부산대학교 도서관

The recent advancements in various communication technologies have paved the way for sensor devices to connect with the internet. It can be expected that the quantity of internet-connected devices can reach a maximum of 75.44 billion by 2025. The quantities of such devices directly influence the amount of data to be transferred. The Internet of Things (IoT) is one of the technologies that provide connectivity among such devices through the existing internet. In addition to this, the IoT generates big data with the characteristics such as time-dependent, location-dependent, and multi-modal data quality. This paper presents a detailed survey about various machine learning techniques that treat the issues of the data generated by IoT devices. Further, the applications of various machine learning algorithms to the IoT data for extracting higher-level information have been presented.