Conference
Short Descriptions
Tuesday 25
| 9:30 - 11 |
COMPUTATIONAL INTELLIGENCE IN A BIOINFORMATIC PROBLEM: THE SEARCH OF COMMON ORIGIN IN PROTEIN FAMILIESJose AguilarCentro de Estudios en Microelectronica y Sistemas Distribuidos (CEMISID) Departamento de Computación, Facultad de Ingeniería Universidad de Los Andes, Mérida. (Venezuela) [Abstract] 
[Article] [Slides]
|
| 11:00 - 11:30 |
Chaotic Associative Memory Using Sine MapJuan C. Gutierrez Caceres & Edward Cayllahua Cahuina>San Pablo Catholic University, Arequipa. (Peru) Abstract
[Article] [Slides]
|
| 13:00 - 14:30 |
New Trends in Artificial Neural Networks for Evolving Intelligent Systems and Knowledge EngineeringProf. Nikola Kasabov, FIEEE, FRSNZKnowledge Engineering and Discovery Research Institute, KEDRI Auckland University of Technology, Auckland. (New Zealand) Abstract  [Slides]
|
| 14:30 - 15:00 |
Neural Network Data Fusion and Uncertainty Analysis for Wind Speed Measurement using Ultrasonic TransducerPh.D Juan MauricioAbstract
[Article] [Slides]
|
| 15:00 - 16:30 |
A Computational Introduction to the Brain-MindJuyang Weng, IEEE FellowAbstract
[Article] [Slides]
|
| 16:30 - 17:00 |
The Neurodynamics of Brain and Behavior: An introduction to Computational Cognitive NeuroscienceDr. Sebastien HelieUCSB, Santa Barbara, CA. (USA) Abstract [Slides]
|
Wednesday 26
| 9:30 - 11:00 |
Computational Intelligence Research in Automotive IndustryDanil ProkhorovToyota Research Institute North America Ann Arbor, MI Abstract [Slides]
|
| 11:00 - 11:30 |
Artificial Vision for Exportable Mangoes Recognition Using Neural NetworksHugo Froilan Vega Huerta(UNMSM) and Ana Huayna Duenas(UNMSM )Abstract
[Article] [Slides]
|
| 13:00 - 14:30 |
Theoretical and Practical Considerations of Networked Dynamic Models for Detection and Isolation of Anomalies in Systems of Interacting Dynamic SystemsDragan DjurdjanovicUniversity of Texas Austin, TX. (USA) Abstract
[Slides]
|
| 14:30 - 15:00 | Artificial Neural Network Design to Compensate for the Doppler Effect on the Radio Frequency Communications During the Tracking of Pico Satellites in Low Earth OrbitAbstract
[Article] [Slides]
|
| 15:00 - 17:00 |
Neurocontrol of helicopters (presentations and demo)Fernando Jimenez Motte and his teamUPC, Lima. (Peru) Abstract
[Article] [Slides]
|
Thursday 27
| 9:30 - 11:00 |
Information Theoretic LearningJose C. PrincipeDistinguished Professor of Electrical Engineering University of Florida (USA) Abstract [Slides]
|
| 11:00 - 11:30 |
Robotic Controller Obtained Through a Speciation-based MetaheuristicFranco Ronchetti and Laura Lanzarini Abstract
[Article] [Slides]
|
| 13:00 - 13:30 |
Virtual Simulation of a Myoelectric ProsthesisWilmer J. Lobato Malaver and Msc. Sergio Salas ArriaranAbstract
[Article] [Slides!]
|
| 13:30 - 14:00 |
Solution to the Tic-Tac-Toe Problem using Hamming Distance approach in a Neural NetworkNazneen Rajani, Rajoshi Biswas, Dr. Gaurav Dar, and Dr. Ramesha C.K.Abstract
[Article] [Slides!]
|
| 14:00 - 14:30 | Artificial Brain based on Top-Down Selective Attention for Noise-Robust Recognition and Multimodal IntegrationSoo-Young Lee Abstract
[Article] [Slides!]
|
| 14:30 - 15:00 | NEURO COPTER” LINEAR QUADRATIC GAUSSIAN DESIGN LQG AND IMPLEMENTATION OF THE CONTROL SYSTEM OF AN UNMANNED AERIAL VEHICLE UAV WITH STATE SPACE MODELLING AND KALMAN FILTERING AND AUTONOUMOUS GUIDANCE WITH COMPUTER VISION AND DATA LINK COMMUNICATIONSFernando Jimenez, Jose Oliden, Juan Huapaya, Germain CardenasAbstract
[Article] [Slides]
|
Detailed Information
January 25, 2011
9:00 --- 9:30
Welcome to the Symposium. Opening remarks from the General and PC Chairs and Local Organizers
9:30 -- 11:00
COMPUTATIONAL INTELLIGENCE IN A BIOINFORMATIC
PROBLEM: THE SEARCH OF COMMON ORIGIN IN PROTEIN FAMILIES
Jose Aguilar
Centro de Estudios en Microelectronica y Sistemas Distribuidos (CEMISID),
Departamento de Computación, Facultad de Ingeniería,
Universidad de Los Andes, Mérida, Venezuela
Abstract:
Research in biomedical science is generating a huge biological information volume more
complex every time, that's why they have begun to require computation techniques for its
processing. Particularly, excessive increase of the databases on proteins, both in the number and
in the size of the same, coming from biological experiments, have caused that infinite
information quantity exceeds what can be processed and understood by human beings. The
databases contain an enormous useful information quantity difficult to discover. Some computer
tools has been developed as response to the needs to obtain new knowledge on the proteins
sequences, using information stored in these databases. But there are still problems to solve to
level at discovery problems, data classification, among others.
As contribution to this area, in this speech we will present the utilization of different
intelligent techniques in a bioinformatic problem: the search for similarities between nonhomologous
protein families, with the goal of discover and identify specific regions conserved in
the protein, in a way to determine what proteins have a common origin. Particularly, the proteins
are modeled like regular expressions using the PROSITE language. The similarities between
non-homologous protein families is carried out in two phase. At the beginning we develop a
comparison method of regular expressions, then we carry out the fusion among the similar
regular expressions.
We are interested in the motifs; a motif is a small region in a previously characterized protein,
with a functional or structural significance in the protein sequence. From the computer point of
view, the problem of the first phase consists of comparison of the motifs of the proteins
expressed using regular expressions. For this, we present a hybrid method of comparison of
motifs based on the Genetic Programming to generate the populations derived from every regular
expression under comparison, and on the Backpropagation Artificial Neural Network for the
comparison between them. For the second phase, we solve the problem of fusion of motifs
among two similar regulars expressions chosen in the first phase (that represent protein families),
using a combinatorial optimization algorithm based on Artificial Ant Colonies. Our approach is
applied to amyloid proteins and is tested using the database AMYPdb to discover possible
similarities between amyloidal families.
11:00 -- 11:30
Chaotic Associative Memory Using Sine Map
Juan C. Gutierrez Caceres & Edward Cayllahua Cahuina
Abstract:
In the last decades, neurobiological researches yield evidences of chaotic behavior in animal and human brains, both in microscopic (neuron) and macroscopic (global brain activity) levels. Such evidences motivate the exploration of chaotic systems in artificial neural networks. In this context, the objectives of the present work are to study the existing chaotic neural networks and to develop new chaotic neural networks for multi-value pattern recognition. The working mechanism is divided in two phases: storing and recognition. In the former phase, a set of patterns are stored in fixed points by the pseudo-inverse matrix learning algorithm . In the latter one, the periodic and chaotic dynamic existing in chaotic maps are employed with the periodic orbit representing a retrieved pattern and the chaotic orbit providing an efficient searching mechanism. One advantage of the proposed models over the existing chaotic neural networks lies in that the new models recognize not only binary, but also multi-value patterns, which is an important feature in practical applications.
11:30 -- 13:00 Lunch
13:00 -- 14:30
New Trends in Artificial Neural Networks for Evolving Intelligent Systems and Knowledge Engineering
Prof. Nikola Kasabov, FIEEE, FRSNZ
Knowledge Engineering and Discovery Research Institute, KEDRI
Auckland University of Technology, Auckland, New Zealand
nkasabov@aut.ac.nz, http://www.kedri.info
Abstract:
The talk presents theoretical foundations and practical applications of evolving intelligent information processing systems inspired by information principles in Nature in their interaction and integration. That includes neuronal-, genetic-, and quantum information principles, all manifesting the feature of evolvability. First, the talk reviews the main principles of information processing at neuronal-, genetic-, and quantum information levels. Each of these levels has already inspired the creation of efficient computational models that incrementally evolve their structure and functionality from incoming data and through interaction with the environment. The talk also extends these paradigms with novel methods and systems that integrate these principles. Examples of such models are: evolving spiking neural networks; computational neurogenetic models (where interaction between genes, either artificial or real, is part of the neuronal information processing); quantum inspired evolutionary algorithms; probabilistic spiking neural networks utilizing quantum computation as a probability theory. The new models are significantly faster in feature selection and learning and can be applied to solving efficiently complex biological and engineering problems for adaptive, incremental learning and knowledge discovery in large dimensional spaces and in a new environment. Examples include: incremental learning systems; on-line multimodal audiovisual information processing; evolving neuro-genetic systems; bio-informatics; biomedical decision support systems; cyber-security. Open questions, challenges and directions for further research are presented.
References:
[1] N.Kasabov (2007) Evolving Connectionist Systems: The Knowledge Engineering Approach, Springer, London (www.springer.de)
[2] N.Kasabov, Evolving Intelligence in Humans and Machines: Integrative Connectionist Systems Approach, Feature article, IEEE CIS Magazine, August, 2008, vol.3, No.3, www.ieee.cis.org, pp. 23-37
[3] N.Kasabov, Integrative Connectionist Learning Systems Inspired by Nature: Current Models, Future Trends and Challenges, Natural Computing, Int. Journal, Springer, Vol. 8, 2009, Issue 2, pp. 199-210,
[4] N.Kasabov, To spike or not to spike: A probabilistic spiking neural model, Neural Networks, Volume 23, Issue 1, January 2010, Pages 16-19
Bio:
Professor Nikola Kasabov is the Director of the Knowledge Engineering and Discovery Research Institute (KEDRI), Auckland. He holds a Chair of Knowledge Engineering at the School of Computing and Mathematical Sciences at Auckland University of Technology. He is a Fellow of IEEE, Fellow of the Royal Society of New Zealand and Fellow of the New Zealand Computer Society. He is the President of the International Neural Network Society (INNS) and a Past President of the Asia Pacific Neural Network Assembly (APNNA). He is a member of several technical committees of IEEE Computational Intelligence Society and IFIP. Kasabov has served as Associate Editor of Neural Networks, IEEE TrNN, IEEE TrFS, Information Science, J. Theoretical and Computational Nanosciences, Applied Soft Computing and other journals. Kasabov holds MSc and PhD from the Technical University of Sofia, Bulgaria. His main research interests are in the areas of intelligent information systems, soft computing, neuro-computing, bioinformatics, brain study, novel methods for data mining and knowledge discovery. He has published more than 400 publications that include 15 books, 120 journal papers, 60 book chapters, 32 patents and numerous conference papers. He has extensive academic experience at various academic and research organisations: University of Otago, New Zealand; University of Essex, UK; University of Trento, Italy; Technical University of Sofia, Bulgaria; University of California at Berkeley; RIKEN and KIT, Japan; TUniversity Kaiserslautern, Germany, and others. Prof. Kasabov has received the Bayer Science Innovation Award, the RSNZ Science and Technology Silver Medal, the APNNA Excellent Service Award and other awards. More information of Prof. Kasabov can be found on the KEDRI web site: http://www.kedri.info.
14:30 -- 15:00
Neural Network Data Fusion and Uncertainty Analysis for Wind Speed Measurement using Ultrasonic Transducer
Ph.D Juan Mauricio
In this work, a wind speed measurement model based on Neural Network Data Fusion of the time-of-flight (ToF) information is presented. The fusion is obtained through threshold detection (TH) and phase difference (PD) techniques For this purpose, a data fusion method is presented based on the self-organized learning to the variables being fused and assessment the uncertainty ToF measurement is development. Simulation results are presented to several measured values using the TH and PD techniques.
15:00 -- 16:30
A Computational Introduction to the Brain-Mind
Juyang Weng, IEEE Fellow
http://www.cse.msu.edu/~weng/
Abstract:
The brain-mind is hyphened because the model of
the mind is inspired by the brain. Artificial neural networks
perform signal processing and they learn. However, they cannot
autonomously learn and develop like a brain. Autonomous mental
development models all or part of the brain and how a system
develops autonomously through interactions with the environments.
The most fundamental difference between traditional
machine leaning and autonomous mental development is that
a developmental program is task non-specific so that it can
autonomously generate internal representations for a wide variety
of simple to complex tasks. This chapter first discusses why
autonomous development is necessary based on a concept called
task muddiness. No traditional methods can perform muddy
tasks. If the electronic system that you design is meant to perform
a muddy task, you need to enable it to develop its own mind. Then
some basic concepts of autonomous development are explained,
including the paradigm for autonomous development, mental
architectures, developmental algorithm, a refined classification
of types of machine learning, spatial complexity and time
complexity. Finally, the architecture of spatiotemporal machine
that is capable of autonomous development is described.
16:30 -- 17:00
The Neurodynamics of Brain and Behavior: An introduction to Computational Cognitive Neuroscience
Dr. Sebastien Helie
UCSB, Santa Barbara, CA, USA
http://www.psych.ucsb.edu/~helie/
Abstract:
Computational Cognitive Neuroscience (CCN) is a new field that lies at the intersection of computational neuroscience, machine learning, and neural network theory (i.e., connectionism). The ideal CCN model should not make any assumptions that are known to contradict the current neuroscience literature and at the same time provide good accounts of any data that depend on single-neuron activity at the lowest level and behavior at the highest level. Furthermore, once set, the architecture of the CCN network and the models of each individual unit should remain fixed throughout all applications. Because of the greater weight they place on biological accuracy, CCN models differ substantially from traditional neural network models in how each individual unit is modeled, how learning is modeled, and how behavior is generated from the network. A variety of CCN solutions to these three problems are described. This presentation is followed by some example CCN models used in psychology.
January 26, 2011
9:30 -- 11:00
Computational Intelligence Research in Automotive Industry
Danil Prokhorov
Toyota Research Institute North America
Ann Arbor, MI
Abstract:
Computational intelligence is traditionally understood as encompassing artificial neural, fuzzy and evolutionary methods and associated computational techniques. Nowadays there is no sharp boundary between CI and other learning methods. Different CI methodologies often get combined with each other and with non-CI methods to achieve superior results in various applications. In this presentation I will discuss CI methodological issues and illustrate them with several applications from the areas of vehicle manufacturing, vehicle system monitoring and control, as well as active safety. These will be representative of CI applications in the industry and beyond. I will also discuss some lessons learned about successful and yet-to-be-successful industrial applications of CI.
Bio:
Dr. Danil Prokhorov began his technical career in St. Petersburg, Russia, in 1992. He was a research engineer in St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences. He became involved in automotive research in 1995 when he was a Summer intern at Ford Scientific Research Lab in Dearborn, MI. In 1997 he became a Ford Research staff member involved in application-driven research on neural networks and other machine learning methods. While at Ford, he took active part in several production-bound projects including neural network based engine misfire detection. Since 2005 he is with Toyota Technical Center, Ann Arbor, MI, overseeing important mid- and long-term research projects in computational intelligence. He has more than 100 papers in various journals and conference proceedings, as well as several inventions, to his credit. His personal home page is http://home.comcast.net/~dvp/
11:00 -- 11:30
Artificial Vision for Exportable Mangoes Recognition Using Neural Networks
Hugo Froilan VEga Huerta and Ana Huayna Duenas
Universidad Nacional Mayor de San Marcos - Lima, PeruAbstract:
11:30 -- 13:00 Lunch
13:00 -- 14:30
Theoretical and Practical Considerations of Networked Dynamic Models for Detection and Isolation of Anomalies in Systems of Interacting Dynamic Systems
Dragan Djurdjanovic
University of Texas
Austin, TX, USA
http://www.me.utexas.edu/directory/faculty/djurdjanovic/dragan/
Abstract:
Recent years have brought significant advances in the understanding and use of the concept of interconnected dynamic models in various areas. The underlying "divide and conquer" paradigm leads to local model tractability, which in turn leads to the ability to achieve favorable global model characteristics in terms of model convergence, accuracy and stability. In this talk, recent findings related to the influence of model topology on the global convergence and accuracy characteristics will be discussed. Furthermore, this talk presents results of applications of networked dynamic models in detection and isolation of abnormalities in complex systems of interacting dynamic subsystems, such as automotive engine systems and electricity generator components. Finally, on-going research and opportunities for further theoretical and practical extensions of the work presented in this paper will be discussed.
14:30 -- 15:00
Artificial Neural Network Design to Compensate for the Doppler Effect on the Radio Frequency Communications During the Tracking of Pico Satellites in Low Earth Orbit
15:00 -- 17:00
Neurocontrol of helicopters (presentations and demo)
Fernando Jimenez Motte and his team
UPC, Lima, Peru
January 27, 2011
9:30 -- 11:00
Information Theoretic Learning
Jose C. Principe
Distinguished Professor of Electrical Engineering
University of Florida
Abstract:
This talk describes our efforts to go beyond the second order moment
assumption still prevalent in optimal signal processing and machine
learning. We show how the second norm of the PDF can be estimated directly
from data avoiding an explicit PDF estimation step. The link between PDF
moments, information theory and Reproducing Kernel Hilbert spaces will be
established. Applications to adaptive systems with entropic cost functions
will be demonstrated. A generalized correlation function called correntopy
will be defined and its applications in signal processing will be outlined.
Correntopy leads to new measures of similarity, to a new definition of
dependence subspaces and to new tests for causality.
Bio:
Jose C. Principe (M’83-SM’90-F’00) is a Distinguished Professor of
Electrical and Computer Engineering and Biomedical Engineering at the
University of Florida where he teaches advanced signal processing, machine
learning and artificial neural networks (ANNs) modeling. He is BellSouth
Professor and the Founder and Director of the University of Florida
Computational NeuroEngineering Laboratory (CNEL) www.cnel.ufl.edu . His
primary area of interest is processing of time varying signals with adaptive
neural models. The CNEL Lab has been studying signal and pattern recognition
principles based on information theoretic criteria (entropy and mutual
information).
Dr. Principe is an IEEE and AIMBE Fellow and received several awards: IEEE
Career Achievement Award from the EMB Society, the Gabor Award from INNS,
the Neural Network Pioneer Award from the IEEE CI Society. He was the past
Chair of the Technical Committee on Neural Networks of the IEEE Signal
Processing Society, Past-President of the International Neural Network
Society, and Past-Editor in Chief of the IEEE Transactions on Biomedical
Engineering. He is a member of the Advisory Board of the University of
Florida Brain Institute. Dr. Principe has more than 600 publications. He
directed 62 Ph.D. dissertations and 65 Master theses. He wrote an
interactive electronic book entitled “Neural and Adaptive Systems:
Fundamentals Through Simulation” published by John Wiley and Sons, another
on Brain Machine Interfaces and more recently two books entitled:
Information Theoretic Learning, Springer 2010 and Kernel Adaptive Filtering,
Wiley, 2010.
11:00 -- 11:30
Robotic Controller Obtained Through a Speciation-based Metaheuristic
Franco Ronchetti and Laura Lanzarini
Abstract:
Metaheuristics, because of their adaptability to the information environment, are highly useful tools used to obtain robotic controllers. Generally, they involve a computationally costly task, which has motivated the study of different alternatives to reduce acquisition time. This article proposes a variable population metaheuristic that uses speciation in order to obtain a robotic controller, based on a minimal architecture neural network that can solve the obstacle avoidance and target reaching problem. This offers an innovative solution as, in general, fixed-size populations are used. The speciation mechanism used for the metaheuristic proposed here ensures genetic diversity by increasing search capacity and avoiding premature convergence. The genetic operators used and the different implementation aspects that were considered for the introduction of this populational variation will be discussed throughout this paper. The tests carried out both in simulated environments as well as the actual robot yielded satisfactory results.
11:30 -- 13:00 Lunch
13:00 -- 13:30
Virtual Simulation of a Myoelectric Prosthesis
Wilmer J. Lobato Malaver and Msc. Sergio Salas Arriaran
Abstract:
This project consists of a virtual simulation that reproduces four (4) movements in a Myoelectric Prosthesis. The project is divided into four (4) parts: Analog Signal Conditioning, Signal Digitization, Digital S ignal Processing and Simulation. The goal of the Analog Signal Conditioning is to prepare the analog signal from the muscles involved in movement (EMG signal) so that it can be digitized for further analysis. The Digitization of the EMG signal part has the task to convert the analog signal into a digital EMG signal, which will be sent to the computer for processing. The Digital Signal Processing is the most important part of the project and consists of two main parts: The Feature Extraction and Pattern Classifier. The first one extracts the necessary and sufficient parameters of the EMG signal. The second one uses these parameters to distinguish the type of movement made by the patient. The last part of the project is the simulation, where are played in real time the contractions made by the patient using the graphical interface of a human arm.
13:30 -- 14:00
Solution to the Tic-Tac-Toe Problem using Hamming Distance approach in a Neural Network
Nazneen Rajani, Rajoshi Biswas, Dr. Gaurav Dar, and Dr. Ramesha C.K.
This paper focuses on using a Hamming Distance Classifier in Neural Networks to find the most optimal move to be made in the Tic-Tac-Toe problem such that the game always ends in a win or a draw.
14:00 -- 14:30
Artificial Brain based on Top-Down Selective Attention for Noise-Robust Recognition and Multimodal Integration
Soo-Young Lee
Abstract:
Top-down selective attention is regarded as the brain mechanism to recognize interesting patterns from noisy and complex background. We present Artificial Brain, i.e., an artificial cognitive system based on a cognitive model of top-down selective attention, and its application to OfficeMate to serve as an artificial secretary in our office. An attention filter was introduced at the input features and adjusted to minimize the output error of the attended class. Low-complexity constraint was proposed to prevent overfitting, and a confidence measure was introduced on each attended class. The final recognition was made with the class with the maximum confidence measure. It also was extended to multimodal integration such as classification with audio and visual information. The proposed algorithm demonstrated much better speech recognition rates with and without lip reading in noisy environments.
14:30 - 15:00
NEURO COPTER” LINEAR QUADRATIC GAUSSIAN DESIGN LQG AND IMPLEMENTATION OF THE CONTROL SYSTEM OF AN UNMANNED AERIAL VEHICLE UAV WITH STATE SPACE MODELLING AND KALMAN FILTERING AND AUTONOUMOUS GUIDANCE WITH COMPUTER VISION AND DATA LINK COMMUNICATIONS
Fernando Jimenez, Jose Oliden, Juan Huapaya, Germain Cardenas
Abstract:
Controlling scale helicopters in its various flight modes is a complex task due to the nonlinearity of its structure and strong coupled motion dynamics. In this paper, an adaptive neural controller is developed for a scale helicopter using data of an artificial vision stage and from sensors installed in the air vehicle. Data is transmitted from the helicopter through a data link stage and is received on a computer where the neuronal controller is implemented. The outputs of the control stage return to the helicopter through the same data link in order to close the control loop. It is shown that a proper communication between various stages that constitute the project, allows an accurate control of a scale helicopter through a computer.