sleep-apnea

KO | EN

gitlite — search

#javascript #python #hacktoberfest #typescript #llm #go #rust #macos #nodejs #awesome #pytorch #security #openai #open-source

(★ 23)

Convolutional neural network which uses 30 second single-channel EEG signals to detect apnea events. Kernels are visualised using Fourier transforms.

sleep-apnea 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# sleep-apnea

Two models:
- A convolutional neural network (CNN) which takes as input 30-second single-channel EEG signals and produces as output a sleep apnea classification.
- A CNN trained on the same data which classifies sleep stage. Possible classifications are N1, N2, N3, REM, and W (awake).

Both models include implementation, validation, and an example trained model.

### Requirements

- Python 3.5-3.8 (you can use [pyenv](https://github.com/pyenv/pyenv) to manage different python versions).
- Training data from [Physionet](https://physionet.org/content/slpdb/1.0.0/).
- This project doesn't run easily on the M1 Macbook due to TensorFlow incompatibilities

### Setup

This project is best set up in a virtual environment to isolate package and language versions.

In the terminal, navigate into the project directory and create a new virtual environment using a compatible (3.5-3.8) version of Python:

```
python3.8 -m venv env
```

Activate virtual environment:

```
source env/bin/activate
```

Install required packages:

```
python -m pip install -r requirements.txt
```

You also need wget if you want to automate the downloading of Physionet data:

```
brew install wget
```

You're all set! Run `python3 -m src.sleepapnea.getdata` to retrieve and preprocess physionet data, and `python3 -m src.sleepapnea.modelarchitecture` to train your first model.

sleep-apnea

sleep-apnea 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

sleep-apnea

sleep-apnea 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README