IoT Sensor Data Integration in Healthcare using Semantics and Machine Learning Approaches

Abstract

In the current scenario, around 35 billion Internet of Things (IoT) devices is connected to the internet. By 2025, it is predicted that the number will grow between 80 and 120 billion devices connected to the internet, supporting to generate 180 trillion gigabytes of new sensor data that year. The IoT sensor data is generated from various heterogeneous devices, communication protocols, and data formats that are enormous in nature. This huge amount of data is not integrated and analysis manually. This is a significant problem for IoT application developers to make the integration of IoT sensor data. However, the high volume of data has intended to lack of manual data integration and formulated the neediness into the research of semantic and machine learning approaches. Semantic annotation of IoT data is the foundation of IoT semantics. Clustering is one way to resolve the integration and analysis of IoT sensor data. Semantics and learning approaches are the keys to address the problem of sensor data integration and analysis in IoT. To overcome these limitations, in this chapter, firstly review on IoT healthcare data integration semantic techniques and secondly overview the machine learning algorithms for integration of IoT healthcare data. Finally, the major research areas are discussed to integrate the IoT healthcare data. The processes and corresponding algorithms of the proposed framework are presented in detail with layer by a layer including the raw data acquisition, semantic annotation, resources data extraction, semantic reasoning, and clustering.