- We recommend ignoring the accelerometer data at first and only starting to incorporate it once you have a fully working algorithm based on PPG data alone. Our baseline algorithms achieved full points without the use of accelerometer data at all.
- Our testing indicates that the difficulty of accurate HR extraction varies by phase. You may find it helpful to first test your algorithm during periods when the PPG data quality is high.
- PPG HR detection is a well-understood problem and you will find many resources online to help you solve this problem. While we do not recommend you to re-invent the wheel, it is advisable to really understand methods if you plan on using them. Usually, this is a prerequisite to being able to tweak an algorithm for maximum performance.
- As a starting pointer, you may want to use some functionalities of the scipy package. More specifically, it provides functions for filtering the signal and the function find_peaks(), which can be helpful in detecting peaks in the PPG signal and offers a range of parameters to optimize. Please note: These are helping pointers for students with limited signal processing experience and not necessarily pointers toward an optimal solution.
- Plot, plot, plot, and then do some more plotting. Visualize everything you are doing - is it what you expect? Can you identify signal sections where your algorithm fails? Why? In signal processing and data analysis as a whole, plotting is key to success. Just assuming that something works is usually not a great strategy. The recordings are long and therefore interactive plots are recommended (with the option to zoom and move around). A possible method to do so locally on your computer is explained in the example notebook.