2016 IEEE Conference on Mechatronics, Adaptive and Intelligent Systems (MAIS)

#Intelligent #Systems #Mechatronics #Robotics #Neural #Networks #Deep #Learning #Reinforce #Computational #Intelligence
Share

Organized by the IEEE Computational Intelligence Society Queretaro Chapter and the Asociación Mexicana de Mecatrónica A.C.


MAIS 2016 strives to bring together people in the area of SMC and CI to provide an international forum for the reporting of current developments, to summarize the state-of-the-art, and to exchange new ideas and advances on all aspects of systems engineering, human machine interfaces, emerging cybernetics, mechatronics systems and intelligent systems. In recent years, a trend has emerged in which bio-inspired intelligence plays a key role in these aspects to pursue for novel technology. The resulting techniques vitalize life science engineering and daily life applications. In light of this trend,the theme for this conference is Intelligent and Mechatronics Systems. Papers related to this themeare especially solicited, including theories, methodologies, and applications of intelligent systems in science, technology, security, education etc. Topics covering industrial issues/applications andacademic research include, but are not limited to:

Analytical Learning
Artificial Neural Networks
Bayesian Learning
Brain-Computer Interface
Combining Inductive and Analytical
Computational Intelligence
Computational Learning Theory
Embedded Systems
Evaluating Hypotheses
Genetic Algorithms
Learning
Learning Sets of Rules
Mechatronics Systems
Incremental Learning
Industrial Application
Instance-Based Learning
Intelligent Systems
Intelligent Systems Fuzzy
Intelligent Transportation Systems
Image Processing
Reinforcement Learning
Software Development
Support vector machine
Systems Modeling & Control
Robotic Systems
Robotics and Manufacturing Automation



  Date and Time

  Location

  Hosts

  Registration



  • Add_To_Calendar_icon Add Event to Calendar
  • Av Luis Donaldo Colosio, Centro
  • Hermosillo, Jalisco
  • Mexico 83000
  • Building: Centro de las Artes Unison

  • Contact Event Host
  • Co-sponsored by Asociación Mexicana de Mecatrónica


  Speakers

Dr. Carlos A. Coello Coello Dr. Carlos A. Coello Coello

Topic:

Metaheurísticas Bio-Inspiradas: Resolviendo Problemas como la Naturaleza lo Haría

En esta plática se hablará sobre las metaheurísticas, con un particular énfasis en aquellas que tienen una inspiración biológica (p.ej., los algoritmos evolutivos, los algoritmos cumulares y las colonias de hormigas). Se pondrá particular énfasis en la forma en que este tipo de herramienta computacional ha permitido resolver problemas de gran complejidad en tiempos razonablemente cortos, mediante la simulación de ciertos procesos de la naturaleza tales como la evolución natural. En la parte final de la plática se discutirán brevemente algunas de las áreas más prometedoras de investigación futura en esta área.

Biography:

Carlos Artemio Coello Coello nació en Tonalá, Chiapas, el 18 de octubre de 1967. Cursó la licenciatura en ingeniería civil en la Universidad Autónoma de Chiapas graduándose con mención honorífica. Ese mismo año, recibió la “Medalla Diario de México” por ser uno de los “mejores estudiantes de México”. Posteriormente, obtuvo una beca de la Secretaría de Educación Pública para cursar estudios de maestría y doctorado en ciencias de la computación en la Universidad Tulane, en Estados Unidos, graduándose en 1993 y 1996, respectivamente. Desde 2001, trabaja en el Centro de Investigación y de Estudios Avanzados del Instituto Politécnico Nacional (CINVESTAV-IPN). El Dr. Coello ha sido pionero en un área de la computación que hoy se conoce como “optimización evolutiva multi-objetivo”, la cual se enfoca a la solución de problemas con dos o más funciones objetivo (normalmente en conflicto entre sí) usando algoritmos con inspiración biológica. Su trabajo ha girado principalmente en torno al diseño de algoritmos, varios de los cuales se han usado para resolver problemas del mundo real en países como Estados Unidos, Colombia, Chile y Cuba. El Dr. Coello cuenta con más de 400 publicaciones, las cuales reportan a la fecha más de 31,000 citas en Google Scholar (su índice h es de 68). Ha dirigido a la fecha 65 tesis (incluyendo 17 de doctorado), varias de las cuales han recibido premios. Es también editor asociado de 8 revistas internacionales, incluyendo las 2 más importantes de su área y pertenece al comité editoral de 4 revistas más. El Dr. Coello es el computólogo más joven en haber llegado al nivel 3 del Sistema Nacional de Investigadores (SNI) en el área VII (a los 37 años de edad), y desde 2010, es Investigador Cinvestav 3F (la categoría más alta posible en el CINVESTAV-IPN). Sólo hay 31 investigadores (de 660 con que cuenta el CINVESTAV-IPN) que ostentan esta categoría y él es el único del área de Tecnología.

Email:

Address:CINVESTAV-IPN, Dept. Computación, Av. Instituto Politécnico Nacional No. 2508, Col. San Pedro Zacatenco, México, D.F., Mexico, Mexico, 07300

Prof. Eduardo José Bayro-Corrochano Prof. Eduardo José Bayro-Corrochano

Topic:

Geometric Cybernetics

In this talk we present a new framework the conformal geometric algebra for applications in computer vision, graphics engineering and robotics. We will show that this mathematical system  keeps our intuitions and insight of the geometry of the problem at hand and it helps  us to reduce considerably the computational burden of the problems. Surprisingly as opposite to the standard projective  geometry, in conformal geometric algebra we can deal simultaneously with incidence algebra operations
(meet and join) and conformal transformations represented effectively using spinors (quaternions, dual quaternions, etc). In this regard this framework appears  promising for dealing with kinematics, dynamics and projective geometry  problems without the  need to abandon the mathematical system (as  current approaches). We present some real tasks of perception and action treated  in a very elegant and efficient way: body--eye calibration, 3D reconstruction and robot navigation and visually guided 3D object grasping making use  of the directed distance and intersections of lines, planes and spheres both involving conformal transformations. For tracking we use the Motor (dual quaternion) extended Kalman filter and for control problems we reformulate the differential geometry and the Jacobian based control rule for n D. O. F. robot arms using conformal geometric algebra. At the final part of the talk we will also present the theory and practicalities of the Multi-vector Support Vector Machines useful for learning in visual guided robotics.  The authors believe that the  framework of geometric algebra  can be in general  of great advantage for applications in image processing,  stereo vision, range data, laser, omnidirectional and odometry based robotic systems, kinematics and dynamics of robot mechanisms and advanced nonlinear  control techniques.We will present a variety of robot vision systems using geometric methods: the humanoid Mexone (30 DOF, 120 cm), the humanoids CinvesRob (34 DOF, 175 cm.), Ñawi the smart eye for visual impaired people guidance, a robotic system for minimal invasive kidney surgery, Bug-II a sewer inspection robot  and others.

Biography:

EDUARDO JOSE BAYRO-CORROCHANO gained his Ph.D. in Cognitive Computer Science in 1993 from the University of Wales at Cardiff. From 1995 to 1999 he has been Researcher and Lecturer at the Institute for Computer Science, Christian Albrechts University, Kiel, Germany, working on applications of geometric Clifford algebra to cognitive systems. At present is a full professor at CINVESTAV Unidad Guadalajara, México, Department of Electrical Engineering and Computer Science. His current research interest focuses on geometric methods for artificial perception and action systems. It includes geometric neural networks, visually guided robotics, humanoids, color image processing, Lie bivector algebras for early vision and robot maneuvering. He developed the quaternion wavelet transform for quaternion multi-resolution analysis using the phase concept. He  is associate editor of  the Journal of Robotica, Journal of Mathematical Imaging and Vision, IEEE Trans. Neural Networks and Learning Systems and member of the editorial board of Journal of Pattern Recognition and  Journal Of Theoretical And Numerical Approximation. He is editor and author of the following books: Geometric Computing for Perception Action Systems, E. Bayro-Corrochano, Springer Verlag, 2001; Geometric Algebra with Applications in Science and Engineering, E. Bayro-Corrochano and G. Sobczyk (Eds.), Birkhauser 2001; Handbook of Geometric Computing  for Pattern Recognition, Computer Vision, Neurocomputing and Robotics, E. Bayro-Corrochano, Springer Verlag, 2005. Geometric Algebra Computing in Engineeringa and Computer Science, E. Bayro-Corrochano and G. Scheuermann (Eds.), Springer Verlag 2010; Geometric Computing for Wavelet Transforms, Robot Vision, Learning, Control and Action, Springer Verlag, 2010. He has published  over 220 refereed journal, book chapters  and conference papers. He is a IEEE senior member and fellow of the IAPR society. He built the humanoid Mexone 110 cm with 30 DOF, a system for intelligent  guidance of visually impaired people and a 3 manipulator-robot system for minimal invasive surgery.

Email:

Address:CINVESTAV, Campus Guadalajara. Department of Electrical Engineering and Computer Science, Avendia Del Bosque 1145, Colonia El Bajío, Guadalajara, Jalisco, Mexico, 45019


Dr. Carlos A. Coello Coello

Topic:

Metaheurísticas Bio-Inspiradas: Resolviendo Problemas como la Naturaleza lo Haría

Biography:

Email:

Address:México, D.F., Mexico, Mexico

Prof. Eduardo José Bayro-Corrochano

Topic:

Geometric Cybernetics

Biography:

Email:

Address:Guadalajara, Jalisco, Mexico