Random Convolutional Kernels for SSVEP Feature Extraction

Steady-State Visual Evoked Potentials (SSVEP) - IEEE SMC 2021

project_description
Explore the docs »

View Demo · Report Bug · Request Feature

About The Project
- Built With
Getting Started
- Prerequisites
- Installation
Usage
Roadmap
Contributing
License
Contact
Acknowledgements

About The Project

Abstract

During the hackathon we performed analysis on data of an SSVEP experiment. SSVEP stands for Steady State Visually Evoked Potentials and it is a response to visual stimulation. This stimulation is performed at specific frequencies. In this particular experiment, the task was to distinguish between four different frequencies. The data we received contained two different patients that performed two sessions of recording each. In each recording, 20 attempts were done, 5 for each frequency. Our approach can be divided in two steps. First, we applied pre-processing steps on the data, to clean them from unwanted frequencies. These resources can be found in the "Pre-Processing" folder. Secondly, the feature extraction and classification has been performed.

Built With

Getting Started

To get a local copy up and running follow these simple steps.

Prerequisites

This is an example of how to list things you need to use the software and how to install them.

npm
```
npm install npm@latest -g
```

Installation

Clone the repo

git clone https://github.com/github_username/repo_name.git

Install NPM packages
```
npm install
```

Usage

Preprocessing

The first steps require to clean the data from the unwanted frequencies. In particular, the preprocessing can be divided in the following steps:

High pass Temporal filtering: it gets rid of slow drifts;
Spatial filtering: we used Common Average Reference (CAR);
Indipendent component analysis (ICA);

After that we segmented the data in smaller epochs and divided into the different classes.

Feature Extraction

Classification

For more examples, please refer to the Documentation

Roadmap

See the open issues for a list of proposed features (and known issues).

Contributing

Contributions are what make the open source community such an amazing place to be learn, inspire, and create. Any contributions you make are greatly appreciated.