IoT based energy aware local approximated MapReduce fuzzy clustering for smart healthcare data transmission

Abstract

Big Data is a collection of large amount used to store and to process for future use. Internet of Things (IoT) technology is used in smart home, smart healthcare. IoT has limited resources like processing capability and supplied energy. Many researchers carried out their research on resource optimized data clustering in bigdata environment. But, the computational complexity and energy consumption was not reduced by existing techniques. Therefore, IoT based Energy Aware Local Approximated Fuzzy MapReduce Clustering (IoT-EALAFMRC) Method is introduced. The main objective of IoT-EALAFMRC Method is introduced to perform an efficient priority based data transmission in smart healthcare environment. Initially, IoT devices are used to collect the large number of patient data in different location at a same time. During data transmission, there is a chance of traffic occurrence. In order to reduce the traffic occurrence rate during the data transmission to the physician (i.e., doctor), Energy Aware Local Approximated Fuzzy MapReduce Clustering is used with map and reduce function to group the patient data into normal constrained data or emergency constrained data based on physical health condition with higher clustering accuracy. IoT-EALAFMRC Method performs the cluster assignment based on neighborhood relationships among data. After clustering of patient data, the data is sent to the physician with minimum time consumption. Through minimizing the traffic, retransmission of patient data gets reduced. This in turn helps to reduce the energy consumption. Experimental evaluation is carried out using IoT-EALAFMRC Method on factors such as energy consumption, clustering accuracy and execution time for different number of patient data.