Rough set data representation using binary decision diagrams
نویسندگان
چکیده
A new information system representation, which inherently represents indiscernibility is presented. The basic structure of this representation is a Binary Decision Diagram. We offer testing results for converting large data sets into a Binary Decision Diagram Information System representation, and show how indiscernibility can be efficiently determined. Furthermore, a Binary Decision Diagram is used in place of a relative discernibility matrix to allow for more efficient determination of the discernibility function than previous methods. The current focus is to build an implementation that aids in understanding how binary decision diagrams can improve Rough Set Data Analysis methods. Representación de datos de conjuntos aproximados mediante diagramas de decisión binarios Resumen. Se expone una nueva representación de sistema de información, que incorpora inherentemente la indiscernibilidad. La estructura básica de esta representación es un diagrama de decisión binario. Se ofrecen los resultados de unas pruebas llevadas a cabo para convertir grandes conjuntos de datos en una representación de sistema de información de diagrama de decisión binario, y se muestra cómo se puede determinar, de forma eficaz, la indiscernibilidad. Además, se utiliza un diagrama de decisión binario en lugar de una matriz de discernibilidad relativa para permitir que la determinación de la función de discernibilidad sea más eficaz que en los métodos anteriores. Actualmente, el interés se centra en la construcción de una implementación que ayude a entender cómo los diagramas de decisión binarios pueden mejorar los métodos de análisis de datos de los conjuntos aproximados.
منابع مشابه
Symbolic Representation for Rough Set Attribute Reduction Using Ordered Binary Decision Diagrams
The theory of rough set is the current research focus for knowledge discovery, attribute reduction is one of crucial problem in rough set theory. Most existing attribute reduction algorithms are based on algebra and information representations, discernibility matrix is a common knowledge representation for attribute reduction. As problem solving under different knowledge representations corresp...
متن کاملTo appear in the Third International Workshop on Rough Sets and Soft Computing (RSSC 94) A Third Dimension to Rough Sets
Rough-sets relative reducts allow one to reduce the number of attributes in a supervised classi cation problem without sacri cing the consistency of the decision table. In many problems, the cardinality of the relative reducts is large, making the decision table unmanageably big. We propose reducing the size of reducts, and hence the decision table, by increasing the number of label values (val...
متن کاملA Third Dimension to Rough Sets
Rough-sets relative reducts allow one to reduce the number of attributes in a supervised clas-siication problem without sacriicing the consistency of the decision table. In many problems, the cardinality of the relative reducts is large, making the decision table unmanageably big. We propose reducing the size of reducts, and hence the decision table, by increasing the number of label values (va...
متن کاملImplicit Representation of Discrete Objects
This tutorial paper discusses the known representations based on Binary Decision Diagrams (BDDs) for various types of discrete objects: incompletely specified functions, sets, finite state machines, binary and multi-valued relations, etc. While presenting the known material, the emphasis is on those aspects of implicit representations that are important to achieve speed-up in computation. The n...
متن کاملA New Symbolic Method for Discernibility Matrix in Rough Set
Generating discernibility matrix consumes huge time and space .To solve this problem, A new Binary Discernibility Matrix (BDM) induced from information table is defined, The concept of Binary Conjunction Matrix(BCM) is then introduced, Finally A novel method for discernibility matrix using Zero-Suppressed BDDs (ZBDD) and Ordered binary decision diagrams (OBDD) is proposed in this paper, experim...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2004