Stress-Detection-From-Wearables

Repository of the 'stress detection from wearables'-task for the module 'Big Data Praktikum'. The task is to detect the stress level of a person based on the data of the wearable sensors (e.g. heart rate, accelerometer, etc.). To be more specific we are looking for commercial wearables as smartwatches.

The WESAD-Dataset is used to train and evaluate the model.

We trained two different models to detect the stress level on the WESAD dataset:

• A CNN-model based on the work of Gil-Martin et al. Human Stress Detection with Wearable Sensors Using Convolutional Neural Networks
• A LDA-classifier based on the work of Siirtola Continuous stress detection using the sensors of commercial smartwatch

Setup

1. Install the required Python packages using:

   pip install -r requirements.txt

2. Download the dataset here and save the WESAD directory inside the data directory.

3. To train the CNN-model follow the notebook for the CNN-model.