of-the-art in the following non-exhaustive list of topics:

• Intelligent devices and solutions for the Internet of things
• Cognitive Sensor Networks
• Neural and neuromorphic Systems
• Intelligent Measurement Systems
• Incremental learning in cyber-physical and embedded systems
• Intelligent diagnosis and healing mechanisms 
• Low level learning mechanisms for time invariant environments
• Intelligent sensors and robotics
• Intelligent systems for embedded applications

Relevance of the topic

Although we experience an increasingly pervasive presence of embedded applications in our everyday life, such that by 2020 it is predicted that each person will possess between 5 and 10 embedded systems, the presence of intelligence in current versions of embedded devices is generally very basic, mostly confined to passive adaptation.  Learning and cognitive mechanisms play a key role here to boost the next generation of embedded systems and applications.

Workshop Organizers

Cesare Alippi (Italy)

CESARE ALIPPI received the degree in electronic engineering cum laude in 1990 and the PhD in 1995 from Politecnico di Milano, Italy. Currently, he is a Full Professor of information processing systems with the Politecnico di Milano. He has been a visiting researcher at UCL (UK), MIT (USA), ESPCI (F), CASIA (RC), USI (CH). Alippi is an IEEE Fellow, Vice-President education of the IEEE Computational Intelligence Society (CIS), Associate editor (AE) of the IEEE Computational Intelligence Magazine, past AE of the IEEE-Trans Instrumentation and Measurements, IEEE-Trans. Neural Networks.

In 2004 he received the IEEE Instrumentation and Measurement Society Young Engineer Award; in 2011 has been awarded Knight of the Order of Merit of the Italian Republic; in 2013 he received the IBM Faculty Award.Current research activity addresses adaptation and learning in non-stationary environments and Intelligent embedded systems. He holds 5 patents and has published one monograph book published by Springer on "Intelligence for embedded systems", 6 edited books and about 200 papers in international journals and conference proceedings.

Manuel Roveri (Italy)

MANUEL ROVERI received the Dr.Eng. degree in Computer Science Engineering from the Politecnico di Milano (Milano, Italy) in June 2003, the MS in Computer Science from the University of Illinois at Chicago (Chicago, Illinois, U.S.A.) in December 2003 and the Ph.D. degree in Computer Engineering from Politecnico di Milano (Milano, Italy) in May 2007.

Currently, he is an assistant professor at the Departent of Electroncis and Information of the Politecnico di Milano. His research interests include intelligent embedded systems, computational intelligence and adaptive algorithms. Manuel Roveri is an Associate Editor of the IEEE Transactions on Neural Networks and Learning Systems and served as chair and member in many IEEE subcommittees.

Keywords

• Embedded systems
• Cyber-physical systems
• Intelligent applications
• Intelligent sensors
• Intelligence for sensor networks
• Neuromorphic systems
• Internet of Things
• Approximate computing

Further information and Paper submission can be found at the conference homepage:  http://www.ijcnn.org/
Please make sure you select the correct Special Session in the submission process.

Call for Papers IJCNN 2015 Special Session "Emerging trends in CI methods for Biomedicine and Healthcare"

Special Session for IEEE IJCNN 2015.


http://www.cs.upc.edu/~avellido/research/conferences/IJCNN15-HealthBiomed.html

Beyond basic research, biology in general and biomedicine in particular are increasingly and rapidly becoming data-based sciences, an evolution driven by technological advances in image and signal non-invasive data acquisition (perfectly exemplified by the 2014 Nobel Prize in Chemistry for the development of super-resolved fluorescence microscopy), or high-throughput genomics, to name just a few. In the Biomedical field, the large amount of data generated from a wide range of devices and patients is creating challenging scenarios for researchers, related to storing, processing and even just transferring information in its electronic form, all these compounded by privacy and anonymity legal issues. The situation is not different in healthcare, where electronic health records are becoming commonplace and new possibilities such as remote home monitoring, or wearable medical devices are likely to make an impact as part as the ambitious p-Health, or 4-P (Predictive, personalized, preventive, participatory) paradigm for medicine. Data-based healthcare finds a paramount example in the current Institute for Systems Biology (ISB, Seattle) "Hundred Person Wellness Project"(*), a pilot in which 100 healthy individuals are intensively monitored on a daily basis. New data requirements require new approaches to data analysis, some of the most interesting ones are currently stemming from the Computational Intelligence (CI) and Machine Learning (ML) community. This session is particularly interested in the proposal of novel CI and ML approaches to problems in the biomedical and healthcare domains, with a non-exclusive focus on methods that overcome the "black-box syndrome" by making models interpretable and thus fulfil the usability requirements of most real medical applications.

Topics that are of interest to this session include (but are not necessarily limited to):

• Novel applications of existing CI and ML methods to biomedicine and healthcare
• Novel CI and ML techniques for biomedicine and healthcare.
• CI and ML-based methods to improve model interpretability in biomedicalproblems, including data/model visualization techniques.
• Novel CI and ML techniques for dealing with non-structured and heterogeneousdata formats.
• Development of user-friendly interactive exploratory interfaces and subjectspecificmodels.

(*) Medicine Gets Up Close and Personal, Nature, 506(7487), 144-145

Organizers:

• Alfredo Vellido, Computer Science Department, Universitat Politècnica de Catalunya BarcelonaTECH, Spain
• Paulo J.G. Lisboa and Sandra Ortega-Martorell, School of Computing and Mathematical Sciences, Liverpool John Moores University, United Kingdom
• José D. Martín, Intelligent Data Analysis Laboratory (IDAL), Department of Electronic Engineering, University of Valencia, Spain

Call for Papers IJCNN 2015 Special Session "Clustering and Co-clustering"

Special Session for IEEE IJCNN 2015.

Updated submission deadline: 5 February, 2015.

Description

Everyday, huge amounts of data are generated by users via the web, social networks, etc. Clustering/Coclustering techniques are a tool of choice to help organize the huge collections of data that increasingly beset us. Clustering/Coclustering is an unsupervised learning approach that allows one to discover global structures in the data (i.e. clusters). Given a dataset, it identifies different data subsets which are hopefully meaningful. The discovered clusters are deemed interesting if they are while instances within each (co)cluster share similar features. This (co)clustering problem has motivated a huge body of work and has resulted in a large number of algorithms. (Co)Clustering has thus been used in numerous real-life application domains such as marketing, city planning, and so forth.

Clustering algorithms are a tool of choice to explore these high-dimensional data sets. However numerous questions remain open as:

• What are the last advances in
• supervised clustering that combines the main characteristics of both traditional clustering and supervised classification tasks?
• quality criteria?
• clustering for big data?
• evolving clustering?
• clustering events or time series?

This special session offers a meeting opportunity for academics and industry researchers belonging to the communities of Computational Intelligence, Machine Learning, Experimental Design, and Data Mining to discuss new areas of (co)clustering, One goal of this special session will be two-fold: On the one hand, to look for new algorithms and techniques proposals based on (co)clustering. On the other hand, to look for new application domains, real problems, where the application of (co)clustering have demonstrated an outstanding performance or interpretation abilities against other traditional approaches.

Publication opportunities: Papers should be submitted to IJCNN. We encourage papers that describe new algorithm and applications of (co)clustering in real-world. In the industrial context, the main difficulties met and the original solutions developed, have to be described.

Paper acceptance and publication will be judged on the basis of their quality and relevance to the special session themes, clarity of presentation, originality and accuracy of results and proposed solutions.

The set of proposed topics includes, but is not limited to::

• Clustering, Coclustering
• Supervised Clustering (Coclustering)
• Semi-Supervised Clustering (Coclustering)
• Quality Criteria for Clustering (Coclustering)
• Measure of Variable Importance for a Clustering (Coclustering)
• Automatic tuning of Cluster Number (Cocluster Number)
• Clustering for Big Data
• Method to assess the evolution of a Clustering (Coclustering)
• Constrainted Clustering (Coclustering)

The list of application domain is includes, but it is not limited to:

• Evolving textual information analysis
• Evolving social network analysis
• Dynamic process control and tracking
• Intrusion and anomaly detection
• Genomics and DNA micro-array data analysis
• Adaptive recommender and filtering systems

A list of Applicative domains could be found in
P. Berkhin « Survey of clustering data mining techniques », Accrue Software, San Jose, CA, 2002.

Organizers:

Vincent Lemaire
ORANGE-LABS, Lannion, France
2 avenue Pierre Marzin
22300 Lannion
vincent.lemaire@orange-ftgroup.com
http://www.vincentlemaire-labs.fr

Pascal Cuxac
INIST-CNRS,
Recherche Développement
2 allée du Parc de Brabois
CS 10310
54519 Vandoeuvre les Nancy Cedex
pascal.cuxac@inist.fr,
https://sites.google.com/site/pascalcuxac/

Jean-Charles Lamirel
TALARIS (ex-TALARIS) -LORIA,
Campus Scientifique
BP 239
54506 Vandoeuvre-lès-Nancy
jean-charles.lamirel@loria.fr

Organizing committee 

(tentative, to be confirmed):

• Abou-Nasr Mahmoud Ford Motor Company USA
• Al Shehabi Shadi Allepo University Syria
• Albatineh Ahmed N. Dept of Biostatistics Florida Int. U. Miami USA
• Alippi Cesare Politecnico di Milano Italia
• Arredondo Tomas U.T.F.S.M. Valparaíso Chile
• Bennani Younes LIPN, Paris France
• Bifet Albert University of Waikato, Hamilton New Zealand
• Bondu Alexis EDF R&D France
• Cabanes Guenael LIPN, Paris France
• Candillier Laurent (Expertiselcandillier.free.fr)
• Chawla Nitesh Notre Dame University, Indiana USA
• Chen Chaomei Drexel University, Philadelphia USA
• Cleuziou Guillaume (LIFO) France
• Cornuéjols Antoine (AgroParisTech) France
• Cuxac Pascal INIST-CNRS, Vandoeuvre-les Nancy France
• Diallo Abdoulaye B. UQAM Montreal Canada
• El Haddadi Anass IRIT France
• Escalante Hugo Jair Mexico
• García-Rodríguez José University of Alicante Spain
• Glanzel Wolfgang KU Leuven, Leuven Belgia
• Guigoures Romain (Zalando - German)
• Grozavu Nistor LIPN, Paris France
• Hammer Barbara University of Bielefeld Germany
• Kumova Bora I. Izmir University Turkey
• Kuntz-Cosperec Pascale Polytech'Nantes France
• Labroche Nicolas (Université de Tours) France
• Lallich Stephane University of Lyon 2 France
• Lamirel Jean-Charles TALARIS- LORIA, Nancy France
• Lebbah Mustapha LIPN, Paris France
• Lemaire Vincent Orange Labs, Lannion France
• Lenca Philippe Telecom Bretagne France
• Li Bin UTS, Sydney Australia
• Nuggent Rebecca Carnegie Mellon University, Pittsburgh USA
• Popescu Florin Fraunhofer Institute, Berlin Germany
• Roveri Manuel Politecnicodi Milano Italia
• Sublemontier Jacques-henri (CEALIST), France
• Tamir Dan Texas State University, San Marcos USA
• Torre Fabien University of Lille3 France
• Urvoy Tanguy Orange Labs, Lannion France
• Vrain Christel (LIFO) France
• Zhou Zhi-Hua Nanjing University China
• Zhu Xingquan Florida Atlantic University USA

Important dates:

• Paper submission UPDATED: February 5, 2015
• Paper decision notification: March 15, 2015
• Camera-ready submission: April 15, 2015

Organizers:

Vincent Lemaire (Orange Labs, France, vincent.lemaire@orange.com) was born in 1968 and he obtained his undergraduate degree from the University of Paris 12 in signal processing and was in the same period an Electronic Teacher. He obtained a PhD in Computer Science from the University of Paris 6 in 1999. He thereafter joined the R&D Division of France Telecom where he became a senior expert in data-mining. His research interests are the application of machine learning in various areas for telecommunication companies with an actual main application in data mining for business intelligence. He developed exploratory data analysis and classification interpretation tools. Active learning and data-space exploration are now his main research interests. He obtained his Research Accreditation (HDR) in Computer Science from the University of Paris-Sud 11 (Orsay) in 2008.

Previous workshop or special session organizations:

• Atelier - Clustering and Co-clustering (CluCo) at EGC 2015
• Incremental classification, concept drift and novelty detection (IClaNov) - ICDM 2014 
• Workshop of the Discovery Challenge - ECML 2014 
• Incremental learning and novelty detection methods and their applications - ESANN 2014 
• Atelier - Clustering and Co-clustering (CluCo) at EGC 2014 
• Incremental clustering, concept drift and novelty detection (IClaNov) - ICDM 2013 
• Active Learning and Experimental Design (ALED) - IJCNN 2013 
• Incremental classification and novelty detection (CIDN) - EGC 2013 
• Active Learning in Real-World Applications - (ALRA) - ECML 2012 
• Active and Incremental Learning (AIL) - ECAI 2012 
• Incremental classification and novelty detection (CIDN) - EGC 2012 
• Active, Incremental and Autonomous Learning: Algorithms and Applications - IJCNN 2012 
• Workshop on Unsupervised and Transfer Learning (UTL) - ICML 2011 
• Autonomous and Incremental Learning (AIL) - IJCNN 2011 
• Active and Autonomous Learning (AAL) - IJCNN 2010 
• Fast scoring on a Large Database - KDD 2009

Jean-Charles Lamirel (LORIA - INRIA, France, lamirel@loria.fr) is Lecturer since 1997. He obtained his PhD in Computer Science in 1995 and his Research Accreditation in the same domain in 2010. He is currently teaching Information Science and Computer Science at the University of Strasbourg and achieving his research at the INRIA laboratory of Nancy. He was a research member of the INRIA-CORTEX project whose scope is Neural Networks and Biological Systems. He has recently integrated the INRIA-TALARIS project whose main concern is automatic language and text processing. Jean-Charles Lamirel main domains of research are textual data mining based on neural networks, multiple viewpoints data analysis paradigms, data mining auto-evaluation methods and evolving data mining. He is board member of the international Webometrics journal: "Collnet Journal of Scientometrics and Information Management" and was taking part in the committee of ICTAI 2011-2012 and WSOM 2012 conference. He is member of the IEE task force on "Evaluation and quality issues in data mining" within the Data Mining Technical Committee and committee member of the corresponding PAKDD-QIMIE 2013 workshop.

Previous workshop or special session organizations:

• Clustering and co-clustering – CluCo - workshop EGC 2014
• Incremental clustering, concept drift and novelty detection (IClaNov), Workshop ICDM 2013
• Incremental classification and novelty detection - CIDN - workshop EGC 2013
• Intelligent analysis of time varying information and concept drift management – IEA/AIE 2012
• Incremental classification and novelty detection - CIDN 2012
• Incremental clustering and novelty detection techniques and their application to intelligent analysis of time varying information - IEA/AIE 2011
• Incremental clustering and novelty detection - CIDN 2011
• International Conference on Webometrics, Informetrics and Scientometrics & 7th COLLNET Meeting in conjunction with the Extra Session on Information Visualization for Webometrics, Informetrics and Scientometrics, Nancy, France, 10-12 May, 2006

Pascal Cuxac (INIST - CNRS, France pascal.cuxac@inist.fr) is Research Engineer at the INIST/CNRS (Institute for Scientific & Technical Information / National Center for Scientific Research) in Nancy, France. He obtained his PhD in Geological and Mining Engineering from the Nancy School of Geology in 1991 and he was working on mechanical behavior of anisotropic rock. In 1993, he joined the CNRS as Research Engineer. Currently, in INIST Research & Development Engineering Service, he takes part in a research program on classification methods for bibliographic corpora, in particular in the development of an incremental unsupervised clustering algorithm.

Previous workshop or special session organizations:

• Clustering and co-clustering – CluCo - workshop EGC 2014
• Incremental clustering, concept drift and novelty detection (IClaNov), Workshop ICDM 2013
• Incremental classification and novelty detection - CIDN - workshop EGC 2013
• Incremental classification and novelty detection - CIDN 2012
• Incremental clustering and novelty detection techniques and their application to intelligent analysis of time varying information - IEA/AIE 2011
• Incremental clustering and novelty detection - CIDN 2011

Call for Papers IJCNN 2015 Special Session "Nature Inspired Deep Learning"

Special Session for IEEE IJCNN 2015.

IMPORTANT DATES

Paper submission UPDATED:  February 5, 2015
Paper Decision notification: March 15, 2015
Camera-ready submission: April 15, 2015
Conference: July 12-17, 2015

AIM

Deep learning has recently emerged as a prominent CI discipline. However, applications of the nature-inspired methods such as particle swarm optimisation and evolutionary optimisation to deep learning are still very limited. Training deep neural networks is a challenging task due to the inherent high dimensionality. The aim of this special session is to discuss the existing nature-inspired approaches to deep learning, to identify problems that arise, and to encourage research in this new and exciting field of computational intelligence.

SCOPE

The topics of the special session include, but are not limited to:

• Applications of evolutionary algorithms to deep learning
• Applications of swarm-based algorithms to deep learning
• Hybrid approaches to deep learning
• Theoretical and empirical analysis of the nature-inspired deep learning algorithms
• Identifying and understanding the limitations of nature-inspired deep learning
• Real-world applications of nature-inspired deep learning
• Training Restricted Boltzmann Machines with nature-inspired algorithms
• Training Deep Belief Networks with nature-inspired algorithms
• Training autoencoders and stacked autoencoders with nature-inspired algorithms
• Training convolutional neural networks with nature-inspired algorithms
• Weight pretraining with nature-inspired algorithms
• High-performance implementations of nature-inspired deep learning
• Analysis of overfitting and generalization of deep networks training using nature-inspired algorithms
• Training of deep networks in dynamic environments

ORGANIZERS

Prof Andries Engelbrecht, Department of Computer Science, University of Pretoria, Pretoria, South Africa (engel@cs.up.ac.za)
Ms Anna Rakitianskaia, Department of Computer Science, University of Pretoria, Pretoria, South Africa (annar@cs.up.ac.za)

SUBMISSION

All papers are to be submitted through the conference website: http://www.ijcnn.org/

More details on the special session can be found at: https://sites.google.com/site/ijcnn2015deepnature/

Call for Papers IJCNN 2015 Special Session "Autonomous Machine Learning for Cyber-Physical Systems"

Special Session for IEEE IJCNN 2015.

Updated submission deadline 5th February, 2015.

Scope and Motivation

Recent development in ICT and sensor devices brings us a new form of intelligent systems called Cyber-Physical System (CPS). In CPS, physical entities such as humans, robots, cars, factories, houses interact and communicate with other entities in both physical- and cyber-worlds. The information processed in cyber-physical worlds are video images, voice/sounds, texts (e.g. documents, tweets, e-mails), control signals, sensor data, etc., and such data are continuously generated as “big stream data”. In general, such data are composed not only of explicit information on physical entities (e.g. location, translation, acceleration), but also of implicit information such as health conditions, emotion, and behaviors, which should be extracted from original sensor data. To acquire knowledge from the latter type of implicit information, autonomous machine learning and data mining methods that can learn from high-dimensional stream data are solicited for CPS.

The purpose of this special session is to share new ideas to develop autonomous machine learning and data mining methods for big stream data that are generated not only by connecting cyber-physical worlds but also within either of cyber- and physical- worlds.

Topics

A wide range of autonomous machine learning/data mining methods and applications for cyber-physical systems is covered, including but not limited to the followings:
Theoretical approaches to machine learning /data mining methods for cyber-physical systems

• Supervised/Unsupervised Learning
• Online/Incremental Learning
• Online Feature Selection/Extraction
• Online Clustering
• Active Learning
• Stream Data Mining
• Text Mining
• Time-Series Analysis

Applications of cyber-physical systems such as

• Human-Robot Interactions
• Smart Life Technologies (Smart Grids, Smart City, Smart Home, Smart Car, Smart Agriculture, etc.)
• Social Network Analysis (e.g. sentimental analysis, user profiling, etc.)
• Cybersecurity
• Opinion Mining
• Emotion/Behavior Mining
• Person Attitude Mining
• Realty Mining

Important Dates

• February 5, 2015: Paper submission deadline
• March 15, 2015: Notification of paper acceptance
• April 15, 2015: Camera-ready deadline
• July 12-17, 2015: Conference days

Submission

1. Manuscripts submitted to special sessions should be done through the paper submission website of IJCNN 2015 as regular submissions. Please follow the instructions below:Go to http://ieee-cis.org/conferences/ijcnn2015/upload.php to submit a paper to IJCNN 2015.
2. Be sure to set the "Main research topic" to “SS32: Autonomous Machine Learning for Cyber-Physical Systems”. (The special sessions are found at the bottom of the list.)

All papers submitted to special sessions will be subject to the same peer-review review procedure as the regular papers. Accepted papers will be part of the regular conference proceedings.

For more information, please contact the Special Session organizers:

• Seiichi Ozawa (ozawasei@kobe-u.ac.jp), Kobe University, Japan
• Nistor Grozavu (nistor@lipn.univ-paris13.fr), LIPN, Paris 13 University, Villetaneuse, France
• Nicoleta Rogovschi (nicoleta.rogovschi@parisdescartes.fr), LIPADE, Paris Descartes University, Paris, France
• Shogo Okada (okada@ntt.dis.titech.ac.jp), Tokyo Institute of Technology, Japan