Granular Computing: An Introduction to
نویسنده
چکیده
What is granular computing(GrC)? It is a shifting paradigm. Let us start with a few words about how the term was coined. In the academic year 1996-97, when Lin (this section editor) took his sabbatical leave at UC-Berkeley, Zadeh suggested granular mathematics (GrM) to be his research area. To limit the scope, Lin proposed the term granular computing [14]. What was GrC then? Zadeh had outlined it in his 1997 seminal paper [15]. While Lin took incremental approach: He mapped his neighborhood system [5] to Zadeh’s intuitive definition [12] and used it as his First GrC Model [8], [9], [10]. It may be important to point out that the concept of neighborhood systems, which was motivated from the approximate retrieval in database [7], is a generalization of topological neighborhood system that formalizes the ancient intuition of infinitesimal granules. Much progress has been achieved, since then. So this section has been organized to represent this progress and to reflect the current state of GrC. We believe in incremental approach, namely, each new step is based on solid results and move forward. So many special theories and applications are gathered. Jointly, they refelct the current state of GrC and may also implicilty hint to the ultimate goals of GrC.. To grasp the main idea from such a diverse collection of papers, a roadmap will be helpful: We suggest the reader start with the first 4 Sections of T. Y. Lin’s paper Granular Computing: Ancient Practices, Modern Theories and Future Directions. There, the readers may want to pay special attentions to the first three examples:
منابع مشابه
INTERVAL ANALYSIS-BASED HYPERBOX GRANULAR COMPUTING CLASSIFICATION ALGORITHMS
Representation of a granule, relation and operation between two granules are mainly researched in granular computing. Hyperbox granular computing classification algorithms (HBGrC) are proposed based on interval analysis. Firstly, a granule is represented as the hyperbox which is the Cartesian product of $N$ intervals for classification in the $N$-dimensional space. Secondly, the relation betwee...
متن کاملSYSTEM MODELING WITH FUZZY MODELS: FUNDAMENTAL DEVELOPMENTS AND PERSPECTIVES
In this study, we offer a general view at the area of fuzzy modeling and fuzzymodels, identify the visible development phases and elaborate on a new and promisingdirections of system modeling by introducing a concept of granular models. Granularmodels, especially granular fuzzy models constitute an important generalization of existingfuzzy models and, in contrast to the existing models, generat...
متن کاملInterval Computations as an Important Part of Granular Computing: An Introduction
This chapter provides a general introduction to interval computations, especially to interval computations as an important part of granular computing. This introduction is aimed at researchers who would like to learn more – and eventually to use – the main ideas and techniques of granular computing. We explain how intervals naturally appear in data processing, which techniques exist for process...
متن کاملIntegrative Levels of Granularity
In their book, Granular Computing: An Introduction, Bargiela and Pedrycz present a view that granular computing is an emerging conceptual and computing paradigm of information processing. A central notion is an information-processing pyramid with multiple levels. Different levels involve different types of processing. The lowest level concerns numeric processing, the intermediate level concerns...
متن کاملGranular Computing: a New Paradigm in Information Processing
Granular computing (GrC) has emerged as one of the fastest growing information processing paradigm in computational intelligence and human-centric systems. It has been gaining popularity in the past ten years. GrC is often loosely defined as an umbrella term to cover any theories, methodologies, techniques, and tools that make use of granules in complex problem solving. As a new paradigm for th...
متن کامل