International Journal of Computer Science Trends and Technology (IJCST) – Volume 2 Issue 5, Sep-Oct 2014 ISSN: 2347-8578 www.ijcstjournal.org Page 119 Granular Computing - A Theoretical Study N.Senthilkumaran 1 , C.Kirubakaran 2 Department of Computer Science and Applications Gandhigram Rural Institute - Deemed University Gandhigram Dindigul Tamil Nadu - India ABSTRACT Granular computing becomes known as an innovative multidisciplinary study and has established much attention in recent years. The framework shared multiple views and multiple levels of understanding in each view from many fields. The three components of the theory are labeled as the philosophy, methodology and the computation, the integration of the above view of granular computing as a way of structured thinking, structured problem solving and information processing and hierarchical granular structures. By using the levels of granularity, granular computing provides a systematic, natural way to analyze, understand, represent, and solve real world problems. The granular computing is a more philosophical way of thinking and a practical methodology of problem solving. This paper presents the study of basic inspiration for granulation and direct Granular computing as a structured combination of algorithmic and non-algorithmic information processing. Keywords:- Granular computing, hierarchy, structured thinking, structured problem solving, Triarchic Theory I. INTRODUCTION In 1979, first time Zadeh [3], [11] declared and explains the concept of information granulation and recommended the information granulation that adapts with fuzzy set theory may offer efficient answers for different applications. In 1997, T. Y. Lin [1], [2], [6], [10] was introduced the Granular computing first time to label some new area of multi-relative studies. The basic theory of granular computing was presented as information granularity or information granulation [1], [5]. Many ideas like natural and social scientific disciplines are represented by granular computing [13]. The interrogative sentence that comes first into what is granular computing, most of researchers utilized the term granular computing without giving a complete definition and as it is not possible easy one [3] [8]. Alternatively, one relies on an agreement of the granular computing based on their working domain and their own intuition [3], [17]. So that no specific explanations may for aspects of granular computing, this may be counterproductive at the early development stage of the study [3]. The researchers of granular computing can create the problem based on hypotheses and models of computational intelligence. From that the granular computing is not come under the specific examples and methods. Thither are many positive aspects for the using of granular computing. Granular computing provides true and innate representations of giving systems. Through the multiple level hierarchy representation, one can easily get a broad understanding of a system. The carrying out of granular computing would lead to more effective information processing schemes. Unwanted, irrelevant details are avoided by focusing on the right level of abstraction. Different hierarchy levels focus on various granularities characterized by different grain sizes. From that way the granular computing able to simplify a complex system or a complex problem. Machine Learning (ML) is grounded in the learning form the sample information. Many arenas have been executed in this field of granular computing, among which are rough set, nearest neighbor classifier, decision tree induction, Bayesian networks, induction rules learning, neural nets, genetic algorithm etc. [12]. Dealing samples with granular computing and a classifier may take from these reconstructed data obtained accurate rate will be a comparative with learning from the raw information straight off in a higher categorization [20]. Human problem solving involves the perception, abstraction, representation and understanding of real problems [19], as well as their solutions, at various levels of granularity. The granularity is motivated to use for its practically simplified the problem, clarity, low expansive, correct approximation, and tolerance of uncertainty. This paper is organized as follows. Section II discusses about the Basic Components of Granular Computing. Section III describes about the Triarchic Theory of Granular Computing. Section IV summarizes Basic Issues of Granular Computing. Section V focuses on Human-Inspired Granular Computing. Section VI explains the conclusion. II. BASIC COMPONENTS OF GRANNULAR COMPUTING On modeling aspects of granular computing, basically three components are focused and their interactions also analyzed. RESEARCH ARTICLE OPEN ACCESS