-
About this course
- Class Overview
-
Syllabus & Downloads
-
Introduction 1 min
-
Class Abstract 1 min
-
Class Objectives 1 min
-
Class Agenda 1 min
-
Limitations of Traditional Techniques 8 min
-
Wavelet Transform 1 min
-
Wavelet Theory 14 min
-
What is a Wavelet? 10 min
-
Wavelet Transform Example 5 min
-
Uncertainty Principle 5 min
-
Continuous Wavelet Transform Example: ECG 2 min
-
Discussion on Applying Wavelets to ECG Signals 3 min
-
When to Use Wavelets 3 min
-
Discussion on Usage of Wavelets 4 min
-
Empirical Mode Decomposition (EMD) 1 min
-
What is Empirical Mode Decomposition 7 min
-
Discussion on EMD Method 5 min
-
Real-World Example: ECG 1 min
-
Discussion on ECG Example 3 min
-
Real-World Example: Motor Vibration 1 min
-
Discussion on Motor Vibration 1 min
-
Denoising Example: ECG Signal 3 min
-
When to Use EMD 2 min
-
Implementation in Embedded Systems 1 min
-
Class Summary 1 min
-
References and Resources 1 min
-
Example Datasets 1 min
- Complete Recording
-
25081 SENS5 (80 min)
- Feedback and Discussion
-
Get in contact with the presentation team
-
We need your feedback
This video is still being processed. Please check back later and refresh the page.
Uh oh! Something went wrong, please try again.
25081 SENS5: Emerging Techniques in Sensor Data Analysis (August 2025)
This class addresses the limitations of traditional sensor signal processing in machine learning applications.
This class addresses the limitations of traditional sensor signal processing in machine learning applications. You will select emerging techniques for your applications, apply these techniques on your sensor data for feature extraction, and identify pathways to incorporating these techniques into your embedded systems.
Prerequisites:
Before taking this class, it is recommended that you are familiar with the Fourier Transform and time-series digital signal filtering.