IEEE IEEE HomeSearch IEEE ShopWeb AccountContact IEEE
MembershipPublications/ServicesServicesStandardsConferencesCareers/Jobs

Home

Next Meetings

Past Meetings

List of Officers

Chapter Information

Useful Links

IEEE Computational Intelligence Society /
Systems, Man & Cybernetics

Ottawa Joint Chapter

 

Past Meetings

2014

Chris Drummond
What ROC Curves Can't Do (and Cost Curves Can)

2013

Nathalie Japkowicz
Data-Driven Ensemble Learning with Deep Search and Class Rebalancing
Diana Inkpen
Analysis of Opinions and Emotions in Texts

2012

John Verdon
The Wealth of People: Framing the Future of Knowledge and Work in the Digital Environment - From Management to Collaboration and Knowledge Governance
Giovanni Acampora, Vincenzo Loia & Autilia Vitiello
On the Temporal Granularity on Fuzzy Cognitive Maps
Julio Valdes
Visual Data Mining with Nonlinear Space Transformations and Virtual Reality
Russell C. Eberhart
Particle Swarm: From Cornfield Vectors to Cognitive Radio
Alfredo Vaccaro
Decentralized Coordination in Smart Grids by Self Organizing Dynamic Fuzzy Agents

2011

James Bezdek
Anomaly Detection in Wireless Sensor Networks: Visual Assessment and Clustering in Environmental Monitoring Systems
Erik Blasch
Multi-Sensor Fusion Performance Assessment
Emilio Miguelanez Martin
Semantic knowledge-based framework to improve the situation awareness of autonomous underwater vehicles
Jerry Mendel
Signal Fusion Using Novel Weighted Averages
Hani Hagras
Type-2 Fuzzy Logic Controllers: A way Forward for Fuzzy Systems in Real World Environments

2010

Rafael Falcon
Nature-Inspired Optimization in Fault-Reactive Wireless Sensor and Robot Networks
Alan Barton
The Use of General Neuron Functions within Neural Networks
Qinghan Xiao
DRDC Biometrics Activities and IEEE CIS Biometrics Mission
Genci Capi
Development of a Robotic Platform for Human Robot Interaction
Slawo Wesolkowski
Risk-Based Multiobjective Optimization for a Vehicle Fleet Mix Problem

2009

Sylvain Chartier
Much To Do About Bidirectional Associative Memory
Russel Eberhart
Swarm Intelligence: Where We've Been and Where We're Going
Simon Haykin
Cognitive Tracking Radar
Qing Chen
Hand Gesture Recognition and Applications in Human-Computer Interactions
Q. J. Zhang
Neural Networks for High-Frequency Electronic Modeling and Design

2008

James M. Keller
Soft Computing for Sensor and Algorithm Fusion
Marcel Turcotte
Applying Relational Learning to Structural Molecular Biology Problems
Moufid Harb
Neural Networks for Environment Recognition and Local Navigation of a Mobile Robot

2007

Oana Frunza
Does pain hurt in both French and English?
Jacek M. Zurada
Data Mining, Neural Networks and Rule Extraction
Stan Matwin
Current Applied Research in Machine Learning: Medical Abstracts and Digital Games
Monique Frize
Information Technologies Applied to Medicine

2006

Evangelia Micheli-Tzanakou
Lying, Deception and Face Familiarity with Visual Evoked Potentials
Diana Inkpen
Information Retrieval from Automatic Speech Transcripts
Jian Pei
Graph Mining and its applications
Jean-Philippe Thivierge
A Unified Model of Spike-Time-Dependent Plasticity and Chemotropic Gradients in Retinotopic Map Formation

2005

Mark Fiala
Computer Vision for Augmented Reality - the ARTag system
Adrian D.C. Chan
Let your muscles do the talking: myoelectrically controlled prostheses to myoelectric speech recognition
Wail Gueaieb
A Robust Hybrid Intelligent Position/Force Control Scheme for Cooperative Manipulators
B. John Oommen
How to Learn from a Stochastic Teacher or a Stochastic Compulsive Liar of Unknown Identity

2004

Dmitry Gorodnichy
Face recognition in video as a new biometrics modality and the appropriate associative memory framework
Julio J. Valdés
The heterogeneous neuron model and its use in hybrid neural networks within computational intelligence compound systems
Ana-Maria Cretu
Neural Network Modeling of 3D Objects for Virtualized Reality Applications
Peter Turney
Corpus-based Learning of Analogies and Semantic Relations

2003

Emil M. Petriu
Hardware Neural Network Architectures Using Random Data Representation
Nicolas D. Georganas
Collaborative Virtual Environments



Date

Wednesday March 12, 2014

Time

13:30-15:00 (EDT)

Location

Building M-50, NRC Auditorium, 1200 Montreal Road (admission and parking are free)

Title

What ROC Curves Can't Do (and Cost Curves Can)

Speaker

Chris Drummond

 

Research Officer

 

Information and Communication Technologies

 

National Research Council

Abstract

In this talk, our focus is on the visualization of a classifier's performance.  This is one of the attractive features of ROC analysis - the tradeoff between false positive rate and true positive rate can be seen directly. A good visualization of classifier performance would allow an experimenter to immediately see how well a classifier performs and to compare two classifiers - to see when, and by how much, one classifier outperforms others. We restrict the discussion to classification problems in which there are only two classes.  The main point of this talk is to show that, even in this restricted case, ROC curves are not a good visualization of classifier performance.  In particular, they do not allow any of the following importantexperimental questions to be answered visually:

  • What is classifier C's performance (expected cost) given specific misclassification costs and class probabilities?
  • For what misclassification costs and class probabilities does classifier C outperform the trivial classifiers?
  • For what misclassification costs and class probabilities does classifier C1 outperform classifier C2?
  • What is the difference in performance between classifier C1 and classifier C2?
  • What is the average of performance results from several independent evaluations of classifier C (e.g. the results of 5-fold cross-validation)?
  • What is the 90% confidence interval for classifier C's performance?
  • What is the significance (if any) of the difference between the performance of classifier C1 and the performance of classifier  C2?

 

Speaker Bio

Chris Drummond is a Research Officer within the ICT Portfolio at the National Research Council (NRC). He holds a B.Tech. in Applied Physics and an M.A.Sc. in Electrical Engineering. In 1999 he completed his Ph.D. in Computer Science at the University of Ottawa. There he spent a further three years as postdoctoral researcher in its School of Information Technology and Engineering until taking up his current position at the National Research Council. His research interests center on machine learning and cover such areas as data mining, learning agents, hybrid systems and cost sensitive learning. Chris has published numerous scientific papers on these topics.




Date

Monday November 18, 2013

Time

13:30-15:00 (EDT)

Location

Building M-50, NRC Auditorium, 1200 Montreal Road (admission and parking are free)

Title

Data-Driven Ensemble Learning with Deep Search and Class Rebalancing

Speaker

Nathalie Japkowicz

 

Professor

 

School of Electrical Engineering and Computer Science

 

University of Ottawa

Abstract

Data-driven ensemble learning, such as Data-driven Error Correcting Output Coding (DECOC) is a multi-class learning approach that combines binary base learners using a coding matrix. The data-driven design of the code atrix takes the complexity of the classification problem into consideration and does so in an unsupervised, and therefore, highly efficient way compared with alternative matrix design methods. In this research, we propose a novel complexity measure which we can use to perform an efficient deep search in the matrix design space. In addition, we also rectify the class imbalance problem that can be encountered by some binary base problems. Both strategies where first consolidated with a study on artificial sets, and then tested on real-world domains. Our results show that our method is not only more efficient than related leading methods on real-world sets, but that it also outperforms them in terms of classification accuracy.

 

Speaker Bio

Nathalie Japkowicz is a Professor of Computer Science at the School of Electrical Engineering and Computer Science and the Director of the Laboratory for Research on Machine Learning for Defense and Security at the University of Ottawa. Recently she has been elected the President of the Canadian Artificial Intelligence Association.

Professor Japkowicz received her Ph.D. from Rutgers University in 1999. After teaching at Ohio State University and Dalhousie University, she accepted a position at the University of Ottawa in 2000 where she has worked ever since, except for academic leaves at Monash University (Australia), Tufts University (USA) and Northern Illinois University (USA). Throughout her career, she has supervised or co-supervised over thirty Master’s and Ph.D. students. She has received a number of grants and contracts totaling over a million dollars in direct outside funding.

She is the author or co-author of over 100 book chapters, articles and papers and she co-authored the book entitled Evaluating Learning Algorithms: A Classification Perspective (Cambridge University Press, 2011). In the past five years, she and her students have received two best paper awards at conferences.

Recent applications of her research include: the monitoring of threats to public safety by detecting Gamma-emitting hazardous materials, the detection of underwater mines or improvised explosive devices with multiple autonomous unmanned vehicle operations, the monitoring of international conformation to the Comprehensive Nuclear Test Ban Treaty, and the detection of serious threats to computer networks.




Date

Tuesday April 30, 2013

Time

10:00-11:30 (EDT)

Location

Building M-50, NRC Auditorium, 1200 Montreal Road (admission and parking are free)

Title

Analysis of Opinions and Emotions in Texts

Speaker

Diana Inkpen

 

Professor

 

School of Electrical Engineering and Computer Science

 

University of Ottawa

Abstract

The automatic detection of opinions and emotions in texts is important for applications such as market analysis, affective computing, natural language interfaces, and intelligent tutoring systems. Texts have been classified by topic, genre, sentiment orientation (positive or negative opinions), or even by the gender of the authors. This talk will focus on classifying texts by the opinion and by the emotion expressed by the authors. Results on several datasets will be presented. A global dataset is then used for training, in order to obtain a more general classifier. Results of a hierarchical classification approach will also be discussed.

 

Speaker Bio

Diana Inkpen is a Professor at the University of Ottawa, in the School of Electrical Engineering and Computer Science. She obtained her doctorate in 2003 from the University of Toronto, Department of Computer Science. She has a Masters in Computer Science and Engineering from the Technical University of Cluj-Napoca, Romania. Her research interests are in the areas of Computational Linguistics and Artificial Intelligence, more specifically: Natural Language Understanding, Natural Language Generation, Lexical Semantics, Information Retrieval, Speech Technology, and Intelligent Agents for the Semantic Web.



Date

Friday December 14, 2012

Time

10:00-12:00 (EDT)

Location

CBY A-605, University of Ottawa

Title

The Wealth of People: Framing the Future of Knowledge and Work in the Digital Environment - From Management to Collaboration and Knowledge Governance

Speaker

John Verdon

 

Office of the Research Scientist

 

Department of National Defence, Canada

Abstract

The presentation examines the implications of hyper-connectivity associated with the digital environment and social media. The thesis is summarized in a ‘McLuhanism” - If the Digital Environment is the MEDIUM…then Social Computing is the MESSAGE Entailing that Modes of Production must become Programmable.

I argue that the purpose of traditional organizational architecture aimed at minimizing ‘transaction costs’ must be re-evaluated. The digital environment has effected an unprecedented collapse of traditional costs associated with any large collective and collaborative efforts of people and organizations. The emerging digital environment and social media capabilities represent new modes of production that proliferate architectures of participation, enable social computing and entail the development of ‘programmable organizations’.

A Medium is anything that extended the mind, body or senses. Thus a Medium can be a new technology, process, idea or original creative work. When a new Medium is created, its message becomes clear in the resultant differences in human interactions and activities. The nature of these differences is embodied in changes of scale, pace, scope or pattern that a medium causes in us as individuals or as a society or culture. These changes (Message) are distinct from the content of the Medium.

Social computing then is the capacity for a large network or ‘swarm’ of people to explore in parallel, a problem space and produce a range of effective solutions, and/or produce a good or service. Social computing increases the capability to search a larger solution space, enable knowledge to flow where and when it is needed and increases human and social capital and network trust.

What is meant by programmable modes of production – is the rapid and agile generation, assemblage and harnessing of knowledge networks, as and when needed, in a way that doesn’t require an organization to re-configure, retool, or re-architect its coordination structures and processes. A programmable mode of production is reliant on responsible autonomy (based on trusted personnel, agent-forum accountability, and context/competence-based leadership) and networked individualism – as a social operating system.

To harness related capabilities organizational architectures will soon require new sets of rules – institutional, and governance frameworks. Institutional innovation is needed in order to harness the increased capabilities as well as the cost savings made possible by new modes of production.

 

Speaker Bio

Mr. John Verdon has a rich and broad background in theoretical and applied social science research which includes formal education in psychology, anthropology, sociology and philosophy. His expertise is lies in foresight and strategic HR research, especially as it relates to social media & the digital environment, complexity sciences, knowledge management and organizational architectures. His research also explores emerging cognitive, biological and nano-technologies and their potential impact. The aim of his research work is on the development of a better theory and philosophy related to harnessing human capital in the 21 st Century.

 


Date

Tuesday October 30, 2012

Time

11:00-12:30 (EDT)

Location

Online Webinar (see registration below)

Title

On the Temporal Granularity on Fuzzy Cognitive Maps

Speaker

Giovanni Acampora, Eindhoven University of Technology

 

Vincenzo Loia, University of Salerno

 

Autilia Vitiello, University of Salerno

Webinar Details

https://attendee.gotowebinar.com/register/7266876103196019456
Please, connect 15 minutes ahead of time

 

Abstract

The theory of fuzzy cognitive maps (FCMs) is a powerful approach to modeling human knowledge that is based on causal reasoning. Taking advantage of fuzzy logic and cognitive map theories, FCMs enable system designers to model complex frameworks by defining degrees of causality between causal objects. They can be used to model and represent the behavior of simple and complex systems by capturing and emulating the human being to describe and present systems in terms of tolerance, imprecision, and granulation of information. However, FCMs lack the temporal concept that is crucial in many real-world applications, and they do not offer formal mechanisms to verify the behavior of systems being represented, which limit
conventional FCMs in knowledge representation. In this webinar, we present a temporal extension to FCMs by exploiting a theory from formal languages, namely, the timed automata, which bridges the aforementioned inadequacies. Indeed, the theory of timed automata enables FCMs to effectively deal with a double-layered temporal granularity, extending the standard idea of B-time that characterizes the iterative nature of a cognitive inference engine and offering model checking techniques to test the cognitive and dynamic comportment of the framework being designed. As shown through experiments, where the proposed approach has been evaluated by simulating a complex municipality garbage collection system, TAFCMs improve conventional FCMs by yielding better performance in terms of representation of dynamic systems behavior.

 

Speaker Bio

Dr. Giovanni Acampora received the Laurea (cum laude) and Ph.D. degrees in Computer Science from the University of Salerno, Salerno, Italy, in 2003 and 2007, respectively. Since July 2012, he is an Assistant Professor at the School of Industrial Engineering, Information Systems, Eindhoven University of Technology, the Netherlands. From March 2007 to March 2012, he has been a Research Associate in the Department of Mathematics and Computer Science, University of Salerno. He was also a Member of the Multi-Agent Laboratory at the University of Salerno and scientific co-responsible of the CORISA Research Centre. From September 2003 to June 2007, he was also in CRDC-ICT Domotic project, where he was engaged in the research on multi-agent systems and artificial intelligence applied to ambient intelligence environments. In this context, he designed and developed the Fuzzy Markup Language, an XML-based environment for modeling transparent fuzzy systems. Currently, FML is under consideration by IEEE Standard Association to become the first standard in the field of computational intelligence. His current research interests include novel algorithms design approaches inspired by natural systems as swarm intelligence, evolutionary, and memetic strategies, investigating the designing of novel human–computer interaction systems based on integration among haptic hardware, virtual reality and augmented reality technologies, formal methods from language theory area, and on the study of temporal effects on the behavior of fuzzy systems modeled through fuzzy controllers and fuzzy cognitive maps. He has written some seminal papers on ambient intelligence and, in particular, his work about fuzzy computation in smart environments is one of the most cited paper of IEEE Transactions on Industrial Informatics.
Dr. Acampora serves as reviewer and associate and guest editor for several international journals and conferences. Dr. Acampora is the chair of the IEEE Computational Intelligence Society Standards Committee. In this context, he also served as Chair of Task Force on Taxonomy and Terminology and Vice-Chair of Task Force on New Standard Proposal. From 2010, he serves as Secretary and Treasurer of Italian Chapter of IEEE Computational Intelligence Society. Currently he is chairing the IEEE Standard Association P1855 Workgroup related to the FML standardization process.

Dr. Vincenzo Loia (SM’08) received the Bachelor’s degree in computer science from the University of Salerno, Fisciano, Italy, in 1984 and the Ph.D. degree in computer science from the University of Paris VI, Paris, France, in 1989. Since 1989, he has been a Faculty member with the University of Salerno, where he teaches Operating Systems, Semantic Web, and Multi-Agents Systems. He is currently a Full Professor of computer science with the Department of Mathematics and Computer Science. He is the author of more than 190 original research papers in international journals, e-book chapters, and international conference proceedings. His current research interests include merging soft computing and agent technology to design technologically complex environments, with particular interest in web intelligence applications. Dr. Loia is the Co-Editor-in-Chief of Soft Computing and the Editor-in-Chief of Ambient Intelligence and Humanized Computing. He serves as an Editor for 14 other international journals. He has been the Chair of the Emergent Technologies Technical Committee of the IEEE Computational Intelligence Society, where he is currently the Chair the of Task Force Intelligent Agents.

Autilia Vitiello received the Laurea degree in Computer Science (cum laude) from the University of Salerno (Italy) in 2009, discussing the thesis "Time Sensitive Fuzzy Agents: formal model and implementation" (advisor Prof. Vincenzo Loia). She is currently a PhD student at Department of Computer Science of the University of Salerno under the supervision of Prof. Vincenzo Loia and Dr. Giovanni Acampora. Her research interests concern computational intelligence, and in particular, fuzzy logic and knowledge representation theories. In last years, she is working on evolutionary algorithms, above all, like means to solve the ontology alignment problem.

 


Date

Friday September 28, 2012

Time

11:00-12:30 (EDT)

Location

Online Webinar (see registration below)

Title

Visual Data Mining with Nonlinear Space Transformations and Virtual Reality

Speaker

Julio Valdes

 

Research Officer

 

Institute for Information Technology

 

National Research Center (NRC)

Webinar Details

Event number: 596 122 422

Event password: This event does not require a password.

Host key: 363761 (Use this to reclaim host privileges.)

Event address: https://ieeemeetings.webex.com/ieeemeetings/onstage/g.php?d=596122422&t=a

 

Abstract

The talk introduces a visual data mining data exploration approach on heterogeneous information systems of general kind. The technique facilitates the process of understanding the underlying structure of single or compound information systems, understood as collection or arbitrary entities described in terms of a collection of properties (possibly heterogeneous, imprecise and incomplete). The objects may be characterized by relations defined on them as well. The approach is based on nonlinear mappings between heterogeneous spaces with extended information systems and a lower dimension space. A particular case is that of spaces with 2,3 dimensions which could be visualized using virtual reality techniques. The spaces can be also constructed for unions of information systems (e.g. heterogeneous and incomplete data sets together with knowledge bases composed by decision rules), simplifying the process of discovery of interesting patterns and relationships between the original data and the symbolic expressions representing the knowledge. This approach has been applied successfully to a wide variety of real-world domains (medicine, astronomy, environment, etc.) and examples are presented.

 

Speaker Bio

Dr. Julio Valdes is a Senior Research Officer at the national research council (NRC), Ottawa, Canada. He obtained his PHD from has a PhD in mathematics (1987) from the Institute of Mathematics, Academy of Sciences of Czechoslovakia. He is a senior member of IEEE Computational Intelligence Society, and in 2005 he Co-chaired the Task Force Computational Intelligence in Earth and Environmental Sciences. Also, in International Neural Networks Society, he Co-chaired the SIG Computational Intelligence in Earth and Environmental Sciences.
In Canada, he is an adjunct Professor in the School of Information Technology and Engineering, University of Ottawa, Canada since 2008. Also, since 2008 he is an adjunct Professor with the Department t of Engineering and Computer Science, University du Québec en Outaouais, Canada. He worked as a Professor in the Doctorate Program on Artificial Intelligence, Department of Languages and Information Systems, Polytechnic University of Catalonia, Barcelona, Spain in 2005.

His areas of interest are: artificial intelligence (mathematical foundations of uncertainty processing and inexact reasoning, knowledge engineering, expert systems and machine learning), digital image and signal processing, pattern recognition, virtual reality, soft computing (fuzzy logic, neural networks, evolutionary algorithms, probabilistic reasoning, rough sets), data mining, data analysis in general and hybrid systems. He also graduated in geophysics (1977), oriented to geo-mathematics, mathematical modeling of natural processes, computer elaboration and data analysis-mining of earth science and environmental data, remote sensing, physics and chemistry of external geodynamic processes and geophysical-geochemical prospecting.

Dr. Valdes has published 206 papers: 45 in refereed journals, 112 in Refereed Conference Proceedings, 24 in Non-refereed Journals or Conferences, 13 technical reports, 13 books and chapters, and more than 146 technical talks.

 


Date

Wednesday July 11, 2012

Time

8:30-10:00 (EDT)

Location

Online Webinar (see details below)

Title

Particle Swarm: From Cornfield Vectors to Cognitive Radio

Speaker

Russell C. Eberhart

 

CTO

 

Phoenix Data Corporation

   

Webinar Details

This webinar is organized by the IEEE Ottawa CIS & SMC Joint Chapter and the IEEE Ottawa CS Chapter..

Meeting information

Topic: CIS Live Webinar Links / Dial-in Information - July 11, 2012
Date: Wednesday, July 11, 2012
Time: 8:30 am, Eastern Daylight Time (New York, GMT-04:00)
Meeting Number: 590 856 057
Meeting Password: (This meeting does not require a password.)

To start or join the online meeting

Go to https://ieeemeetings.webex.com/ieeemeetings/j.php?ED=199185787&UID=497062897&RT=MiMxMQ%3D%3D

Teleconference information

Provide your phone number when you join the meeting to receive a call back. Alternatively, you can call:
Call-in toll-free number: 1-866-2030920  (US)
Call-in number: 1-206-4450056  (US)
Show global numbers: https://www.tcconline.com/offSite/OffSiteController.jpf?cc=3924546129
Conference Code: 392 454 6129

For assistance

1. Go to https://ieeemeetings.webex.com/ieeemeetings/mc
2. On the left navigation bar, click "Support".
To add this meeting to your calendar program (for example Microsoft Outlook), click this link:
https://ieeemeetings.webex.com/ieeemeetings/j.php?ED=199185787&UID=497062897&ICS=MS&LD=1&RD=2&ST=1&SHA2=FnAW12TLJ7VUtIXkdcUs6VyB6XzBHIBqivtSqMhxCCI=

To check whether you have the appropriate players installed for UCF (Universal Communications Format) rich media files, go to https://ieeemeetings.webex.com/ieeemeetings/systemdiagnosis.php

http://www.webex.com

CCM:+12064450056x84982#

IMPORTANT NOTICE: This WebEx service includes a feature that allows audio and any documents and other materials exchanged or viewed during the session to be recorded. You should inform all meeting attendees prior to recording if you intend to record the meeting. Please note that any such recordings may be subject to discovery in the event of litigation.

 

Abstract

Particle swarm optimization has evolved from modeling social systems to applications for security and defense. Engineering applications for estimating battery state of charge and optimizing container port yard planning were among early successes. Applications to the fields of extended analog computing and biomedical engineering are ongoing. A recent focus has emerged in the fields of security and defense applications. Included are developments in unmanned vehicle mission planning optimization, intelligent traffic barrier networks, and resource allocation optimization for cognitive radio.

 

Speaker Bio

Russell C. Eberhart is the CTO of Phoenix Data Corporation, Indianapolis, Indiana. He is also Professor Emeritus of Electrical and Computer Engineering at the Purdue School of Engineering and Technology, Indiana University Purdue University Indianapolis (IUPUI). He was formerly Vice President and CTO of Computelligence, LLC. He received his Ph.D. from Kansas State University in electrical engineering. He is co-editor of a book on neural networks (1991), and co-author of Computational Intelligence PC Tools, published in 1996 by Academic Press. He is co-author of a book with Jim Kennedy and Yuhui Shi entitled Swarm Intelligence, published by Morgan Kaufmann in 2001. He is the co-author, with Yuhui Shi, of a book entitled Computational Intelligence: Concepts to Implementations, published in August 2007 by Morgan Kaufmann/Elsevier. He was awarded the IEEE Third Millenium Medal. In January 2001, he became a Fellow of the IEEE. He was elected a Fellow of the American Institute for Medical and Biological Engineering in 2002. He has been awarded four U. S. Patents, and is co-inventor for another pending patent. He has done ground-breaking work in applying swarm intelligence to human tremor analysis, sleep disorders medicine, evolutionary analog computing, logistics, spectrum warfare, and optimization of resource allocation.

 


Date

Wednesday June 27, 2012

Time

9:00-10:00 (EDT)

Location

Online Webinar (see registration below)

Title

Decentralized Coordination in Smart Grids by Self Organizing Dynamic Fuzzy Agents

Speaker

Alfredo Vaccaro

 

Assistant Professor

 

University of Sannio

   

Webinar Details

This webinar is organized by the IEEE Ottawa CIS & SMC Joint Chapter.

Registration is free but it is required..

After registering you will receive a confirmation email containing information about joining the Webinar.

System Requirements:
PC-based attendees
Required: Windows© 2000, XP Home, XP Pro, 2003 Server, Vista, 7

Macintosh©-based attendees
Required: Mac OS© X 10.4 (Tiger©) or newer

Note: the webinar is expected to last no longer than an hour. However, time is allowed for Questions and Answers.

For all other locations, please, check the actual time in your time zone. If you are not sure, you can use this Time Zone Converter

Please, login at least 15 minutes earlier to check your connection and make sure that you are ready to attend the talk when it begins.

 

Registration

Space is limited. Reserve your Webinar seat now at:
https://www2.gotomeeting.com/register/446316930

 

Abstract

Optimal power system asset control is one of the main issues to address in a Smart Grids context. In this domain, the application of traditional hierarchical control paradigms has some disadvantages that could hinder their application in Smart Grids where the constant growth of grid complexity and the need for massive pervasion of
Distribution Generation Systems (DGS) require more scalable, more flexible control and regulation paradigms. To try and overcome these challenges, in this webinar a decentralized non-hierarchal control architecture based on intelligent and cooperative smart entities is described. The proposed solution intends to bring two main contributions to the existing literature. The first is the definition of a decentralized architecture aimed at computing the actual value of the cost function and its gradient without the need of a central fusion center acquiring and processing all the sensor acquisitions. The second is the proposal of a distributed and cooperative optimization strategy aimed at identifying the optimal asset of the grid controllers.

 

Speaker Bio

Alfredo Vaccaro got the MSc. degree cum laude and commendation in Electronic Engineering from the University of Salerno in 1998. Since March 2002 he is Research Scientist and Ass. Professor of Electric Power Systems at the Department of Engineering of University of Sannio. His special fields of interest include electric power system analysis with particular emphasis to innovative architectures and new paradigms for smart electricity systems, cooperative smart sensor networks for protection and diagnostic of complex electricity systems, integration of distributed generation systems on electrical networks, soft computing and interval based methodologies in power systems analysis, power system communication for Wide Area Monitoring Systems.

 


Date

Wednesday November 23, 2011

Time

9:30-11:30 (EDT)

Location

Building M-50, NRC Auditorium, 1200 Montreal Road

Title

Anomaly Detection in Wireless Sensor Networks: Visual Assessment and Clustering in Environmental Monitoring Systems

Speaker

James C. Bezdek

 

Retired

 

Milton, FL, USA

   

Abstract

A. General information about wireless sensor networks (WSNs). There are four categories of network anomalies: isolated and epoch anomalies are aberrant behavior internal to a single node; second order anomalies are atypical behavior of an entire node; and higher order anomalies are one or more subtrees of nodes in the network that exhibit anomalous behavior. We discuss two types of models to detect anomalies; DCAD models that use data capture by level sets of elliptical summaries; and ESAD models that rely on visual assessment of elliptical summaries, with detection based on single linkage clustering.

B. We define and illustrate three (DCAD) models that use data capture by level sets of ellipsoids having effective radii chosen with differing assumptions (viz., % of points captured, % of points within k standard deviations from the mean, and % of points captured based on the chi-squared distribution. Examples are given using real WSN data from the Intel Berkeley Research Lab (IBRL).

C. The ESAD models use visual assessment of elliptical summaries for anomaly detection. These models begin with four measures of similarity on sets of ellipsoids, namely compound normalized, transformation energy, Bhattacharya distance and focal dissimilarity. We define the four measures and compare them with some simple two-dimensional examples that reveal some surprising differences between human and mathematical assessment of elliptical similarities.

D. The similarities in C easily become dissimilarities, so we can apply visual assessment techniques (the recursive iVAT method of talk R1.C) to images of the (dis)similarity data. These images enable us to assess cluster tendency amongst the set of ellipsoids, and estimate the number of clusters (of elliptical summaries) in the data.
E. We show that these images are capable of detecting each of the anomalous behaviors defined in A with numerical examples using both real WSN and artificial data. The real data include the IBRL network, the Great Barrier Reef Ocean Observation System, and the Grand St. Bernard network for wind monitoring in a mountain pass on the border between France and Switzerland. Our model reliable detects first and second order anomalies in each of the three real data sets that are caused by Cyclone Hamish and node drift. These examples illustrate the real effectiveness of the ESAD model for detecting unusual events in environmental monitoring networks.

 

Speaker Bio

Jim received the PhD in Applied Mathematics from Cornell University in 1973. Jim is past president of NAFIPS (North American Fuzzy Information Processing Society), IFSA (International Fuzzy Systems Association) and the IEEE CIS (Computational Intelligence Society): founding editor the Int'l. Jo. Approximate Reasoning and the IEEE Transactions on Fuzzy Systems: Life fellow of the IEEE and IFSA; and a recipient of the IEEE 3rd Millennium, IEEE CIS Fuzzy Systems Pioneer, and IEEE technical field award Rosenblatt medals. Jim's interests: woodworking, optimization, motorcycles, pattern recognition, cigars, clustering in very large data, fishing, co-clustering, blues music, wireless sensor networks, poker and visual clustering. Jim retired in 2007, and will be coming to a university near you soon.

 


Date

Tuesday September 27, 2011

Time

14:00-15:30 (EDT)

Location

Room 379, Building M-50, NRC, 1200 Montreal Road

Title

Multi-Sensor Fusion Performance Assessment

Speaker

Erik Blasch

 

Fusion Research Engineer

 

US Air Force Research Laboratory (AFRL)

 

Currently an AFRL Exchange Scientist to DRDC/Decision Support Group (Valcartier, QC)

   

Abstract

Contemporary research thrusts of information fusion (IF) deal with the integration of multiple sensors. The output from individual sensors and exploitation results in performance modeling, assessment and evaluation. Information fusion over the sensor products requires an integrated performance evaluation. For example, the use of imaging sensors from a variety of platforms requires a performance analysis over operating conditions of sensors, targets, and the environment (e.g. congested and urban terrains). The talk will focus on (1) tracking and sensor fusion performance evaluation, (2) methods of evaluation including common data sets, comparative analysis, and metrics, and (3) explorative examples of multisensor results to aid decision support.

Examples presented that demonstrate IF performance evaluation include: synthetic aperture radar (SAR), radar tracking, feature analysis and recognition, unattended ground sensors, and, wide area surveillance from Electro-optical sensors to detect, locate, follow targets. Additionally, metrics of Measures of Performance from low-level information fusion tracking and identification will be explored as enabling Measures of Effectiveness for high-level information fusion situation awareness.

 

Speaker Bio

Erik Blasch is currently an AFRL exchange scientist to Defence R&D Canada at Valcartier in the Future C2 Concepts and Structures Group of the C2 Decision Support Systems Section. Prior to the sabbatical, Dr. Blasch was the Information Fusion Evaluation Tech Lead for the Air Force Research Laboratory - COMprehensive Performance Assessment of Sensor Exploitation (COMPASE) Center (AFRL/RYAA), Adjunct EE and BME Professor in at Wright State University (WSU) and Air Force Institute of Technology (AFIT), and a reserve officer with the Air Force Office of Scientific Research (AFRL/AFOSR). He was a founding member of the International Society of Information Fusion (ISIF) in 1998 and the 2007 ISIF President. He is currently on the Board of Governors of the IEEE Aerospace and Electronics Systems Society. Dr. Blasch has focused on Automatic Target Recognition, Targeting Tracking, and Information Fusion research compiling 350+ scientific papers and book chapters. He is active in ISIF, IEEE (AES and SMC), and SPIE. Dr. Blasch received his B.S. in Mechanical Engineering from the Massachusetts Institute of Technology in 1992 and Master’s Degrees in Mechanical (‘94), Health Science (‘95), and Industrial Engineering (‘95) (Human Factors) from Georgia Tech and attended University of Wisconsin for an MD/PHD in Mech. Eng/Neurosciences (‘95-97) until being called to Active Duty in the United States Air Force. He completed an MBA(‘98), MSEE(‘98), MS Econ(‘99), MS/PhD Psychology (ABD) (‘01), and a PhD in Electrical Engineering (‘99) from Wright State University and is a graduate of Air War College (‘09). He is a Fellow of SPIE.

 


Date

Tuesday June 14, 2011

Time

11:00-12:30 (EDT)

Location

Online Webinar (see registration below)

Title

Semantic knowledge-based framework to improve the situation awareness of autonomous underwater vehicles

Speaker

Emilio Miguelanez Martin

 

Senior Development Engineer

 

Seebyte Ltd.

   

Webinar Details

This webinar is organized by the IEEE Toronto Signals & Computational Intelligence Chapter, the IEEE Ottawa CIS Chapter and the IEEE UKRI CIS Chapter.

Registration is free but it is required..

After registering you will receive a confirmation email containing information about joining the Webinar.

System Requirements:
PC-based attendees
Required: Windows© 2000, XP Home, XP Pro, 2003 Server, Vista, 7

Macintosh©-based attendees
Required: Mac OS© X 10.4 (Tiger©) or newer

Note: the webinar is expected to last no longer than an hour. However, time is allowed for Questions and Answers.

For all other locations, please, check the actual time in your time zone. If you are not sure, you can use this Time Zone Converter

Please, login at least 15 minutes earlier to check your connection and make sure that you are ready to attend the talk when it begins.

 

Registration

Space is limited. Reserve your Webinar seat now at:
h https://www2.gotomeeting.com/register/546211042

 

Abstract

This work proposes a semantic world model framework for hierarchical distributed representation of knowledge in autonomous underwater systems. This framework aims to provide a more capable and holistic system, involving semantic interoperability among all involved information sources. This will enhance interoperability, independence of operation, and situation awareness of the embedded service-oriented agents for autonomous platforms. The results obtained specifically impact on mission flexibility, robustness and autonomy. The presented framework makes use of the idea that heterogeneous real-world data of very different type must be processed by (and run through) several different layers, to be finally available in a suited format and at the right place to be accessible by high-level decision making agents. In this sense, the presented approach shows how to abstract away from the raw real-world data step by step by means of semantic technologies. The work concludes by demonstrating the benefits of the framework in a real scenario. A hardware fault is simulated in a REMUS 100 AUV while performing a mission. This triggers a knowledge exchange between the status monitoring agent and the adaptive mission planner embedded agent. By using the proposed framework, both services can interchange information while remaining domain independent during their interaction with the platform. These results are readily applicable to land and air robotics.

 

Speaker Bio

Emilio Miguela ́n ̃ez (M’01) received the MPhys degree in Physics from the University of Manchester in 2000. Then, he pursued a MSc degree in Information Technology (Systems) and his PhD degree on the application of evolutionary computation approaches to fault diagnosis in the domain of semiconductor at Heriot-Watt University. He started his professional career working as research engineer at Test Advantage Ltd developing intelligent systems and knowledge mining solutions for the semiconductor manufacturing environment.

 


Date

Wednesday May 18, 2011

Time

13:00-14:30 (EDT)

Location

Online Webinar (see registration below)

Title

Signal Fusion Using Novel Weighted Averages

Speaker

Jerry Mendel

 

Professor, Department of Electrical Engineering

 

University of South California

   

Webinar Details

This webinar is organized by the IEEE Toronto Signals & Computational Intelligence Chapter, the IEEE Ottawa CIS Chapter and the Coastal Los Angeles Section.

Registration is free but it is required..

After registering you will receive a confirmation email containing information about joining the Webinar.

System Requirements:
PC-based attendees
Required: Windows© 2000, XP Home, XP Pro, 2003 Server, Vista, 7

Macintosh©-based attendees
Required: Mac OS© X 10.4 (Tiger©) or newer

Note: the webinar is expected to last no longer than an hour. However, time is allowed for Questions and Answers.

For all other locations, please, check the actual time in your time zone. If you are not sure, you can use this Time Zone Converter

Please, login at least 15 minutes earlier to check your connection and make sure that you are ready to attend the talk when it begins.

 

Registration

Space is limited. Reserve your Webinar seat now at:
https://www2.gotomeeting.com/register/188381851

 

Abstract

The weighted average is arguably the earliest and most widely used form of signal fusion, but, traditionally, the weighted average is limited to numerical values for signals and weights. Using precise numerical values is often problematic, and suggests that more versatile—novel—weighted averages (NWAs) are needed, ones that are not limited to numbers. This webinar describes the following hierarchy of NWAs: the interval weighted average in which intervals are used for signals and/or weights; the fuzzy weighted average in which type-1 fuzzy sets are used for signals and/or weights; and, the linguistic weighted average in which words modeled by interval type-2 fuzzy sets are used for signals and/or weights. The webinar describes how these NWAs can be computed, and how NWAs can be used across a broad spectrum of decision making. Two hierarchical decision making applications illustrate the use of NWAs.

 

Speaker Bio

Jerry M. Mendel received the Ph.D. degree in electrical engineering from the Polytechnic Institute of Brooklyn, Brooklyn, NY. Currently he is Professor of Electrical Engineering and Systems Architecting Engineering at the University of Southern California in Los Angeles, where he has been since 1974. He has published over 500 technical papers and is author and/or editor of nine books, including Uncertain Rule-based Fuzzy Logic Systems: Introduction and New Directions (Prentice-Hall, 2001) and Perceptual Computing: Aiding People in Making Subjective Judgments (Wiley & IEEE Press, 2010). His present research interests include: type-2 fuzzy logic systems and their applications to a wide range of problems, including smart oil field technology and computing with words. He is a Life Fellow of the IEEE, a Distinguished Member of the IEEE Control Systems Society, and a Fellow of the International Fuzzy Systems Association. He was President of the IEEE Control Systems Society in 1986.

 


Date

Tuesday April 26, 2011

Time

10:00-11:30 (EDT)

Location

Online Webinar (see registration below)

Title

Type-2 Fuzzy Logic Controllers: A way Forward for Fuzzy Systems in Real World Environments

Speaker

Hani Hagras

 

Professor, School of Computer Science and Electronic Engineering

 

University of Essex (UK)

   

Webinar Details

This webinar is organized by the IEEE Toronto Signals & Computational Intelligence Chapter, theIEEE Ottawa CIS Chapter, the IEEE Computational Intelligence Society, the IEEE Region 7 (IEEE Canada) and the IEEE UK and Republic of Ireland CIS Chapter.

Registration is free but it is required..

After registering you will receive a confirmation email containing information about joining the Webinar.

System Requirements:
PC-based attendees
Required: Windows? 2000, XP Home, XP Pro, 2003 Server, Vista

Macintosh?-based attendees
Required: Mac OS? X 10.4 (Tiger?) or newer

Note: the webinar is expected to last no longer than an hour. However, time is allowed for Questions and Answers.

For all other locations, please, check the actual time in your time zone. If you are not sure, you can use this Time Zone Converter

Please, login at least 15 minutes earlier to check your connection and make sure that you are ready to attend the talk when it begins.

 

Registration

Space is limited. Reserve your Webinar seat now at:
https://www2.gotomeeting.com/register/792957898

 

Abstract

Type-1 Fuzzy Logic Controllers (FLCs) have been applied to date with great success to many different applications. However, for many real-world applications, there is a need to cope with large amounts of uncertainties. The traditional type-1 FLC using crisp type-1 fuzzy sets cannot directly handle such uncertainties.
A type-2 FLC using type-2 fuzzy sets can handle such uncertainties to produce a better performance. Hence, type-2 FLCs will have the potential to overcome the limitations of type-1 FLCs and produce a new generation of fuzzy controllers with improved performance for many applications, which require handling high levels of uncertainty.
Through the review of the various type-2 FLC applications, it has been shown that as the level of imprecision and uncertainty increases, the type-2 FLC will provide a powerful paradigm to handle the high level of uncertainties present in real-world environments. It has been also shown in various applications that the type-2 FLCs have given very good and smooth responses that have always outperformed their type-1 counterparts. Thus, using a type-2 FLC in real-world applications can be a better choice since the amount of uncertainty in real systems most of the time is difficult to estimate. It is envisaged to see a wide spread of type-2 FLCs in many real-world application in the next decade.
This talk will introduce the interval type-2 FLCs and how they present a way forward for fuzzy systems in real world environments and applications that face high levels of uncertainties. The talk will present different ways to design interval type-2 FLCs. The talk will also present the successful application of type-2 FLCs to many real world settings including industrial environments, mobile robots, ambient intelligent environments and intelligent decision support systems. The talk will conclude with an overview on the future directions of type-2 FLCs.

 

Speaker Bio

Prof. Hani Hagras is a Professor in the School of Computer Science and Electronic Engineering, Director of the Computational Intelligence Centre and the Head of the Fuzzy Systems Research Group in the University of Essex, UK. His major research interests are in computational intelligence, notably type-2 fuzzy systems, fuzzy logic, neural networks, genetic algorithms, and evolutionary computation. His research interests also include ambient intelligence, pervasive computing and intelligent buildings. He is also interested in embedded agents, robotics and intelligent control. He has authored more than 200 papers in international journals, conferences and books. He is a Fellow of the Institution of Engineering and Technology (IET (IEE)) and a Senior Member of the Institute of Electrical and Electronics Engineers (IEEE). He was the Chair of IEEE Computational Intelligence Society (CIS) Senior Members Sub-Committee. He is also the Vice- Chair of the IEE CIS Emergent Technologies Technical Committee. His research has won numerous prestigious international awards where most recently he was awarded by the IEEE Computational Intelligence Society (CIS), the 2004 Outstanding Paper Award in the IEEE Transactions on Fuzzy Systems. He is an Associate Editor of the IEEE Transactions on Fuzzy Systems. He is also an Associate Editor of the International Journal of Robotics and Automation, the Journal of Cognitive Computation, the Journal of Applied Computational Intelligence and Soft Computing and the Journal of Ambient Computing and Intelligence. He is a member of the IEEE Computational Intelligence Society (CIS) Fuzzy Systems Technical Committee. Prof. Hagras chaired several international conferences where most recently he served as the General Co-Chair of the 2007 IEEE International Conference on Fuzzy systems London, July 2007 and he served as the Programme Chair of 2009 IEEE Symposium on Intelligent Agents, Nashville, USA, April 2009. He also served as the Programme Chair of the 2010 International Conference on Intelligent Systems and Design (ISDA 2010) and he is also the General Co-Chair of the 2011 IEEE Symposium on Intelligent Agents and 2011 IEEE Symposium on Advances to Type-2 Fuzzy Logic Systems.

 


 

Date

Friday December 17, 2010

Time

13:00-14:00

Location

Room 5077, SITE Building, University of Ottawa

Title

Nature-Inspired Optimization in Fault-Reactive Wireless Sensor and Robot Networks

Speaker

Rafael Falcon

 

Ph.D. Candidate, SITE

 

University of Ottawa

   

The talk will be followed by the annual meeting of the chapter

Abstract

Small teams of mobile robots provide nowadays the ability to assist wireless sensor networks in many threatening scenarios that unexpectedly arise during their operational lifetime. The perceived risk or vulnerability that the network is exposed to triggers an immediate, corporate action from the robotic agents (actuators). We focus on a sort of actuators which are able to carry static sensors and deploy them all over the field. By doing so, they can collaboratively react to hardware/software faults that stem in the sensor nodes, thus preserving the network coverage. Determining the true ensemble of faulty nodes and the ensuing replacement trajectory are NP-hard problems which call for the application of metaheuristic optimization algorithms. In this talk, we will illustrate how the social interaction mechanisms present in natural systems like ant colonies, bird flocks, firefly swarms and groups of chromosomes can be exploited to solve challenging combinatorial optimization problems in the context of a fault-reactive wireless sensor and robot network.

 

Speaker Bio

Rafael Falcon received his Bachelor and Master degrees in Computer Science from Universidad Central de Las Villas (Cuba) in 2003 and 2006, respectively, before joining the School of Information Technology and Engineering ( University of Ottawa ) in 2008 as a PhD candidate. He has co-edited two Springer volumes on fuzzy and rough set theories and is a member of the International Rough Set Society, IEEE and IEEE Computational Intelligence Society. His current research interests embrace wireless sensor and robot networks, evolutionary optimization, fuzzy logic and fault-tolerant systems. Besides having served as reviewer for prestigious IEEE CIS journals and conferences, the speaker is collaborating nowadays with an industry partner in the Ottawa area to embed the core protocols of his PhD thesis into real-world, sensory-operated environments.

 


Date

Wednesday May 12, 2010

Time

19:00-20:00

Location

Room 5077, SITE Building, University of Ottawa

Title

The Use of General Neuron Functions within Neural Networks

Speaker

Alan J. Barton

 

NRC-CNRC Institute for Information Technology

   

Abstract

Classical Artificial Neural Networks (ANNs) may have their neurons organized in many ways. For example, Feedforward Neural Networks are aggregations of weights multiplied by inputs and controlled via activation functions; with the potential addition of bias nodes.
This presentation will demonstrate the use of a methodology for construction of ANNs that do not require the use of weights nor the apriori specification of activation functions when learning the functions associated to the neurons within the ANN as is performed within the classical case. A brief discussion of related work and examples will be shown from various applications of the approach, including:
   - Biological Data, such as Magnetic Resonance Spectra from Brain Cancer samples and clinical data from Breast Cancer samples,
   - Geophysical Prospecting Data, such as from Insunza measurements for learning about the presence of an underground cave, and
   - Hydrochemical Data, such as from Werenskiold glacial water samples for learning about global climate changes.

In addition, if time permits, a preliminary analysis of the parameters controlling the construction of the ANNs will be stated (e.g. the Parameter Space) along with a discussion of one possible way to analyse the set of constructed ANNs (e.g. the Mathematical Expression Space; based on a recently published similarity measure).

 

Speaker Bio

Alan J. Barton's current research interests lie within Computational Intelligence (e.g. Neural Networks, Evolutionary Computation, etc.) and High Performance Computing (e.g. Distributed and Parallel Computation, etc.).  He holds a Master of Computer Science (M.C.S.) from Carleton University in Ottawa, Ontario, Canada (2009) and has a combined Computer Science and Mathematics degree (B.Sc.) from the University of Victoria in British Columbia, Canada (2000). He has also completed the required course and laboratory work (Proteomics, Genomics and Bioinformatics) and obtained a certificate in BioInformatics (2006).

 


Date

Thursday March 25, 2010

Time

18:00-21:00

Location

Algonquin College, T-Building, Room T327

Title

DRDC Biometrics Activities and IEEE CIS Biometrics Mission

Speaker

Qinghan Xiao, Defence Scientist

 

Defence Research and Development Canada

   

Abstract

In recent years, biometric technologies have emerged as solutions to security-related applications such as access control, identity verification, forensic investigation, and terrorism suspect identification. Various biometric technologies are available for identifying or verifying an individual by measuring his/her fingerprint, hand, face, signature, voice, or a combination of the traits. Since a biometric trait cannot be captured in precisely the same way twice, biometric matching is always a “fuzzy comparison”. This feature makes computational intelligence (CI), which is primarily based on artificial intelligence, neural networks, fuzzy logic, evolutionary computing, etc., an ideal solution for solving different biometric problems.

This seminar will address the following issues based on the speaker’s expertise in biometric technologies and experience in organizing IEEE biometric activities:

  • Biometrics and biometric applications
    • Various biometric technologies along with their advantages and limitations
    • Generic biometric system configuration
    • Examples of biometric implementations
  • DRDC Ottawa biometric R&D
    • Facial presence monitoring system for information security
    • Multi-biometric fusion
    • Non-ideal fingerprint image processing
    • Fingerprint spoofing and anti-spoofing
  • IEEE CIS biometrics mission and activities
    • Task Force on Biometrics of Intelligent Systems Applications (ISA) TC
    • Special sessions and workshops
    • “Biometrics, theory, methods, and applications”, IEEE Press Series on Computational Intelligence
 

Speaker Bio

Qinghan Xiao, IEEE Senior Member, is a Defence Scientist at the Defence R&D Canada. He has served as the Chair of Task Force on Biometrics of Intelligent Systems Applications Technical Committee since 2008, and has been recently appointed as the CIS representative at IEEE Biometrics Council. His current research interests include biometric, smart card and RFID technologies. Dr. Xiao is a Canadian delegate of the ISO/IEC JTC1 SC37 standards committee on biometrics, and leads “Red Team/Blue Team” study for the Canadian Operational Support Command. He has been invited as speaker and chaired biometric special sessions/workshops for several national and international events. Dr. Xiao holds a Ph.D. in Computer Science from the University of Regina.

 


Date

Wednesday March 17, 2010

Time

14:00-16:00

Location

Room 5084, SITE Building, University of Ottawa

Title

Development of a Robotic Platform for Human Robot Interaction

Speaker

Genci Capi , Associate Professor

 

University of Toyoma, Japan

 

Department of Electrical and Electronic Systems Engineering

   

Abstract

Robots are, or soon will be, used in such critical domains as search and rescue, military battle, mine and bomb detection, scientific exploration, law enforcement, and hospital care. Such robots must coordinate their behaviors with the requirements and expectations of human team members; they are more than mere tools but rather quasi-team members whose tasks have to be integrated with those of humans. In the Intelligent Robotics Lab, University of Toyama we are working on Human-Robot Interaction and in this talk I will present the research work on:
1. Gesture recognition for human robot interaction.
2. Human robot interaction using natural language.
3. Intelligent robot navigation using the visual information.
4. Robot Map Building.

 

Speaker Bio

Genci Capi is an Associate Professor of Electrical and Electronic Engineering at the University of Toyama, and the Director of the Intelligent Robotics Laboratory. His current research interests are in the areas of intelligent and autonomous robots, brain-machine interface and multi-robots system. He is the recipient of several awards such as the Highly Commended Award from the Literati Awards for Excellence. Dr. Capi is member of the editorial board of several journals and organizer of many conferences in the field of intelligent robots. He has authored more than 100 articles in high-impact journals and conferences proceedings.

 


Date

Tuesday February 23, 2010

Time

11:00-12:00

Location

Room 5077, SITE Building, University of Ottawa

Title

Risk-Based Multiobjective Optimization for a Vehicle Fleet Mix Problem

Speaker

Slawo Wesolkowski, Scientist

 

DRDC-Ottawa

 

Centre for Operational Research and Analysis (CORA)

 

http://www.cora.drdc-rddc.gc.ca/index-eng.asp

   

Abstract

Organizations transporting people and cargo are concerned about determining how many vehicles they need to accomplish required transportation tasks. Those approaches usually involve using Discrete Event Simulation (DES). However, integrating DES in a framework to determine an optimal fleet is impossible due to the high computational cost of DES and the very large combinatorial space of possible fleets. Therefore, a surrogate or approximate model for DES needs to be devised. In this talk, the Stochastic Fleet Estimation (SaFE) model is presented, a very simple Monte Carlo-based model, which generates a vehicle fleet based on the average set of required tasks that the fleet is supposed to accomplish (the average fleet). This model is then used within a multiobjective optimization framework (using NSGA II as the optimizer) in order to determine optimal fleets with respect to different objectives. The optimization searches for Pareto-optimal combinations of valid platform-assignments for a list of tasks, which can be applied to entire scenarios output by SaFE. The following three objectives are used: performance, cost and risk. Variance information associated with the average platform numbers generated by SaFE is used to compute different risk-based objectives. Various optimal solution fleets are discussed.

 

Speaker Bio

Slawo Wesolkowski is a Scientist at DRDC CORA. He has previously worked for Vantage Point International (now C-CORE), NCR Canada Ltd., Nortel, Moteurs Leroy-Somer (France), the University of Waterloo, and the National Research Council of Canada. He holds five US patents, and one Canadian/EU patent. He obtained BASc, MASc and PhD degrees in Systems Design Engineering from the University of Waterloo, Canada. He is currently Vice President Members Activities of the IEEE Computational Intelligence Society. He was the General Chair of the 2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications (IEEE CISDA).

 


Date

Friday December 04, 2009

Time

12:30-13:30

Location

Room 5084, SITE Building, University of Ottawa

Title

Much To Do About Bidirectional Associative Memory

Speaker

Sylvain Chartier, Assistant Professor

 

University of Ottawa

 

School of Psychology

 

http://aix1.uottawa.ca/~schartie/

   

The talk will be followed by the annual meeting of the chapter

Abstract

Associative memory is at the core of human learning. This type of learning is best captured using Bidirectional Associative Memory (BAM). BAM has been extensively studied since its introduction by Kosko (1988). Over the years, several variants have been proposed to overcome the original model’s limited storage capacities and improve its noise sensitivity, and most of today’s BAM models can store and recall all the patterns in a learning set. Over the last few years, we proposed a BAM that is able; to learn online any type of correlated patterns (binary and real values); to perform multi-step pattern recognition as well as one-to-many association; to control the attractors (switch from fixed-points to dynamic orbits, momentarily disable desired attractors); to perform nonlinear separable task and perform autonomous perceptual feature creation; to learn in noisy environments; to create and reorganize its cluster-based categories in a flexible way and to encompasses competitive and topological model properties. All those behaviors are obtained using the same learning rule (based on covariance only), the same output function and the same general architecture. Therefore, the proposed BAM is one step closer to unified various classes of models within a general architecture as well as being a good candidate to explain human learning behaviors.

 

Speaker Bio

Sylvain Chartier received the B.A. degree from the University of Ottawa, in 1993 and the B.Sc. and Ph.D. degrees from the Université du Québec à Montréal, in 1996 and 2004, respectively, all in psychology. His doctoral thesis was on the development of an artificial neural network for autonomous categorization. From 2004 to 2007, he was a post-doctoral fellow at the Centre de recherche de l’Institut Philippe-Pinel de Montréal where he conducted research on eye-movement analysis and classification. Since 2007, He is an Assistant Professor at the University of Ottawa. His research interests are in the development of unsupervised and supervised recurrent associative memories. He is also interested in nonlinear time series analysis as well as cognition, perception, and statistics.

 


Date

Monday November 02, 2009

Time

10:30-11:30

Location

Building M-50, NRC Auditorium, 1200 Montreal Road

Title

Swarm Intelligence: Where We've Been and Where We're Going

Speaker

Russel Eberhart , University Professor

 

Indiana University Purdue University Indianapolis

 

Purdue School of Engineering and Technology

 

http://www.engr.iupui.edu/~eberhart/

   

Abstract

The definition of, and basic principles of, swarm intelligence are first discussed.  Application areas are listed.  Three swarm intelligence paradigm examples are reviewed: cultural algorithms, ant colony optimization, and particle swarm optimization.  Tracking and optimizing dynamic systems with swarms is discussed.  Recent applications are summarized: unmanned air vehicle mission planning, putting a person in the swarm using an NK landscape game, and optimizing resource allocation.  Measuring swarm population diversity, and using non-parametric statistics for performance metrics are reviewed.  Finally, recent accomplishments of the swarm intelligence field, and challenges being faced by the field, are outlined.

 

Speaker Bio

Russell C. Eberhart is Professor of Electrical and Computer Engineering at the Purdue School of Engineering and Technology, Indiana University Purdue University Indianapolis (IUPUI).  He is also Vice President and Chief Technology Officer of Computelligence LLC, Indianapolis, Indiana.  He received his Ph.D. from Kansas State University in electrical engineering.  He is co-editor of a book on neural networks, and co-author of Computational Intelligence PC Tools, published in 1996 by Academic Press.  He is co-author of a book with Jim Kennedy and Yuhui Shi entitled Swarm Intelligence, published by Morgan Kaufmann/Academic Press in April 2001.  He was awarded the IEEE Third Millenium Medal.  In 2001, he became a Fellow of the IEEE, and in 2002 he became a Fellow of the American Institute for Medical and Biological Engineering.   He is the co-author, with Yuhui Shi, of a book entitled Computational Intelligence: Concepts to Implementations, published by Morgan Kaufmann/Elsevier in 2007.  His areas of research include swarm intelligence and extended analog computing, and the analysis of sleepy and inattentive driving.

 


Date

Friday July 10, 2009

Time

13:00-14:00

Location

Conference Room, Building T-86 5084, DRDC Ottawa

Title

Cognitive Tracking Radar

Speaker

Simon Haykin, University Professor

 

McMaster University

 

Cognitive Systems Laboratory

 

http://soma.mcmaster.ca/haykin.php

   

Abstract

In early 2006, I described the idea of Cognitive Radar in an invited paper that was published in the IEEE Signal Processing Magazine. This paper was followed by an invited chapter on Cognitive Radar that appeared in a book edited by Fulvio Gini. With these two contributions, the idea of Cognitive radar was born.

In this lecture I will expand on the practical implementation of a Cognitive Tracking Radar. Most importantly, experimental results will be presented tot  demonstrate the practical validity of this new and exciting development,. The Cognitive Tracker   builds on two functional blocks:

(a) the newly discovered Cubature Kalman Filter for estimating the state of the radar environment, and

(b) approximate dynamic programming for the optimum selection of transmitted radar waveform on the basis of information passed onto the transmitter by the receiver.

The experimental study is based on data pertaining to an "object falling in space." I will close the lecture by describing my vision as to how I see the impact of cognition on such diverse areas of application as radar, wireless communications, and the power grid.

 

Speaker Bio

Simon Haykin received his B.Sc. (First-class Honours), Ph.D., and D.Sc., all in Electrical Engineering from the University of Birmingham, England. He is a Fellow of the Royal Society of Canada, and a Fellow of the Institute of Electrical and Electronics Engineers. He is the recipient of the Henry Booker Medal from 2002, the Honorary Degree of Doctor of Technical Sciences from ETH Zentrum, Zurich, Switzerland, 1999, and many other medals and prizes. He is a pioneer in adaptive signal-processing with emphasis on applications in radar and communications, an area of research which has occupied much of his professional life.

 

DRDC Seminar Series

This presentation is part of the Defence R&D Canada - Ottawa Seminar Series. Visitors are encouraged to contact the seminar committee (drdco.seminar@drdc-rddc.gc.ca) before traveling to DRDC Ottawa. Further logistical information is appended below. We invite speakers from government, industry and academia, in all aspects of defense research and related civil applications.

Shirleys Bay Campus staff without access to Building 5A can present themselves at the building¹s main entrance at 9:45; an escort to Conf. Room B will be available. DRDC employees without access to Shirleys Bay Campus should explicitly request special arrangements from the DRDC Ottawa seminar committee. In addition, staff members are welcome to invite other visitors; however, security arrangements become the sole responsibility of the staff making this invitation.

 


Date

Thursday April 30, 2009

Time

10:30-11:30

Location

Room 5084, SITE Building, University of Ottawa

Title

Hand Gesture Recognition and Applications in Human-Computer Interactions

Speaker

Qing Chen, Post-Doc

 

University of Ottawa

 

School of Information Technology and Engineering

 

http://www.discover.uottawa.ca/~qchen

   

Abstract

In this talk, I will introduce our work on vision-based hand gesture recognition and its applications in human-computer interactions. To effectively detect different hand gestures and analyze hand movements, we divide the problem into two levels. The lower level of our approach focuses on detecting and recognizing different hand postures with a set of Haar-like features. The advantages and limitations of this approach compared with other approaches such as color-based algorithms will be discussed. The higher-level tries to analyze the trajectories of the hand postures detected by the lower-level using a set of predefined  grammars. With the recognized gestures, we can convert them in to a set of gesture commands for HCI applications such as playing a car navigation game and interacting with a web-based browser.

 

Speaker Bio

Qing Chen is currently a PostDoc at the DiscoverLab of University of Ottawa. He received his Ph.D. in Electrical Engineering from University of Ottawa in 2008. His Ph.D. research is focused on real-time vision-based hand tracking and gesture recognition. His general research interests include vision-based object detection, tracking and recognition, statistical/syntactic pattern recognition, vision-based human-computer interactions. He also received his M.A.Sc from University of Ottawa in 2004 and his Bachelor degree from Jianghan Petroleum Institute, Hubei, China in 1994.

 


Date

Tuesday February 10, 2009

Time

12:00-13:30

Location

Room 5084, SITE Building, University of Ottawa

Title

Neural Networks for High-Frequency Electronic Modeling and Design

Speaker

Q. J. Zhang, Professor (IEEE Fellow)

 

Carleton University

 

Department of Electronics

 

http://www.doe.carleton.ca/~qjz

   

Abstract

Recent advances in the application of Artificial Neural Networks (ANN) to radio-frequency (RF) and microwave design created an exciting direction of computer-aided modeling and design of high-frequency electronics. ANNs are trained to learn the high-frequency behavior of electronic components, and trained ANNs can be used as models for high-level electronic design. The ANN models are much faster than detailed electromagnetic/physics based models of electronic components, and more accurate than conventional empirical/equivalent circuit models. It leads to substantial increase in modeling accuracy, speed, and flexibility. Applications are being made in modeling and design of passive and active RF/microwave electronic components and circuits, high-speed VLSI interconnects, printed antennas, LTCC circuits, semiconductor devices, measurement standards, filters, amplifiers, mixers and so on. Automated model generation algorithms integrating data generation and ANN training are being developed. Knowledge based neural networks exploiting prior knowledge such as empirical/semi-analytical models are being introduced in microwave computer-aided design (CAD). This leads to new level of CAD methodologies combining equivalent circuit/empirical models, electromagnetic/physics simulation and behavioral modeling with ANN and optimization algorithms for fast and accurate design of high-frequency circuits and systems. This talk presents a review of the state of the art in these emerging directions. The presentations highlight implementable methodologies for automated modeling and design of high-frequency electronic components, circuits and systems. The presentation covers fundamental concepts and methodologies, industrial applications, and future trends in R&D.

 

Speaker Bio

Q.J. Zhang received the B.Eng. degree from the Nanjing University of Science and Technology, Nanjing, China in 1982, and the Ph.D. Degree in Electrical Engineering from McMaster University, Hamilton, Canada, in 1987. He joined the Department of Electronics, Carleton University, Ottawa, Canada in 1990 where he is presently a Professor.
His research interests are modeling, optimization and neural networks for high-speed/high-frequency electronic design, and has over 200 publications in the area. He is an author of the book Neural Networks for RF and Microwave Design (Boston: Artech House, 2000), and a coeditor of Modeling and Simulation of High-Speed VLSI Interconnects (Boston: Kluwer, 1994). He is a contributor to Encyclopedia of RF and Microwave Engineering, (New York: Wiley, 2005), Fundamentals of Nonlinear Behavioral Modeling for RF and Microwave Designs, (Boston: Artech House, 2005), Tutorials on Emerging Methodologies and Applications in Operations Research, (New York: Springer, 2005), and Analog Methods for Computer-Aided Circuit Analysis and Diagnosis, (New York: Marcel Dekker, 1988). He was a Guest co-Editor for the Special Issue on High-Speed VLSI Interconnects for the International Journal of Analog Integrated Circuits and Signal Processing (Boston: Kluwer, 1994), and twice a Guest Editor for the Special Issues on Applications of ANN to RF and Microwave Design for the International Journal of RF and Microwave CAE (New York: Wiley, 1999, 2002).
Dr. Zhang is on the editorial board of the IEEE Transactions on Microwave Theory and Techniques, the International Journal of RF and Microwave CAE, and the International Journal of Numerical Modeling. He is an Associate Editor for the Journal of Circuits, Systems and Computers. He is a member of the Technical Committee on CAD of the IEEE MTT Society. He is a Fellow of the IEEE, and a Fellow of the Electromagnetics Academy..

 


Date

Thursday December 18, 2008

Time

10:30-12:00

Location

Building M-50, NRC Auditorium, 1200 Montreal Road

Title

Soft Computing for Sensor and Algorithm Fusion

Speaker

James M. Keller , Professor

 

University of Missouri-Columbia

 

Electrical and Computer Engineering Department

 

http://www.missouri.edu/~kellerj

   

The talk will be followed by the annual meeting of the chapter

Abstract

Sensor and algorithm fusion is playing an increasing role in many application domains. As detection and recognition problems become more complex and costly (for example, landmine detection and automatic activity monitoring), it is apparent that no single source of information can provide the ultimate solution. However, complementary information can be derived from multiple sources. Given a set of outputs from constituent sources, there are many frameworks within which to combine the pieces into a more definitive answer. This tutorial will focus on the fusion of multiple partial confidence values within the framework of fuzzy set theory.

So, the question then becomes: what methodology do we use to combine partial decision information? There are many choices, but I will focus on the use of fuzzy set theoretic mechanisms to fuse confidence from multiple sources. Two general approaches will be considered, fuzzy integrals and fuzzy logic rule-based systems. Fuzzy integrals have a long history and have been studied in the context of pattern recognition and information fusion for several years being first introduced for this purpose by Tahani and Keller in 1990. Fuzzy integrals combine the objective evidence supplied by each information source with the expected worth of each subset of information sources (via a fuzzy measure) to assign confidence to hypotheses or to rank alternatives in decision making. This is a nonlinear combination of information and the worth of the information for the decision in question, dealing with the uncertainty in both forms of data. Different fuzzy measures yield different integration operations, including averaging, linear combinations of order statistics, and many others. Measures can be found by heuristic assignment or via training algorithms. New results with discriminative training will be discussed. Next, a fusion system based on a linguistic extension of the Choquet fuzzy integral will be shown. The uncertainty in the data is now expressed as a linguistic vector, i.e., a vector of fuzzy sets. The linguistic Choquet integral is used to fuse both position and confidence uncertainty in the landmine detection scenario.

Fuzzy logic rule-based systems provide another mechanism to fuse together the results of different features, classification algorithms and sensors. Such a system employs rules much like those that a human expert might derive. Again, uncertainty in the component parts is modeled by linguistic variables taking on fuzzy sets as values. I will describe the application of fuzzy rule-based classifiers in image processing and landmine detection.

 

Speaker Bio

James M. Keller received the Ph.D. in Mathematics in 1978. He holds the University of Missouri Curators’ Professorship in the Electrical and Computer Engineering and Computer Science Departments on the Columbia campus. He is also the R. L. Tatum Professor in the College of Engineering. His research interests center on computational intelligence: fuzzy set theory and fuzzy logic, neural networks, and evolutionary computation with a focus on problems in computer vision, pattern recognition, and information fusion including bioinformatics, spatial reasoning in robotics, geospatial intelligence, sensor and information analysis in technology for eldercare, and landmine detection. His industrial and government funding sources include the Electronics and Space Corporation, Union Electric, Geo-Centers, National Science Foundation, the Administration on Aging, The National Institutes of Health, NASA/JSC, the Air Force Office of Scientific Research, the Army Research Office, the Office of Naval Research, the National Geospatial Intelligence Agency, and the Army Night Vision and Electronic Sensors Directorate. Professor Keller has coauthored over 300 technical publications.

Jim is a Fellow of the Institute of Electrical and Electronics Engineers (IEEE) for whom he has presented live and video tutorials on fuzzy logic in computer vision, is an International Fuzzy Systems Association (IFSA) Fellow, is a national lecturer for the Association for Computing Machinery (ACM), is an IEEE Computational Intelligence Society Distinguished Lecturer, and is a past President of the North American Fuzzy Information Processing Society (NAFIPS). He received the 2007 Fuzzy Systems Pioneer Award from the IEEE Computational Intelligence Society. He finished a full six year term as Editor-in-Chief of the IEEE Transactions on Fuzzy Systems, is an Associate Editor of the International Journal of Approximate Reasoning, and is on the editorial board of Pattern Analysis and Applications, Fuzzy Sets and Systems,International Journal of Fuzzy Systems, and the Journal of Intelligent and Fuzzy Systems. He is currently the Vice President for Publications of the IEEE Computational Intelligence Society. He was the conference chair of the 1991 NAFIPS Workshop, program co-chair of the 1996 NAFIPS meeting, program co-chair of the 1997 IEEE International Conference on Neural Networks, and the program chair of the 1998 IEEE International Conference on Fuzzy Systems. He was the general chair for the 2003 IEEE International Conference on Fuzzy Systems.

 


Date

Thursday July 3, 2008

Time

11:00-12:00

Location

Room 379, Building M-50, NRC Auditorium, 1200 Montreal Road

Title

Applying Relational Learning to Structural Molecular Biology Problems

Speaker

Marcel Turcotte, Professor

 

University of Ottawa

 

School of Information, Technology and Engineering

 

http://www.site.uottawa.ca/~turcotte

   

Abstract

I will present our work on applying relational learning to discover rules characterizing protein folds. Inductive Logic Programming (ILP) has been chosen for its ability to 1) discover relations, 2) represent background information, as well as 3) its expressiveness. Several representations for the background set have been explored, and the results have been interpreted in their biological context.
The rules that were automatically found are often similar to the descriptions found in SCOP (a database of protein folds) or the published scientific literature. Finally, I will conclude presenting some future applications, in particular, for the determination of protein function from structure information.
This is a joint work with M.J.E. Sternberg and S. Muggleton from Imperial College London/UK.

 

Speaker Bio

I (Marcel Turcotte) completed a Ph.D. at the University of Montreal, Canada, under the supervision of Guy Lapalme and Robert Cedergren. I was then a postoctoral fellow at the University of Florida, USA, where I worked with Steven Benner on evolutionary-based approaches to protein secondary structure prediction. I then moved to the United Kingdom to work in the Biomolecular Modelling Laboratory (Mike Sternberg, head) of the Imperial Cancer Research Fund. In 2000, I returned to Canada where I joined the School of Information Technology and Engineering at the University of Ottawa.

 


Date

Tuesday March 18, 2008

Time

10:00-11:00

Location

Room 5084, SITE Building, University of Ottawa

Title

Neural Networks for Environment Recognition and Local Navigation of a Mobile Robot

Speaker

Moufid Harb, Ph.D., Research Scientist

 

Larus Technologies Corp.

 

http://www.larus.com

 

University of Ottawa

 

School of Information, Technology and Engineering

 

http://www.site.uottawa.ca/~mharb

   

Abstract

This presentation will focus on a computer based design and test of three neural controllers for local navigation, and another two neural networks for environmental recognition, fed off-line by a simulated model of a laser range-finder. These neural networks are the major components of a control system that performs a global neural navigation of a mobile robot, which could be used to perform industrial missions within industrial environments. This control system can guide a mobile robot to track its predefined path to arrive to its final goal through a set of sub-goals, or autonomously plan its path to arrive to the desired final goal, and to avoid obstacles that are found along the way. The presentation will include simulation results and live demonstrations.

 

Speaker Bio

Moufid Harb (M'07) is a Research Collaborator with the School of Information Technology and Engineering at the University of Ottawa, and a Research Scientist with Larus Technologies. He received his Bachelor of Eng. in Electrical Engineering in 1983 from Damascus University, his M.Sc. in Instrument Design and Application in 1994 from Manchester University, Institute of Science and Technology (UMIST), England-UK and his Ph.D. in Electrical Engineering in 2001 from Damascus University/Syria in collaboration with Ruher University of Bochum/Germany. His research interests include autonomous robotic navigation, sensor modeling and simulation, and intelligent systems. Dr. Harb is a member of the IEEE Ottawa Section. He is a member of the IEEE Instrumentation and Measurement Society, and the IEEE Computational Intelligence Society. He is currently a vice-chair of the IEEE Computational Intelligence Society - Ottawa Chapter.

 


Date

Wednesday December 19, 2007

Time

10:30-11:30

Location

Room 5084, SITE Building, University of Ottawa

Title

Does pain hurt in both French and English?

Speaker

Oana Frunza, Ph.D. Candidate

 

University of Ottawa

 

Text Analysis and MAchine LEarning (TAMALE) Group

 

http://www.site.uottawa.ca/~ofrunza

   

The talk will be followed by the annual meeting of the chapter

Abstract

Cognates are pair of words in different languages similar in spelling and meaning. They can help a second-language learner on the tasks of vocabulary expansion and reading comprehension. False friends are pairs of words that have similar spelling but different meanings. Partial cognates are pairs of words in two languages that have the same meaning in some, but not all contexts. Detecting the actual meaning of a partial cognate in context can be useful for Machine Translation tools and for Computer-Assisted Language Learning tools.

In this talk I will present research that I have done for cognates and false-friends identification and partial cognate disambiguation tasks. I will describe the method that we propose to automatically classify a pair of words as cognates or false friends, and also a supervised and a semi-supervised method to disambiguate partial cognates between two languages. We applied all our methods to French and English, but they can be applied to other pairs of languages as well.

I will also present a tool that I built to annotate French texts with equivalent English cognates or false friends, in order to help a second-language learner.

 

Speaker Bio

Oana Frunza is currently a Ph.D. Candidate at University of Ottawa, Canada. She is doing research in Natural Language Processing and Machine Learning with Dr. Diana Inkpen. She has a Computer Science background form “Babes-Bolyai” University, Romania and a M.S.C. Diploma from University of Ottawa, Canada in Natural Language Processing and Machine Learning. Her main research is focused on automatic text classification, semantic representation and machine learning techniques applied to various text processing tasks. She is an author or co-author of papers that were published in prestigious international conferences.

 


Date

Friday November 09, 2007

Time

10:30-12:00

Location

Building M-50, NRC Auditorium, 1200 Montreal Road

Title

Data Mining, Neural Networks and Rule Extraction

Speaker

Jacek M. Zurada, Distinguished University Scholar (IEEE Fellow)

 

University of Louisville

 

Computational Intelligence Laboratory

 

http://ci.louisville.edu/zurada/

   

Abstract

This lecture discusses paradigms of neurocomputing in context of effective data mining tasks such as data-driven modeling, feature extraction, dimensionality reduction, visualization, knowledge extraction and logic rule discovery. These tasks often involve handling of heterogenous, subjective, imprecise and noisy data. Of special importance here is the concept of dimensionality reduction of input data vectors. An approach is presented that leads to reduced models achieved through evaluation of sensitivity matrices of perceptron networks. When developing reduced models it is also useful to eliminate underutilized internal weights and, possibly, also neurons via pruning techniques. The concluding part of the talk reviews the potential of perceptron networks for producing understandable IF-THEN rules.

 

Speaker Bio

Dr. Jacek M. Zurada serves as the Distinguished University Scholar and Professor of Electrical and Computer Engineering at the University of Louisville, Louisville, Kentucky, USA. He is the author of several books such Introduction to Artificial Neural Systems, and co-editor of Computational Intelligence: Imitating Life, and of Knowledge Based Neurocomputing. He is also the author or co-author of more than 300 journal and conference papers in the area of neural networks and computational intelligence. In 1998-2003, Dr. Zurada was the Editor-in-Chief of IEEE Transactions on Neural Networks. In 2004-05 he served as the President of IEEE Computational Intelligence Society. He is an IEEE Fellow.

 


Date

Tuesday July 17, 2007

Time

13:30-14:30

Location

Room 379, Building M-50, NRC Auditorium, 1200 Montreal Road

Title

Current Applied Research in Machine Learning: Medical Abstracts and Digital Games (PDF)

Speaker

Stan Matwin, Professor

 

University of Ottawa

 

School of Information, Technology and Engineering

 

http://www.site.uottawa.ca/~stan/

   

Abstract

In this talk we will discuss two current applications of Machine Learning, being developed at the Text Analysis and Machine Learning (TAMALE) research group at the University of Ottawa. The first application (joint work with Dr. D. Inkpen), in cooperation with TrialStat, targets screening of medical abstracts for a Systematic Review System. Systematic reviews are the basic tool of Evidence-based-medicine. We will describe the task, and outline the requirements and challenges a Machine Learning solution must meet. The second application is in the area of Digital games Based Learning. In a joint effort with Distil Interactive, we are using Machine Learning in acquiring profiles of different classes of people using digital games for skill certification. Here as well we will outline some of the requirements and challenges the task presents from the perspective of Machine Learning. Interestingly, some of the challenges are shared by both tasks and are among the challenges before the entire field.

 

Speaker Bio

Stan Matwin is a professor at the School of Information Technology and Engineering, University of Ottawa, where he directs the Text Analysis and Machine Learning (TAMALE) lab. His research is in machine learning, data mining, and their applications, as well as in technological aspects of Electronic Commerce. Author and co-author of 150 research papers, he has worked at universities in Canada, the U.S., Europe and Latin America, where in 1997 he held the UNESCO Distinguished Chair in Science and Sustainable Development. Former president of the Canadian Society for the Computational Studies of Intelligence (CSCSI) and of the IFIP Working Group 12.2 (Machine Learning). Founding Director of the Graduate Certificate in Electronic Commerce at University of Ottawa. Founding Director of the Information Technology Cluster of the Ontario Research Centre for Electronic Commerce. Chair of the NSERC Grant Selection Committee for Computer Science and member of the Board of Directors of Communications and Information Technology Ontario (CITO). Recipient of a CITO Champion of Innovation Award. Programme Committee Chair and Area Chair for a number of international conferences in AI and Machine Learning. Member of the Editorial Boards of the Machine Learning Journal, Computational Intelligence Journal, and the Intelligent Data Analysis Journal.

 


Date

Monday February 07, 2007

Time

17:30-19:00

Location

Room 5084, SITE Building, University of Ottawa

Title

Information Technologies Applied to Medicine

Speaker

Monique Frize, Professor

 

Carleton University

 

Department of Systems and Computer Engineering

 

http://www.sce.carleton.ca/faculty/frize.html

 

University of Ottawa

 

School of Information, Technology and Engineering

 

http://www.site.uottawa.ca/~frize/

   

Abstract

The talk will present current research and development in biomedical engineering. Using machine learning and data mining techniques such as artificial neural networks and case-based reasoning, we design and attempt to improve the performance of these tools to predict premature births (before the 23rd week of gestation); we also predict complications for infants in intensive care; we are developing an automated technique to assess pain levels in babies and adults using an infra-red camera and imaging techniques.

 

Speaker Bio

Dr. Frize joins Carleton University, as a Professor in the Department of Systems and Computer Engineering, and the University of Ottawa, as a Professor in the School of Information Technology and Engineering, in July 1997.
Dr. Frize graduated with a Bachelor of Applied Science (Electrical Engineering), received an Athlone Fellowship and completed a Master's in Philosophy in Electrical Engineering (Engineering in Medicine) at Imperial College of Science and Technology in London (UK), a Master's of Business Administration at the Université de Moncton (New Brunswick), and a doctorate from Erasmus Universiteit in Rotterdam, The Netherlands.
Monique Frize worked as a clinical engineer for 18 years, initially at Hopital Notre-Dame in Montreal (1971-79), and then was appointed as Director of the Regional Clinical Engineering Service in Moncton, New Brunswick, providing services for seven hospitals in the South-Eastern region. Dr. Frize was also Research Associate in the Faculty of Science and Engineering at UniversitJ de Moncton and was the first Chair of the Division of Clinical Engineering for the International Federation of Medical and Biological Engineering (IFMBE). In December, l989, she was appointed the first holder of the Nortel-NSERC Women in Engineering Chair at the University of New Brunswick (Fredericton) and Professor in the Electrical Engineering department.
In 1992, Monique Frize received an Honorary Doctorate from the University of Ottawa (DU); in June 1993, a Ryerson Fellowship; in 1994, an Honourary Doctorate in Science (DSc) at York University; in 1995, an Honourary Doctorate in Engineering at Lakehead (DEng). She was inducted as a Fellow of the Canadian Academy of Engineering in 1992 and as Officer of the Order of Canada in October 1993. In 1995, Dr. Frize received the Second Historical Professional Achievement Award (jointly with Dr. Michael Shaffer) from the American College of Clinical Engineers, for her paper: "Clinical Engineering in today's hospital: Perspectives of the Administrator and the Clinical Engineer". In September 1996, Dr. Frize received the 6th Annual Meritas-Tabaret Award for career achievement from the Alumni Association of the University of Ottawa and the Advocacy Award presented by WITT (Women in Trades and Technology) in May 1997. Born in Montreal, Canada, Dr. Frize's mother tongue is French, and she is fluently bilingual. She is married to Peter Frize and they have a son, Patrick Nicholas.

 


Date

Monday December 04, 2006

Time

10:30-12:00

Location

Building M-50, NRC Auditorium, 1200 Montreal Road

Title

Lying, Deception and Face Familiarity with Visual Evoked Potentials

Speaker

Evangelia Micheli-Tzanakou, Professor

 

Rutgers University

 

Department of Biomedical Engineering

 

Director of Computational Intelligence Laboratories

 

http://cil.rutgers.edu/tzanakou/

   

Abstract

The recent urgency for counter-terrorism and the fight to protect ones’ homeland are of grave concern to nations throughout the world.  Finding an efficient process that could have screened passengers prior to boarding a flight or even a train may have derailed many devastating events.  Scientific research has continuously proved that there is an explicit marker of neuronal activity that correlates with awareness, past experience, and short-term interactions from the well-known P300 peak of an evoked potential.  This study examines the effects of memory recognition to certain key stimuli mixed with irrelevant variables in an effort to identify if a trained terrorist, per se, could not only be identified from a group of subjects, but also validate that the willingness to withhold information is out of the control of the individual; it is simple, one has no control in concealing their brain’s activity. Face familiarity is also examined through a series of experiments.

 

Speaker Bio

Dr. Tzanakou is Professor, Director of Computational Intelligence Laboratories (2000-present); Chair Biomedical Eng., Rutgers University (1990-00). Has published 250+ scientific papers.  Authored/co-authored 4 books/edited proceedings, graduated 37 M.S. and Ph.D.'s; Founding Fellow, American Institute for Medical & Biological Eng., 1993; Member of Sigma Xi and Eta Kappa Nu; Honorary Member: British Brain Research Association; European Brain/Behavior Society.  Awards:  NJ Women of Achievement, 1995; Featured "Notable Twentieth Century Scientists," 1994; Achievement Award, Society of Women Engineers, 1992; Outstanding IEEE Branch Advisor/Counselor, 1985; Pioneer (IEEE Web page).  Book Series Editor: Biomedical Engineering, Plenum/Klewer (1999-present); Biomedical Systems, IES Book series, CRC Press (1997-present); Editorial Board: IEEE Transactions on Nano-BioScience (2002-present); Biomedical Engineering On Line, (2001-present), IEEE Transactions on Biomedical Information Technology (1997-01); Intern. J. Adv. Computational Intelligence (1997-99); Advanced Computational Intelligence and Intelligent Informatics, (2000-present); International J. on Artificial Intelligence Tools, (2004-present). Associate Editor, IEEE Transactions on Neural Networks (2000-present), (1989-92).

 


Date

Friday November 17, 2006

Time

17:30-19:00

Location

Room 5084, SITE Building, University of Ottawa

Title

Information Retrieval from Automatic Speech Transcripts (PDF)

Speaker

Diana Inkpen, Assistant Professor

 

University of Ottawa

 

School of Information Technology and Engineering

 

http://www.site.uottawa.ca/~diana/

   

Abstract

Browsing through large volumes of spoken audio is known to be a challenging task for end users. To alleviate this problem we can allow users to gist a spoken audio document by glancing over a transcript generated through Automatic Speech Recognition, or to implement information retrieval systems over the text transcribed by the speech recognizer.
Unfortunately, such transcripts typically contain many recognition errors which are highly distracting and make gisting more difficult. I present an approach that detects recognition errors by identifying words which are semantic outliers with respect to other words in the transcript. I investigate a wide range of evaluation measures and show that we can significantly reduce the number of errors in content words, with the trade-off of losing some good content words.
Also described are information retrieval experiments from a collection of spontaneous speech. I show comparative results for indexing the automatic transcripts as opposed to indexing the manual summaries and keywords available in the collection.

 

Speaker Bio

Dr. Diana Inkpen is a professor at the School of Information Technology and Engineering, University of Ottawa since July 2003. She obtained her doctorate in 2003 from University of Toronto, Department of Computer Science.  She has a Masters in Computer Science and Engineering from the Technical University of Cluj-Napoca, Romania. Her research projects and publications are in the areas of Computational Linguistics and Artificial Intelligence, more specifically: Information Retrieval, Information Extraction, Natural Language Understanding, Natural Language Generation, Speech Processing, and Intelligent Agents for the Semantic Web.
Dr. Inkpen is involved in many collaborative research projects, with University of Toronto, University of Waterloo, IBM Centre for Advanced Studies, and the National Research Council (the Institute for Information Technology and the Canada Institute for Scientific and Technical Information). The team led by Dr. Diana Inkpen and composed of two of her graduate students won the international competition in Information Retrieval CLEF 2005 (Cross-Language Evaluation Forum), the CL-SR task (Cross-Language Spoken Retrieval).

 


Date

Friday September 15, 2006

Time

10:30-12:00

Location

Room 379, Building M-50, NRC Auditorium, 1200 Montreal Road

Title

Graph Mining and its Applications

Speaker

Jian Pei, Assistant Professor

 

Simon Fraser University

 

Computing Science Department

 

http://www.cs.sfu.ca/~jpei/

 

http://iit-iti.nrc-cnrc.gc.ca/colloq/0607/06-09-15_e.html

   

Abstract

Graph models are popularly used in many applications, such as marketing analysis, protein interactions, social networks, and web analysis. Mining significant and interesting graph patterns from collections of graphs as well as other types of data has become an important research problem. In this talk, I shall discuss the problem of mining graph databases and graph patterns in three aspects: how to model patterns in graphs, how to mine large graphs and how to handle many graphs. Particularly, I shall present several interesting approaches recently developed by us. The quasi-clique mining method finds dense areas across multiple large graphs. The ADI approach indexes databases with a large number of (relatively small) graphs and mines frequent sub-graphs. The frequent closed partial order mining approach derives DAG models from large sequence databases. I shall also address the potential extensions of the above methods.

 

Speaker Bio

Jian Pei received a Ph.D. degree in Computing Science from Simon Fraser University, in 2002. He is currently an Assistant Professor of Computing Science at Simon Fraser University. His research interests can be summarized as developing effective and efficient data analysis techniques for novel data intensive applications. Particularly, he is currently interested in various techniques of data mining, data warehousing, online analytical processing, and database systems, as well as their applications in bioinformatics, privacy preservation, and education. His current research is supported in part by the Natural Sciences and Engineering Research Council of Canada (NSERC), the National Science Foundation (NSF) of the United States, Hewlett-Packard Company (HP), and the Canadian Imperial Bank of Commerce (CIBC). He has published prolifically in refereed journals, conferences, and workshops, has served extensively in the organization committees and the program committees of many international conferences and workshops, and has been a reviewer for the leading academic journals in his fields. He is a member of the ACM, the ACM SIGMOD, and the ACM SIGKDD.

 


Date

Thursday February 09, 2006

Time

15:00-16:30

Location

NRC Institute for Biological Sciences, 1200 Montreal Road Building M-54, Room 235

Title

A Unified Model of Spike-Time-Dependent Plasticity and Chemotropic Gradients in Retinotopic Map Formation

Speaker

Jean-Philippe Thivierge , Psychology Ph.D. candidate

 

McGill University

 

Laboratory for Natural and Simulated Cognition

 

http://www.psych.mcgill.ca/labs/lnsc/html/Lab-Home.html

   

Abstract

Both activity-dependent and independent processes play a role in the development of the vertebrate visual system. Molecular guidance cues provide a rough topography of early projections, while refinement of termination zones (TZs) occurs later on through correlated retinal activity. Experiments involving B2 subunit knock-out mice have found a cumulative role of removing activity-dependent and independent processes, thus arguing for their distinct roles. A computational account of these results is proposed, based on a unified model that combines chemotropic gradients and spike-time-dependent synaptic plasticity. The model is employed to simulate recent empirical data, and proposes possible interactions between activity-dependent and independent processes.

 

Speaker Bio

Jean-Philippe Thivierge is a post-doctoral fellow at the Université de Montréal, where his research interests include the application of computational intelligence tools to cognitive modelling, structures and algorithms in neural networks, bioinformatics, and developmental computational neurobiology.  He already has a wide range of publications in these areas, including some very interesting computational models for the development of the visual system.  JP has been very active as a young leader in his area of research, in business ventures, and with his professional associations.  He was Local Arrangements Chair for the 2005 International Joint Conference on Neural Networks, for which he also chaired a session of international leaders to celebrate developments arising from Donald Hebb's work in Montreal 50 years ago.  He also has been a guest editor for the "IEEE International Journal of Neural Networks", "Journal of Machine Learning", and he has been collaborating with the NRC.

 


Date

Thursday December 01, 2005

Time

15:00-16:30

Location

NRC Auditorium, 1200 Montreal Road Building M-50

Title

Computer Vision for Augmented Reality - the ARTag system

Speaker

Mark Fiala, Research Officer

 

NRC-CNRC Institute for Information Technology

 

Computational Video Group

 

http://iit-iti.nrc-cnrc.gc.ca/personnel/fiala_mark_e.html

   

Abstract

Augmented Reality (AR) is the convergence of the real world and virtual computer generated imagery, it is the fusion of real and virtual reality through overlaying virtual objects over real images or video. A virtual object can be made to look like it belongs in a real scene if it is rendered from the right viewpoint, something done routinely in movie making but still a research topic for real time systems where you can look at and walk around virtual objects using a head-mounted display, PDA, cellphone, or tablet PC. To do this, the graphics rendering system must know the pose of the camera, this pose determination can be done accurately and inexpensively using computer vision. One way is to use markers like the ARTag marker system that will be described in the talk. Designing markers to add to the environment for robust detection in camera and video imagery is a computer vision application useful to
situations where a camera-object pose is desired such as AR, industrial position tracking, photo-modeling and robot navigation. Examples of augmented reality and the ARTag system developed at the NRC will be shown.

 

Speaker Bio

Dr. Mark Fiala is a computer vision researcher at Canada's National Research Council (NRC), where he works in the Computational Video Group centered in Ottawa, Ontario. His work includes fiducial marker systems, panoramic vision, and general computer vision topics such as image segmentation and camera calibration. He graduated from his PhD in Electrical Engineering in 2002 in the field of panoramic computer vision. He also holds an Electrical Engineering BSc and has spent over 5 years in industry in hardware design for imaging and telecom applications. His best known recent work is the "ARTag" fiducial marker system.

 


Date

Thursday September 29, 2005

Time

17:00-18:30

Location

Room 5084 of SITE Building at the University of Ottawa

Title

Let your muscles do the talking: myoelectrically controlled prostheses to myoelectric speech recognition (PDF)

Speaker

Adrian Chan, Assistant Professor

 

Department of Systems and Computer Engineering

 

Carleton University

 

http://www.sce.carleton.ca/faculty/chan.html

   

Abstract

For decades there has been extensive research and development on myoelectrically controlled powered prostheses. The basic premise of the device is that myoelectric signals from residual muscles could be used as a control signal for upper arm prostheses. The advantages of such a prosthesis are: 1) it frees the user from straps and harnesses required of body powered and mechanical switch control; 2) the myoelectric signal can be noninvasively detected on the surface of the skin; 3) proportional control can be implemented with relative ease and the amplitude of the myoelectric signal varies in sympathy with the contractile force; and 4) the muscle activity required to provide a control signal is relatively small and can resemble the effort of an intact limb. In recent, years pattern recognition techniques have been explored to provide users an interface that is more natural and intuitive, while providing a higher degree of classification accuracy and controllability. Work has been extended from this application towards myoelectric speech recognition; using myoelectric signals from facial muscles to perform speech recognition. Such a device would be useful for persons with temporary or permanent speech impairments.

 

Speaker Bio

Dr. Adrian D.C. Chan graduated with his B.A.Sc. in Computer Engineering, University of Waterloo (1997), M.A.Sc. in Electrical Engineering, University of Toronto (1999), and Ph.D. in Electrical Engineering, University of New Brunswick (2002). Currently, he is an Assistant Professor in the Department of Systems and Computer Engineering, Carleton University. His research is in biomedical engineering, focusing on biological signal processing and noninvasive sensors. Dr. Chan has been recognized as one of Macleans 25 Best and Brightest (2004) and Ottawa Life Magazine's Top 50 People in the Capital (2005), and received the Ottawa Life Sciences Council Dr. Michael Smith Promising Scientist Award (2004).

 


Date

Thursday April 21, 2005

Time

17:00-18:30

Location

Room 5084 of SITE Building at the University of Ottawa

Title

A Robust Hybrid Intelligent Position/Force Control Scheme for Cooperative Manipulators (PDF)

Speaker

Wail Gueaieb, Assistant Professor

 

School of Information Technology and Engineering

 

University of Ottawa

 

http://mcr1.site.uottawa.ca/~wgueaieb/site/

   

Abstract

A decentralized adaptive fuzzy controller is proposed for addressing the problem of controlling the positions and internal forces within multiple coordinated manipulator systems in the face of parametric and modeling uncertainties as well as external disturbances. The controller makes use of a multi-input multi-output fuzzy logic engine and a systematic online adaptation mechanism to fully approximate the overall system's dynamics. Unlike conventional adaptive controllers, the proposed controller does not require a perfect prior model of the system's dynamics nor does it require a linear parameterization of the system's uncertain physical parameters. Using a Lyapunov stability approach, the controller is proven to be robust in the face of varying intensity levels of the aforementioned uncertainties, and the position and the internal forces are proven to asymptotically converge to zero under such conditions. Through a computer simulation of two 3-DOF manipulators, the performance of the controller is verified and compared to that of one of the most efficient conventional adaptive controllers proposed in the literature.

 

Speaker Bio

Dr. Wail Gueaieb received the Bachelor and Master’s degrees in Computer Engineering and Information Science from Bilkent University, Turkey, in 1995 and 1997, respectively, and the Ph.D. in Intelligent Mechatronics from the University of Waterloo, Canada, in 2001. He then joined Intelligent Mechatronic Systems Inc. in 2001 where he held the positions of a senior systems design engineer in expert systems and a software manager. During his career at Intelligent Mechatronic Systems Inc., he worked on the design, implementation, and productization of a new generation of smart advanced automotive safety systems. He is also the author/co-author of three patents. In July 2004, he joined the School of Information Technology and Information Science (SITE). His areas of expertise span the fields of intelligent systems design using tools of computational intelligence with application to a wide range of industries.

 


Date

Wednesday February 23, 2005

Time

18:00-19:30

Location

Room 5084 of SITE Building at the University of Ottawa

Title

How to Learn from a Stochastic Teacher or a Stochastic Compulsive Liar of Unknown Identity (PDF)

Speaker

B. John Oommen, FIEEE, Professor

 

School of Computer Science

 

Carleton University

 

http://www.scs.carleton.ca/~oommen

   

Abstract

All of the research that has been done in learning, has involved learning from a Teacher who is either deterministic or stochastic. In this talk, we shall present the first known results of how a learning mechanism can learn while interacting with either a stochastic teacher or a stochastic compulsive liar. In the first instance, the teacher intends to teach the learning mechanism. In the second, the compulsive liar intends to consciously mislead the learning mechanism. We shall present a formal strategy for the mechanism to perform ε-optimal learning without it knowing whether it is interacting with a teacher or a compulsive liar. Believe It Or Not - IT WORKS !

A joint work with Dr. Govindachari (presently in Bangalore) and Dr. Kuipers (Texas).

 

Speaker Bio

Dr. John Oommen was born in Coonoor, India on September 9, 1953. He obtained his B.Tech. degree from the Indian Institute of Technology, Madras, India in 1975. He obtained his M.E. from the Indian Institute of Science in Bangalore, India in 1977. He then went on for his M.S. and Ph. D. which he obtained from Purdue University, in West Lafayettte, Indiana in 1979 and 1982 respectively. He joined the School of Computer Science at Carleton University in Ottawa, Canada, in the 1981-82 academic year. He is still at Carleton and holds the rank of a Full Professor. His research interests include Automata Learning, Adaptive Data Structures, Statistical and Syntactic Pattern Recognition, Stochastic Algorithms and Partitioning Algorithms. He is the author of more than 215 refereed journal and conference publications and is a Fellow of the IEEE. Dr. Oommen is on the Editorial Board of the IEEE Transactions on Systems, Man and Cybernetics, and Pattern Recognition.

 


Date

Wednesday December 15, 2004

Time

16:00-17:30

Location

Room 5084 of SITE Building at the University of Ottawa

Title

Face recognition in video as a new biometrics modality and the appropriate associative memory framework (PDF)

Speaker

Dmitry O. Gorodnichy, Research Officer

 

NRC-CNRC Institute for Information Technology

 

Computational Video Group

 

http://iit-iti.nrc-cnrc.gc.ca

 

http://synapse.vit.iit.nrc.ca/memory (project homepage)

 

The talk will be followed by the annual meeting of the chapter

Abstract

The purpose of this talk is two-fold. First, the audience will be introduced with the basics of the attractor-based associative neural networks. These networks are known as a mathematical tool for building recognition systems which work in a fashion similar to that of the human brain. Second, the audience will be presented with a new framework for recognizing faces in video. While the problem of recognizing faces in video has received a lot of attention recently, in particular, because of such a highly demanded application of it as security surveillance, this problem is often erroneously treated as an extension of the problem of recognizing faces in photographs. Photographs, which are usually taken under very constrained conditions, provide hard biometrics data, as do, for instance, the fingerprints. Video footage, on the other hand, such as the one taken by a surveillance camera, will very unlikely contain the facial data of high quality and is therefore the source of "softer" biometrics. As we will show, however, the soft biometrics provided by video is still very informative and can be efficiently used to memorize and recognize faces. In the demonstrations to be shown, the developed mini brain model allows one to discriminate guests of a talk show in a prerecorded low-resolution video.

 

Speaker Bio

Dr. Dmitry Gorodnichy is a research officer with the Computational Video Group of the Institute for Information Technology of the National Research Council of Canada. He has two Ph.D. degrees: one - in Computing Science (2000) from the University of Alberta, Edmonton, Canada, for his work on Vision-based World Model Learning, and the other (1997) - in Mathematics from the Glushkov Cybernetics Center of Ukrainian Ac.Sc., Kiev, Ukraine, for his work on Mathematical models of human memory. His MSc (with honours) in Information Technology (1994) is from the Moscow Institute of Physics and Technology, Moscow, Russia. He is the author of two patents and over thirty conference and journal papers, including an IJCNN Best Presentation Award paper, a recipient of several scientific awards, including the Young Investigator Award from the Canadian Image Processing and Pattern Recognition Society and the NRC-CNRC Outstanding Scientific Achievement Award. He is the principle investigator of Nouse™ (Nose as Mouse) and Blink Detection perceptual vision technologies featured in the 2002 and 2003 NRC-CNRC Annual Reports, and is listed as one of 2003 Leaders of Tomorrow by the Partnership Group for Science and Engineering of Canada. He was the Program Chair for the International Conference on Vision Interface, the organizer and the program chair of the First IEEE Workshop on Face Processing in Video and is now the Exhibits Chair for the INNS-IEEE International Joint Conference on Neural Networks to be held in Montreal next year. He is a reviewer for many scientific conferences, journals and organizations, including NSERC, and is also presently the Chair for IEEE Computational Intelligence Society, Ottawa Chapter.

 


Date

Thursday November 25, 2004

Time

16:00-17:00

Location

Room 5084 of SITE Building at the University of Ottawa

Title

The heterogeneous neuron model and its use in hybrid neural networks within computational intelligence compound systems

Speaker

Julio J. Valdés, Senior Research Officer

 

NRC-CNRC Institute for Information Technology

 

Integrated Reasoning Group

 

http://iit-iti.nrc-cnrc.gc.ca

   

Abstract

A framework is presented for processing heterogeneous information based on the construction of general observational domains, and similarity-based function calculi suitable for data mining and other tasks in domains which can be described by the corresponding observational models. These calculi are intuitive, simple, and sufficiently general for classification and pattern recognition tasks. Functions in these calculi are represented by a particular kind of neuron models and their behavior is illustrated with examples from real-world domains showing their capabilities in processing heterogeneous, incomplete and fuzzy information, possibly with time dependencies.

 

Speaker Bio

Dr. Julio Valdés has a PhD in mathematics (1987). His areas of interest are: artificial intelligence (mathematical foundations of uncertainty processing and inexact reasoning, knowledge engineering, expert systems and machine learning), digital image and signal processing, pattern recognition, virtual reality, soft computing (fuzzy logic, neural networks, evolutionary algorithms, probabilistic reasoning, rough sets), data mining, data analysis in general and hybrid systems. He also graduated in geophysics (1977), oriented to geomathematics, mathematical modeling of natural processes, computer elaboration and data analysis-mining of earth science and environmental data, remote sensing, physics and chemistry of external geodynamic processes and geophysical-geochemical prospecting.

 


Date

Wednesday May 05, 2004

Time

17:00-18:30

Location

Room 5084 of SITE Building at the University of Ottawa

Title

Neural Network Modeling of 3D Objects for Virtualized Reality Applications

Speaker

Ana-Maria Cretu, Ph.D. Candidate

 

Sensing and Modeling Research Laboratory (SMRLab)

 

School of Information Technology and Engineering

 

University of Ottawa

 

acretu@site.uottawa.ca

   

Abstract

This talk presents a critical comparison between three neural architectures for 3D object representation in terms of purpose, computational cost, complexity, conformance and convenience, ease of manipulation and potential uses in the context of virtualized reality. Starting from a pointcloud that embeds the shape of the object to be modeled, a volumetric representation is obtained using a multilayered feedforward neural network or a surface representation using either the self-organizing map or the neural gas network. The representation provided by the neural networks is simple, compact and accurate. The models can be easily transformed in size, position (affine transformations) and shape (deformation). Some potential uses of the presented architectures in the context of virtualized reality are for the modeling of set operations and object morphing, for the detection of objects collision and for object recognition, object motion estimation and segmentation.

 

Speaker Bio

Ana-Maria Cretu obtained her Master degree from the School of Information Technology and Engineering at the University of Ottawa, Canada, where she is now a PhD student. Ms. Cretu's research interests include neural networks, 3D object modeling, tactile sensing and multi-sensor data fusion. She is a Student Member of IEEE.

 


Date

Wednesday February 25, 2004

Time

16:00-17:00

Location

Room 5084 of SITE Building at the University of Ottawa

Title

Corpus-based Learning of Analogies and Semantic Relations (PDF)

Speaker

Peter Turney, Senior Research Officer

 

Information Analysis and Retrieval Group

 

NRC Institute for Information Technology

 

http://iit-iti.nrc-cnrc.gc.ca

   

Abstract

This talk will present an algorithm for learning from unlabeled text, based on the Vector Space Model (VSM) of information retrieval, that can solve verbal analogy questions of the kind found in the Scholastic Aptitude Test (SAT). A verbal analogy has the form A:B::C:D, meaning "A is to B as C is to D"; for example, mason:stone::carpenter:wood. SAT analogy questions provide a word pair, A:B, and the problem is to select the most analogous word pair, C:D, from a set of five choices. The VSM algorithm correctly answers 47% of a collection of 374 college-level analogy questions (random guessing would yield 20% correct). This research is motivated by relating it to work in cognitive science and linguistics, and by applying it to a difficult problem in natural language processing, determining semantic relations in noun-modifier pairs. The problem is to classify a noun-modifier pair, such as "laser printer", according to the semantic relation between the noun (printer) and the modifier (laser). The approach is to use a supervised nearest-neighbour algorithm that assigns a class to a given noun-modifier pair by finding the most analogous noun-modifier pair in the training data. With 30 classes of semantic relations, on a collection of 600 labeled noun-modifier pairs, the learning algorithm attains an F value of 26.5% (random guessing: 3.3%). With 5 classes of semantic relations, the F value is 43.2% (random: 20%). The performance is state-of-the-art for these challenging problems.

 

Speaker Bio

Dr. Peter Turney is a Senior Research Officer in the Interactive Information Group of the National Research Council. In 1988, he obtained his PhD from the University of Toronto, where he then accepted a Postdoctoral Fellowship. He joined the NRC in 1989, and he has since worked on a variety of projects, all involving applications of machine learning technology. His recent work focuses on machine learning applied to natural language. He is the author or co-author of more than sixty publications, a past editor of Canadian Artificial Intelligence magazine, and a member of the Advisory Board of the Journal of Artificial Intelligence Research.

 


Date

Wednesday December 03, 2003

Time

16:00-17:30

Location

Room 5084 of SITE Building at the University of Ottawa

Title

Hardware Neural Network Architectures Using Random Data Representation

Speaker

Emil M. Petriu, Dr. Eng., P.Eng., Professor

 

Sensing and Modeling Research Laboratory (SMRLab)

 

School of Information Technology and Engineering

 

University of Ottawa

 

http://www.site.uottawa.ca/~petriu

 

petriu@site.uottawa.ca

Abstract

The idea of using computational techniques that mimic the processing behaviour of the biological nervous systems was advanced by von Neuman in 1965. The resulting random-pulse machine concept deals with analog variables represented by the mean rate of random-pulse streams using simple digital circuits to perform arithmetic and logic operations. This concept presents a good trade-off between the electronic circuit complexity and the computational accuracy.

The talk presents the random-pulse data representation and discusses how it can be used to the design of modular random-pulse neural networks. A generalization of the random-pulse machine concept, namely the multi-bit random-data machine, is then discussed. The advantage of using multi-bit data instead of pulses (which are 1-bit data) is a considerable reduction in the time needed to get an acceptable accuracy for the statistical averages of the data streams carrying the information. As in the case of the random-pulse machine, the arithmetic operations are performed by relatively simple logic circuits. The resulting architectures have high functional packing density making them suitable for the VLSI implementation of hardware parallel neural networks.

 

Speaker Bio

Emil M. Petriu is a professor in the School of Information Technology and Engineering at the University of Ottawa, Canada, where he has been since 1985. Dr. Petriu's research interests include intelligent sensors, robot sensing and perception, neural networks, and fuzzy control. During his career he has published more than 180 technical papers, authored two books, edited other two books, and received two patents. He is a Fellow of IEEE, Fellow of the Canadian Academy of Engineering, and Fellow of the Engineering Institute of Canada. For more info, see www.smrlab.uottawa.ca

 


Date

Friday April 25, 2003

Time

16:00-17:00

Location

Room 5084 of SITE Building at the University of Ottawa

Title

Collaborative Virtual Environments

Speaker

Nicolas D. Georganas, FIEEE, Professor

 

Distributed and Collaborative Virtual Environments Research Laboratory (DISCOVER)

 

School of Information Technology and Engineering

 

University of Ottawa

 

http://www.site.uottawa.ca/~georgana

Abstract

One of the hottest topics in Virtual Reality research is that of "Distributed" Virtual Environments (DVE). The idea behind DVE is very simple; a simulated world runs not on one computer system, but on several, using a series of client server applications. The computers are connected over a network and people using those computers are able to interact in real time, sharing the same virtual world.

Collaborative Virtual Environments (CVE) add new dimensions to human-factors, networking, and database issues. For example, human-factors research in VR has traditionally focused on the development of natural interfaces for manipulating virtual objects and traversing virtual landscapes. Collaborative manipulation, on the other hand, requires the consideration of how participants should interact with each other in a shared space, in addition to how co-manipulated objects should behave. Other issues include: how participants should be represented in the collaborative environment; how to effectively transmit non-verbal cues that real-world collaborators so casually and effectively use; how to best transmit video and audio via a channel that allows both public addressing as well as private conversations to occur; how to filter relevant information to reduce processing (increase performance) at each client for large worlds; and how to sustain a virtual environment even when all its participants have left.

This talk will expose basic notions in CVE and describe several applications.

 

Speaker Bio

Nicolas D. Georganas, is Distinguished University Professor and Canada Research Chair in Information Technology, School of Information Technology and Engineering, University of Ottawa, Canada. He is a Fellow of IEEE, Fellow of the Canadian Academy of Engineering, Fellow of the Engineering Institute of Canada, and Fellow of the Royal Society of Canada. In 2002, he received the Killam Prize for Engineering, Canada's highest award for career achievements in research. His research interests are in Multimedia Communications, Pervasive Computing, Intelligent Sensors, Tele-Haptics and Collaborative Virtual Environments. For more info, see www.discover.uottawa.ca

 

 

If you would like to contact the IEEE Webmaster, email to webmaster@ieee.org
© Copyright 2005, IEEE.   Terms & Conditions.  Privacy & Opting Out of Cookies.
Small IEEE Logo
(Rafael Falcon, rfalcon@ieee.org)
http://ottawa.ieee.ca/ci/ index.html
(Modified:November 20, 2013)