Book Image

Hands-On Industrial Internet of Things

By : Giacomo Veneri, Antonio Capasso
Book Image

Hands-On Industrial Internet of Things

By: Giacomo Veneri, Antonio Capasso

Overview of this book

We live in an era where advanced automation is used to achieve accurate results. To set up an automation environment, you need to first configure a network that can be accessed anywhere and by any device. This book is a practical guide that helps you discover the technologies and use cases for Industrial Internet of Things (IIOT). Hands-On Industrial Internet of Things takes you through the implementation of industrial processes and specialized control devices and protocols. You’ll study the process of identifying and connecting to different industrial data sources gathered from different sensors. Furthermore, you’ll be able to connect these sensors to cloud network, such as AWS IoT, Azure IoT, Google IoT, and OEM IoT platforms, and extract data from the cloud to your devices. As you progress through the chapters, you’ll gain hands-on experience in using open source Node-Red, Kafka, Cassandra, and Python. You will also learn how to develop streaming and batch-based Machine Learning algorithms. By the end of this book, you will have mastered the features of Industry 4.0 and be able to build stronger, faster, and more reliable IoT infrastructure in your Industry.
Table of Contents (18 chapters)

Building I-IoT analytics

Identifying the right parameters and techniques is the most important part of building I-IoT analytics. In 1977, John Tukey wrote the book Exploratory Data Analysis. The following method is based on EDA and is applied to the new cloud DevOps requirements. The following are the steps that we need to accomplish:

Analytics development workflow

Step 0 – problem statement

The first step is to always define the scope of the problem, the constraint of the problem, and the expected behavior. Then, we should align the business expectation with the technical expectation. It is a good practice during this step to define the success of our analytics. For example, you might accept 50% false positive results...