Fuzzy Rule Based Big Data Analytics Strategies for Providing Healthcare-as-a Service in Cloud

Abstract

Medical data analysis is one of the significant parts of human life with the advancement of information and communicative technology and has two major issues. First, the information gathered about the patients in remote healthcare applications comprises huge data since it changes regarding volume, velocity, variety and, and value. New strategies are required to store and retrieve data based on the context of data on the cloud to access the information in less time.  To process such a huge assortment of heterogeneous information is perhaps the greatest test that needs a specific methodology. Secondly, it is difficult to give precise definitions and symptoms of clinical ideas and the relationship between the concepts in the greater part of the cases because of boundaries are not satisfactory. A set of fuzzy rules are created to analyze and diagnose the patient status dependent on the basic signs. The fuzzy strategy yields an early warning of any patients irregularity status and it is efficient for decision making in numerous classification problems. These systems have been effectively applied in hospitality because of their granular computing to depict the complex frameworks without requiring an exact scientific model. The primary thought of this paper is to draw a short depiction of fuzzy logic applications on different clinical diagnosis systems and their related fields. Further, we have illustrated a literature review on fuzzy strategies used in big data analytics with health care as a service. Besides, the process of fuzzy along with fuzzification, defuzzification, and the major tasks of fuzzy logic is presented.