tinyML device monitors packages for damage in transit
tinyML device monitors packages for damage in transit
Arduino Team – September 10, 2022
![](https://blog.arduino.cc/wp-content/uploads /2022/09/spaces-EJB5OaeYjM5VSFEKLEFz-uploads-git-blob-e1569bdbc3ad13b71bc36f15921c84134cc4e854-IMG_1756-1024x683.jpg)
While the advent of large-scale online shopping has been a great convenience, it has also led to a sharp increase in the number of returned items. This can be attributed to a number of factors, but shipping damage is a big contributor to this problem. Shebin Jose Jacob's solution involves creating a small tracker that accompanies the package on its journey and sends alerts when mishandling is detected.
Jacob started by creating a new Edge Impulse project and collecting about 30 minutes of motion samples from an Arduino Nano 33 BLE Sense's built-in three-axis accelerometer. Each sample was classified into one of five categories ranging from no movement to a hard drop or a vigorous jolt. The features were then generated and used to train a Keras model, which yielded 91.3% accuracy in testing.
![](https://blog.arduino.cc/wp-content/uploads /2022/09/spaces-EJB5OaeYjM5VSFEKLEFz-uploads-git-blob-f2e9947f0aaa26a421c20e05ea78c05648baed88-IMG_1751-1-1024x683.jpg)
![](https://blog.arduino.cc/wp-content/uploads /2022/09/spaces-EJB5OaeYjM5VSFEKLEFz-uploads-git-blob-816823811ebf9f5196e73e8c813fbf0b04ddd71d-Interface-1024x608.png)
More details can be found here in Jacob's project description.
![tinyML device monitors packages for damage in transit](https://blog.arduino.cc/wp-content/uploads/2022/09/spaces-EJB5OaeYjM5VSFEKLEFz-uploads-git-blob-e1569bdbc3ad13b71bc36f15921c84134cc4e854-IMG_1756.jpg)
Arduino Team – September 10, 2022
![](https://blog.arduino.cc/wp-content/uploads /2022/09/spaces-EJB5OaeYjM5VSFEKLEFz-uploads-git-blob-e1569bdbc3ad13b71bc36f15921c84134cc4e854-IMG_1756-1024x683.jpg)
While the advent of large-scale online shopping has been a great convenience, it has also led to a sharp increase in the number of returned items. This can be attributed to a number of factors, but shipping damage is a big contributor to this problem. Shebin Jose Jacob's solution involves creating a small tracker that accompanies the package on its journey and sends alerts when mishandling is detected.
Jacob started by creating a new Edge Impulse project and collecting about 30 minutes of motion samples from an Arduino Nano 33 BLE Sense's built-in three-axis accelerometer. Each sample was classified into one of five categories ranging from no movement to a hard drop or a vigorous jolt. The features were then generated and used to train a Keras model, which yielded 91.3% accuracy in testing.
![](https://blog.arduino.cc/wp-content/uploads /2022/09/spaces-EJB5OaeYjM5VSFEKLEFz-uploads-git-blob-f2e9947f0aaa26a421c20e05ea78c05648baed88-IMG_1751-1-1024x683.jpg)
![](https://blog.arduino.cc/wp-content/uploads /2022/09/spaces-EJB5OaeYjM5VSFEKLEFz-uploads-git-blob-816823811ebf9f5196e73e8c813fbf0b04ddd71d-Interface-1024x608.png)
More details can be found here in Jacob's project description.
What's Your Reaction?
![like](https://vidianews.com/assets/img/reactions/like.png)
![dislike](https://vidianews.com/assets/img/reactions/dislike.png)
![love](https://vidianews.com/assets/img/reactions/love.png)
![funny](https://vidianews.com/assets/img/reactions/funny.png)
![angry](https://vidianews.com/assets/img/reactions/angry.png)
![sad](https://vidianews.com/assets/img/reactions/sad.png)
![wow](https://vidianews.com/assets/img/reactions/wow.png)