Machine learning methods for IoT and their Future Applications

With the advent of rapid developments, large number of heterogeneous devices is able to connect with the help of IOT technology. Although IOT possess very complex architecture because of connectivity of variety of devices and services in the system. In this paper, a brief concept of urban IOT system is presented which are designed to support smart city and advanced communication technologies. Hence a comprehensive survey of architecture, technologies, and computational frameworks is provided for a smart IOT. It also discusses the major vulnerabilities and challenges faced by IOT and also present how machine learning is applied to IOT. Hence smart city is considered as the use case and it explains how various techniques are applied to data in order to extract great results with good efficiency.

I. Introduction

Internet of things is the advent of exciting and most dynamic developments in the field of information and communication technology. Over the past two decades we have seen that network topologies are restricted in connecting the end-user devices such as laptops, desktops, smartphones and tablets which are available recently [1], [2]. Now in today’s scenario devices are now connected to networks which include electric meters, medical devices, street lights, smart TVs, traffic controls and Alexa and Google home as digital assistants. Hence by 2020, the number of devices connected to internet has expanded approximately by 25 billion and it may generate US$13 trillion revenue by 2025 [3], [4].