Plenary Lecture
Proposed Method and Program for Classification of Information Systems
Professor Amaury A. Caballero
Department of Electrical and Computer Engineering
Florida International University
USA
E-mail: caballer@fiu.edu
Abstract: The necessity of interpreting the huge quantity of received information for its use in many technological processes is of primarily importance in the modern industry. Different methods have been developed for extracting useful information from a row dataset. Neural networks and information entropy have been used to discriminate. Also the combination of rough sets and fuzzy logic for classification is a widely adopted method. Rough set theory helps in minimizing the number of attributes that influence the selection and fuzzy logic permits to discriminate when there is more than one possible solution for the same attributes and intervals. Differently from other works, the concept of information measure is used in this work, together with a fuzzy logic discrimination tool. Using these concepts, an attribute reduction is initially obtained and then, if necessary, fuzzy logic can be applied for discriminating among the possible solutions. The method results simpler than others and as accurate as the methods usually employed. Using the basic information concepts, the proposed method and a program have been developed for minimizing the number of used attributes for the discrimination of objects, under some maximum error restriction, α. In the conference, it is shown with examples that having a row database with the values obtained from different sources in different runs, it is possible:
1) To minimize and show the attributes that discriminate selected objects without any uncertainty for the accepted error α
2) To minimize and show the attributes that discriminate selected objects with uncertainty for the accepted error α
3) To show the discriminated objects without any uncertainty, and those that can be discriminated with certain uncertainty for the selected attributes and the accepted error α
4) To show the objects that cannot be discriminated with the selected attributes for the accepted error α.
Brief Biography of the Speaker: Amaury A. Caballero obtained his Bachelor Degree in Electrical Engineering from the University of Havana, Cuba, earned his Ph.D. in Technical Cybernetics from the Energy Institute of Moscow, Russia, and his Professional Engineer License from the state of Florida, USA. For more than 20 years he taught and performed research at the Higher Polytechnic Institute of Havana, where he earned the category of Full Professor and directed research in the areas of Automatic Control and Robotics. He was also a member of the Higher Scientific Council of the Cuban Academy of Sciences and was awarded medals in recognition of his work from the Cuban Ministry of Higher Education and at the Technical University of Brno, in Czech Republic, where he participated in a post-doctoral Study in robotics and developed research with the Faculty. Dr. Caballero has been invited to give speeches at the Universidad de Pamplona in Colombia, the Universidad Católica de Santa María in Peru, the Universidad Tecnologica Centroamericana in Honduras, and the Universidad Autonoma Estatal del Estado de Hidalgo in Mexico, where he also imparted a graduate course in fuzzy logic. He has published two text books and one monograph in the area of automatic control and obtained five certificates of invention in the same area. He also wrote published research reports and papers, published in scientific journals and conference proceedings. In total he has over 100 publications. Presently, he is a Senior Lecturer at Florida International University, where he teaches in the department of Electrical and Computer Engineering and has conducted in-depth research in the areas of automation applied to construction management and in fuzzy logic applications, and also works as a consultant in electrical engineering.