EI-Demos / Package in Transit Health (Sensor)
This is the finished Edge Impulse project for the tutorial 'Continuous motion recognition'. From here you can acquire new training data, design impulses and train models.
About this project
Understand if your sensitive packages were not handled with TLC
This project demonstrates how to use the 3-axis accelerometer to classify whether a package had been dropped or violently shaken during its shipment.
You can also follow our tutorial to guide you through building your continuous motion recognition model, from data collection to deployment on embedded devices.
Sensor & Block Information
- Accelerometer data (.cbor files) @ 62.5 Hz
- Spectral Features DSP block for time-based sensor data
- Neural Network Classifier with prediction outputs: "dropped", "idle", "violent_shaking"
- Anomaly Detection block for anomaly score output of unknown motions (motions the model was not trained on)
Download block output
Title | Type | Size | |
---|---|---|---|
Spectral features training data | NPY file | 4510 windows | |
Spectral features training labels | NPY file | 4510 windows | |
Spectral features testing data | NPY file | 59 windows | |
Spectral features testing labels | NPY file | 59 windows | |
NN Classifier model | TensorFlow Lite (float32) | 5 KB | |
NN Classifier model | TensorFlow Lite (int8 quantized) | 3 KB | |
NN Classifier model | TensorFlow SavedModel | 11 KB | |
NN Classifier model | Keras h5 model | 5 KB | |
Anomaly detection model | JSON | 7 KB |
Clone project
You are viewing a public Edge Impulse project. Clone this project to add data or make changes.
Run this model
Scan QR code or launch in browser
Summary
Data collected
9m 41sProject info
Project ID | 87707 |
Project version | 2 |
License | Apache 2.0 |