▶What You Will Learn
- Discover the key concepts and architectures used with edge analytics
- Understand how to use long-distance communication protocols for edge analytics
- Deploy Microsoft Azure IoT Edge to a Raspberry Pi
- Create Node-RED dashboards with MQTT and Text to Speech (TTS)
- Use MicroPython for developing edge analytics apps
- Explore various machine learning techniques and discover how machine learning is related to edge analytics
- Use camera and vision recognition algorithms on the sensory side to design an edge analytics app
- Monitor and audit edge analytics apps
▶Key Features
- Become well-versed with best practices for implementing automated analytical computations
- Discover real-world examples to extend cloud intelligence
- Develop your skills by understanding edge analytics and applying it to research activities
▶Who This Book Is For
If you are a data analyst, data architect, or data scientist who is interested in learning and practicing advanced automated analytical computations, then this book is for you. You will also find this book useful if you're looking to learn edge analytics from scratch. Basic knowledge of data analytics concepts is assumed to get the most out of this book.
▶What this book covers
- Chapter 1, Introduction to Edge Analytics, outlines how everything old is new again! The rise of the personal computer in the 1980s and 1990s led to a revolution in computing. Instead of so-called dumb terminals connected to a large computer, many computers were connected in a network spreading the processing power around. Edge analytics is like the personal computer revolution but for Internet-of-Things (IoT) devices. We will start this chapter by comparing edge analytics to the computer revolution before we discuss the advantages of using edge analytics in an IoT application. We will both look at the basic edge analytics architecture and introduce the Microsoft Azure IoT Edge platform.
- Chapter 2, How Does IoT Edge Analytics Work?, discusses the components used in an edge analytics application and how they fit together. Now that we understand what edge analytics is, let's turn our attention to how it works. In this chapter, we will conclude by looking at real-world edge analytics applications.
- Chapter 3, Communications Protocols Used in Edge Analytics, outlines how one part of an IoT or edge analytics application is the connection to the internet. The other part is the connection from our edge device to the sensors. In this chapter, we will explore ways by which we can connect our edge device to the internet. We will look at some of the longdistance technologies, as well as the familiar Wi-Fi protocol. In our exploration of Wi-Fi, we will gain an understanding as to the radio frequency spectrum and where different communication protocols fit into this spectrum. We will also take a look at Bluetooth and consider how we may use it in our applications.
- Chapter 4, Working with Microsoft Azure IoT Hub, is the beginning of our work with Azure IoT services using Microsoft Azure, after Chapter 1, Introduction to Edge Analytics, where we touched on Azure IoT Edge and Azure IoT. The lessons learned from this will provide a good basis for using the Raspberry Pi with Azure IoT Edge.
- Chapter 5, Using the Raspberry Pi with Azure IoT Edge, builds on what we covered in Chapter 4, Working with Microsoft Azure IoT Hub, where we learned a bit about Microsoft Azure and the IoT Hub in Azure. This background is essential to understanding Azure IoT Edge. In this chapter, we will learn how to install Azure IoT Edge on the Raspberry Pi and read data from it using the Microsoft Device Explorer.
- Chapter 6, Using MicroPython for Edge Analytics, covers MicroPython as a subset of Python 3. MicroPython was developed as a programming language for microcontrollers. With microcontrollers getting more and more powerful, learning MicroPython is becoming more essential. Imagine having the ability to take your Python knowledge and apply it to the physical world. Imagine building lightweight, energy-efficient, and powerful edge analytics applications with all the advantages of using the Python programming language. With MicroPython, you can.
- Chapter 7, Machine Learning and Edge Analytics, considers one of the most exciting fields in the realm of technology today—machine learning. As this technology matures and gets into the hands of more and more people, exciting new applications are created, such as a tool for detecting respiratory diseases based on audio analysis of breathing patterns. By combining edge analytics with machine learning, the capabilities on the sensory side are vast. This, combined with the ever-increasing power of microcontrollers and single-board computers such as the Raspberry Pi, means that the future looks very bright indeed for edge analytics and machine learning. In this chapter, we will explore the advantages of machine learning at the edge with a Raspberry Pi as we write a program to distinguish between the face of a person and the face of a dog. We will then jump into the exciting new world of Artificial Intelligence of Things (AIoT) as we take a small microcontroller and turn it into a QR code decoder tool.
- Chapter 8, Designing a Smart Doorbell with Visual Recognition, remembers how years ago, the only way to recognize who was knocking at your door without being too obvious was to peer through a little peephole near the top of the door. Observant visitors would notice the light disappear from the peephole once a face was pressed up against it on the other side. So, in other words, we really weren't fooling anyone into thinking we weren’t home if we decided that the visitor was not worthy of us opening the door. Times have certainly changed. We have the technology now to filter unwanted visitors for us without being detected. Using a camera and vision recognition algorithms on the sensory side, we will design an edge analytics application that alerts us to who is at the door.
- Chapter 9, Security and Privacy in an Edge Analytics World, covers how, when deploying an application to the internet, the risks posed by cybercriminals should be taken very seriously. Internet-enabled devices including edge computers are prone to cyber-attacks where they may be used to shut down websites or cause havoc on the internet, not to mention the destruction of our networked applications. In this chapter, we will cover security and in turn, privacy, when it comes to our edge analytics applications.
- Chapter 10, What Next?, examines where we are at the end of our edge analytics journey. I hope you enjoyed the ride. Tell them what you are going to tell them, tell them, and then tell them what you just told them—those are the great words of wisdom given to me by the more seasoned speakers at my Toastmasters club. In this chapter, we will recap what we have learned and then look ahead to the future of edge analytics.
