Big data analytics in healthcare internet of things

Abstract

Nowadays, wearable medical devices play a vital role in many environments such as continuous health monitoring of individuals, road traffic management, weather forecasting, and smart home. These sensor devices continually generate a huge amount of data and stored in cloud computing. This chapter proposes Internet of Things (IoT) architecture to store and process scalable sensor data (big data) for healthcare applications. Proposed architecture consists of two main sub-architecture, namely, MetaFog-Redirection (MF-R) and Grouping & Choosing (GC) architecture. Though cloud computing provides scalable data storage, it needs to be processed by an efficient computing platforms. There is a need for scalable algorithms to process the huge sensor data and identify the useful patterns. In order to overcome this issue, this chapter proposes a scalable MapReduce-based logistic regression to process such huge amount of sensor data. Apache Mahout consists of scalable logistic regression to process large data in distributed manner. This chapter uses Apache Mahout with Hadoop Distributed File System to process the sensor data generated by the wearable medical devices.