Are you ready to start using machine learning to develop a deeper understanding of your IoT data?
This course uses hands-on lab activities to guide students through a series of machine learning implementations that are common for IoT scenarios, such as predictive maintenance. After completing this course, students will be able to implement predictive analytics using their IoT data.
The course is divided into four modules that cover the following topic areas:
- Machine learning for IoT
- Data preparation techniques
- Predictive maintenance modeling
- Fault prediction modeling
This course is completely lab-based. There are no lectures or required reading sections. All of the learning content that you will need is embedded directly into the labs, right where and when you need it. Introductions to tools and technologies, references to additional content, video demonstrations, and code explanations are all built into the labs.
Some assessment questions will be presented during the labs. These questions will help you to prepare for the final assessment.
The course includes four modules, each of which contains two or more lab activities. The lab outline is provided below.
Module 1: Introduction to Machine Learning for IoT
- Lab 1: Examining Machine Learning for IoT
- Lab 2: Getting Started with Azure Machine Learning
- Lab 3: Exploring Code-First Machine Learning with Python
Module 2: Data Preparation for Predictive Maintenance Modeling
- Lab 1: Exploring IoT Data with Python
- Lab 2: Cleaning and Standardizing IoT Data
- Lab 3: Applying Advanced Data Exploration Techniques
Module 3: Feature Engineering for Predictive Maintenance Modeling
- Lab 1: Exploring Feature Engineering
- Lab 2: Applying Feature Selection Techniques
Module 4: Fault Prediction
- Lab 1: Training a Predictive Model
- Lab 2: Analyzing Model Performance
Chris Howd and Sheila Shahpari