Chapter 1, Defining IoT Analytics and Challenges, defines, for the purposes of this book, what constitutes the Internet of Things. It will also define what is meant by the term Analytics when used in the book. The chapter will discuss special challenges that come with IoT data from the volume of data to issues with time and space that are not normally a concern with internal company data sets. The reader will have a good grasp of the scope of the book and the challenges that he or she will learn to overcome in the later chapters.
Chapter 2, IoT Devices and Networking Protocols, reviews in more depth the variety of IoT devices and networking protocols. The reader will learn the scope of device and example use cases, which will be discussed in easy-to-understand categories. The variety of networking protocols will be discussed along with the business need they are trying to solve. By the end of the chapter, the reader will understand the what and the why of the major categories of devices and networking protocol strategies. The reader will also start to learn how to identify characteristics of the device and network protocol from the resulting data.
Chapter 3, IoT Analytics for the Cloud, speaks about the advantages to cloud-based infrastructure for handling and analyzing IoT data. The reader will be introduced to cloud services, including AWS, Azure, and Thingworx. He or she will learn how to implement analytics elastically to enable a wide variety of capabilities.
Chapter 4, Creating an AWS Cloud Analytics Environment, provides a step-by-step walkthrough on creating an AWS environment. The environment is specifically geared towards analytics. Along with screenshots and instructions on setting it up, there will be explanation on what is being done and why.
Chapter 5, Collecting All That Data - Strategies and Techniques, speaks about strategies to collect IoT data in order to enable analytics. The reader will learn about tradeoffs between streaming and batch processing. He or she will also learn how to build in flexibility to allow future analytics to be integrated with data processing.
Chapter 6, Getting to Know Your Data - Exploring IoT Data, focuses on exploratory data analysis for IoT data. The reader will learn how to ask and answer questions of the data. Tableau and R examples will be covered. He or she will learn strategies for quickly understanding what the data represents and where to find likely value.
Chapter 7, Decorating Your Data - Adding External Datasets to Innovate, speaks about dramatically enhancing value by adding in additional datasets to IoT data. The datasets will be from internal and external sources. The reader will learn how to look for valuable datasets and combine them to enhance future analytics.
Chapter 8, Communicating with Others - Visualization and Dashboarding, talks about designing effective visualizations and dashboards for IoT data. The reader will learn how to take what they have learned about the data and convey it in an easy-to-understand way. The chapter covers both internal and customer-facing dashboards.
Chapter 9, Applying Geospatial Analytics to IoT Data, focuses on applying geospatial analytics to IoT data. IoT devices typically have a diverse geographic location when deployed and sometimes even move. This creates an opportunity to extract value by applying geospatial analytics. The reader will learn how to implement this for their IoT analytics.
Chapter 10, Data Science for IoT Analytics, describes data science techniques such as machine learning, deep learning, and forecasting using ARIMA on IoT data. The reader will learn the core concepts for each. They will understand how to implement machine learning methods and ARIMA forecasting on IoT data using R. Deep learning will be described along with a way to get started experimenting with it on AWS.
Chapter 11, Strategies to Organize Data for Analytics, focuses on organizing data to make it much easier for data scientists to extract value. It introduces the concept of Linked Analytical Datasets. The reader will learn how to balance maintainability with data scientist productivity.
Chapter 12, The Economics of IoT Analytics, talks about creating a business case for IoT analytics projects. It discusses ways to optimize the return on investment by minimizing costs and increasing opportunity for revenue streams. The reader will learn how to apply analytics to maximize value in the example case of predictive maintenance.
Chapter 13, Bringing It All Together, wraps up the book and reviews what the reader has learned. It includes some parting advice on how to get the most value out of Analytics for the Internet of Things.
