Data is now a huge part of many sports, from F1 racing to football. Presenting that data to fans is secondary to the real purpose: helping teams and athletes maximize performance. No matter what sport you enjoy, you can benefit from that kind of quantified training. Manivannan proved that by building his Smart AI Boxing Band based on the Arduino Nesso N1.

Launched last November, the Nesso N1 is a high-performance development board with a built-in full-color touchscreen, rechargeable battery, and host of sensors. In many cases, you can accomplish your goal without any other hardware at all. In this case, Manivannan was almost able to pull that off, he just needed one other component: a pulse sensor.

That pulse sensor was necessary because Manivannan’s wearable tracks user biometrics alongside physical movement. It shifts the color of the Nesso N1 display according to heartbeat for monitoring intensity levels without breaking rhythm, while also delivering live analytics directly on the device. The band can, for example, tell a wearer how performing an uppercut correlates with their heart rate. Or a boxer might like to know that they start favoring jabs once they’re tired.

For that to be possible, the Nesso N1 needs to recognize various types of punches. Manivannan used Edge Impulse for that, training it on data from the Nesso N1’s built-in IMU. After training, it was able to very reliably differentiate between hooks, jabs, uppercuts, and the ideal time between them. It can then log those events along with biometric data for post-training (or post-bout) analysis.

The Smart AI Boxing Band is a compact tool that helps boxers understand their technique, pace their rounds, and push harder with real-time feedback. More details on the project are available in Manivannan’s write-up.