Data acquisition (DAQ)

Data acquisition (DAQ) · Course page

Collect sensor data that matches what the model needs: sampling rate, Nyquist, windows, the CSV schema, and recording the IMU and audio on one shared timeline.

Module goal

Collect trustworthy raw data, because a clean upstream is the first condition for an accurate model.

Lessons

Lesson	Topic	Time (min)	Slides
2.1	Sampling to match the model: rate, Nyquist, windows and the CSV schema	60	slides.md
2.2	Hands-on: a DAQ logger that saves a dataset to CSV	75	slides.md
2.3	Audio and several sensors on one timeline: PDM at 16 kHz, timestamps and jitter	60	slides.md
2.4	Hands-on: recording the IMU and audio into one file	75	slides.md

Lessons come in pairs: a concept lesson followed by a hands-on lesson with a practice file, a solution, and a lab.

Module checkpoint

You pass this module once you can do all of the following (details are in the Lab section of each hands-on lesson):

• A logger that genuinely saves N labelled samples to CSV, letting you choose the label, sampling at a steady rate, writing to a file on the board, and verifiable for the correct number of lines (lesson 2.2).
• A dataset logging at least two sensors on one shared timeline: the /multicapture.csv file has columns t_ms + IMU + db, with real values changing with motion and sound (lesson 2.4).