Course Description
According to the Internet of Things Global Standards Initiative, IoT is defined as the network of physical objects or things embedded with electronics, software, sensors, and network connectivity, which enable these objects to collect and exchange data.
As a recent report by McKinsey pegs the potential economic impact of IoT at $11 trillion by 2025, the most important ingredient of the IoT boom is considered to be the data generated by the collection of sensors.
This course will first give an introduction to the concept of IoT and then provide students with the knowledge of how to handle the data deluge related to IoT. It’s geared towards engineers who would like to understand how to utilize the data generated by IoT technologies, or executives who would like to gain some insights to different applications this data can be used for.
What am I going to get from this course?
- Apply the fundamentals of machine learning and statistics to extract value from IoT data
- Understand different business use-cases for IoT data
- Understand different types of IoT data
Curriculum
Module 1: Intro to Analytics for the Internet of Things
19:37
Lecture 1
Intro to Analytics for the Internet of Things
19:37
This lecture will touch upon the common use cases in IoT, the type of data sensors generate & the analytical techniques used to generate insights from this data, and how to drive business value using analytics.
Module 2: Clustering
19:19
Lecture 2
Clustering
19:19
Clustering is one of the most commonly-used unsupervised learning methods. This lecture gives the audience some explanation of the most common algorithms in clustering, and solves some example problems.
Module 3: Decision Trees
16:28
Lecture 3
Decision Trees
16:28
The concept of decision trees is an integral part of the supervised learning domain. This module first gives an explanation of what a decision tree is, then gives some examples which this concept can be applied to.
Module 4: Random Forests
11:59
Lecture 4
Random Forests
11:59
This is an introductory lecture about the Random Forests method. It starts off with the basic theory behind the method, gives some explanation about the advantages/disadvantages the method has when compared to Decision Trees, and then dives deep into the algorithm with the help of some real life examples.
Module 5: Regression
19:35
Lecture 5
Regression
19:35
An overview of how simple multiple regression and multiple linear regression work, and how these two can be used on IoT data.
This lecture explains what SVD (Singular Value Decomposition) is, how to interpret it, and gives us an example by implementing the SVD method on a recommender system.
Module 7: Time Series Modeling for IoT Data
18:14
Lecture 7
Time Series Modeling for IoT Data
18:14
An overview of the three commonly used methods in time series modeling: Moving Averages, Exponential Smoothing and Holt-Winters Exponential smoothing, all backed by real-life examples.
