Introduction: Squats Counter Using TensorFlow Lite and Tiny Motion Trainer

This ‘Arduino Nano 33 BLE Sense’ based Squats counter can count the number of Squats performed by an individual using the Accelerometer readings and TinyML based Machine learning model.

Supplies

Hardware:

  1. Arduino Nano 33 BLE Sense
  2. USB to Micro USB Type B Cable

Software:

  1. Arduino IDE
  2. Tensorflow Lite

Step 1: Demonstration

The Squats counter can detect squats by measuring the accelerometer readings and prints them on the Serial monitor.

The device is to be attached to the individual’s thigh and can be powered using a power bank or a battery.

Step 2: Things Used in This Project:

I am using this complementary Google IO kit from Sparkfun which includes the Arduino Nano 33 BLE Sense which is capable of running TinyML projects with ease.

Step 3: Getting Things Ready

1. Upload the tf4micro-motion-kit code to the Arduino Nano 33 BLE Sense

2. After uploading the code, open the (Tiny Motion Trainer Experiment) by Google and pair the Bluetooth device with the laptop.

Step 4: Select the Appropriate Settings for Training the Model

Step 5: Capture the Data Required to Train Your Model

Step 6: Train Your Model

Step 7: Test Your Model

Step 8: Download the Arduino Code and Upload It to the Arduino BLE Sense Board

Step 9: Test the Model by Using the Serial Monitor

Step 10: Final Touch

Update the code as per your requirements or use mine: BLE_Sense_Arduino_Code

Place the device on your thigh using a Hook and Loop fastener (Velcro tape)

Step 11: Done!

Be the First to Share

Recommendations

  • Fix It Speed Challenge

    Fix It Speed Challenge

  • Jewelry Challenge

    Jewelry Challenge

  • Raspberry Pi Contest

    Raspberry Pi Contest

Leave a Reply