A detailed analysis of Deep Learning for Internet of Things (IoT) Applications
In the age of the Internet of Things (IoT), a massive amount of data belonging to a wide range of fields and applications are being collected/generated. The velocity of big data generated by IoT is characterized in terms of time and location dependency with varying data quality. The key to developing “Smart” IoT applications lies in intelligent processing and analysis of the gathered big data. This paper provides an overview of Deep Learning (DL) methodologies and the potential of emerging DL techniques in IoT data analytics. It also discusses different types of data generated by IoT applications and how specific DL models provide better results for specific applications. A brief study on Smart City and its data characteristics has been provided. This paper also covers software frameworks used to develop DL for different IoT applications.
This paper would answer the following questions –
- How different data is generated in an IoT Application?
- What are the available computing frameworks for processing data?
- What are the characteristics of IoT data and its analytics requirements?
- How to analyze the characteristics of the different datasets generated by applications in a Smart City?
- What are the various frameworks available for DNN Inference and Training?
- What are the primary services of IoT that use DL as their intelligence engine?
