Deep Learning for Internet of Things Data Analytics

Abstract

The recent technological innovations and brisk amalgamation of domains such as sensing and actuating technologies, embedded systems, wireless communication, and data analytics are accelerating the growth of Internet of Things (IoT). The massive number of sensors deployed in IoT generate humongous volumes of data for a broad range of applications such as smart home, smart healthcare, smart manufacturing, smart transportation, smart grid, smart agriculture etc. Analyzing such data in order to facilitate enhanced decision making, increase productivity and accuracy, ameliorate revenue is a critical process that makes IoT a precious idea for businesses and a standard of life improving paradigm. Although deriving concealed information and inferences out of IoT data is promising to improve the standard of our lives, it is a complicated task that cannot be accomplished by conventional paradigms. Deep Learning would play a vital role in creating smarter IoT as it has shown remarkable results in different fields including image recognition, information retrieval, speech recognition, natural language processing, indoor localization, physiological and psychological state detection etc. and these form the foundation services for IoT applications. In this regard, investigating the potential of Deep Learning for IoT data analytics becomes indispensable. Motivated to address this concern, this paper explores the flair of Deep Learning for analyzing data generated from IoT environments. A detailed discussion on various Deep Learning architectures, their role in IoT data analytics and potential use cases is also presented. Finally, open research challenges and future research directions are discussed in order to promote future research in this domain.