problems, data and analysis task are moving to the edge platform. However, most edge devices do not have
enough capacity to process and train large amounts of data. In this paper, we propose a new framework struc-
ture that can analyze IoT data by distributing analysis role. The proposed framework is designed to maximize
the resources of the cloud to generate the model and to use the model at the edge to enable immediate and
instantaneous actuator operation. And we also present a case study to verify this framework.
10. Scalable and Flexible IoT data analytics: when Machine Learning meets SDN and
Virtualization
Link: https://ieeexplore.ieee.org (Accessed on 01 July 2019)
Abstract:
This paper deals with Internet of Things (IoT) data analytics in a collaborative platform where computing
resources are available both at the network edge and at the backend cloud. Thereby, the requirements of both
low-latency and delay tolerant IoT applications can be met. Moreover, this platform faces the challenging
heterogeneous features of IoT data, i.e. its high dimensionality or its geo-distributed and streaming data
nature. The proposed approach relies on two pillars. On the one hand, recent advances of machine learning
(ML) techniques are leveraged to describe how the IoT data analytics can be performed in our platform. On the
other hand, the virtualization, centralized management, global view and programmability of the computing
and network resources are considered to fulfill the requirements of the ML methods. Unlike the related work,
herein the interplay and synergies between those two pillars are explained. Also, the ML methods for this
collaborative platform are described in more detail.
SUMMARY
IoT, Data Analytics and Machine Learning work together to solve complex problems with ease.
In the previous chapter, we have seen how AI is making its presence in the IoT world and creating
a positive impact. Machine learning, a subset of AI is also greatly helping IoT to gain intelligence
and creating an automated world to solve complex problems. Data analytics is another great
element that helps to get meaning out of the massive data that we generate in IoT. Data analytics
provide various models to process this data in an ecient manner.
In this chapter, we have learnt the following concepts:
• What is data analytics and how it is useful for the IoT world?
• Applications of machine learning in conjunction with IoT in the real world,
• Basics of modeling in machine learning,
• Classification and regression problems and dierentiate between them,
• The fundamentals of logistic and linear regression,
• The structure of the K-nearest neighbor, and
• The working of random forest,
• How to decipher convolutional neural networks, and
• Underlying theory of Bayesian models.
In the next chapter, we will spend time understanding various security challenges that the
IoT world is facing. We will explore the security threats and discuss in details how to think
about solving this in the subsequent chapter.
270 Internet of Things
Internet_of_Things_CH10_pp249-270.indd 270 9/3/2019 10:15:58 AM
..................Content has been hidden....................
You can't read the all page of ebook, please click here login for view all page.