Edge Impulse Experts / cough-monitor-audio (Created by Eivind Holt)
This is your Edge Impulse project. From here you acquire new training data, design impulses and train models.
About this project
Impulse project for counting coughs for monitoring progress in treatment of lung diseases (e.g. COPD, asthma). Trained on one healthy person for demonstration purposes only. Example of public crowd-sourced datasets: https://www.kaggle.com/datasets/himanshu007121/coughclassifier-trial
Creating your first impulse (100% complete)
Acquire data
Every Machine Learning project starts with data. You can capture data from a development board or your phone, or import data you already collected.
Design an impulse
Teach the model to interpret previously unseen data, based on historical data. Use this to categorize new data, or to find anomalies in sensor readings.
Deploy
Package the complete impulse up, from signal processing code to trained model, and deploy it on your device. This ensures that the impulse runs with low latency and without requiring a network connection.
Download block output
| Title | Type | Size | |
|---|---|---|---|
| Spectrogram training data | NPY file | 647 windows | |
| Spectrogram training labels | NPY file | 647 windows | |
| Spectrogram testing data | NPY file | 290 windows | |
| Spectrogram testing labels | NPY file | 290 windows | |
| NN Classifier model | TensorFlow Lite (float32) | 49 KB | |
| NN Classifier model | TensorFlow Lite (int8 quantized) | 19 KB | |
| NN Classifier model | TensorFlow SavedModel | 50 KB | |
| NN Classifier model | Keras h5 model | 45 KB |
Clone project
Summary
Data collected
7m 15sProject info
| Project ID | 105885 |
| Project version | 6 |
| License | No license attached |
|
|
