Monte Carlo dropout for uncertainty estimation and motor imagery classification
Motor Imagery (MI)-based Brain–Computer Interfaces (BCIs) have been widely used as an alternative communication channel to patients with severe motor disabilities, achieving high classification accuracy through machine learning techniques. Recently, deep learning techniques have spotlighted the stat...
- Autores:
-
milanés hermosilla, daily
Trujillo Codorniú, Rafael
López-Baracaldo, René
Sagaro Zamora, Roberto
Delisle-Rodriguez, Denis
Villarejo Mayor, John Jairo
Núñez Alvarez, José Ricardo
- Tipo de recurso:
- Article of journal
- Fecha de publicación:
- 2021
- Institución:
- Corporación Universidad de la Costa
- Repositorio:
- REDICUC - Repositorio CUC
- Idioma:
- eng
- OAI Identifier:
- oai:repositorio.cuc.edu.co:11323/8928
- Acceso en línea:
- https://hdl.handle.net/11323/8928
https://doi.org/10.3390/s21217241
https://repositorio.cuc.edu.co/
- Palabra clave:
- Brain–computer interfaces
Monte Carlo dropout
Motor imagery
Shallow convolutional neural network
Uncertainty estimation
- Rights
- openAccess
- License
- CC0 1.0 Universal
| Summary: | Motor Imagery (MI)-based Brain–Computer Interfaces (BCIs) have been widely used as an alternative communication channel to patients with severe motor disabilities, achieving high classification accuracy through machine learning techniques. Recently, deep learning techniques have spotlighted the state-of-the-art of MI-based BCIs. These techniques still lack strategies to quantify predictive uncertainty and may produce overconfident predictions. In this work, methods to enhance the performance of existing MI-based BCIs are proposed in order to obtain a more reliable system for real application scenarios. First, the Monte Carlo dropout (MCD) method is proposed on MI deep neural models to improve classification and provide uncertainty estimation. This approach was implemented using Shallow Convolutional Neural Network (SCNN-MCD) and with an ensemble model (E-SCNN-MCD). As another contribution, to discriminate MI task predictions of high uncertainty, a threshold approach is introduced and tested for both SCNN-MCD and E-SCNN-MCD approaches. The BCI Competition IV Databases 2a and 2b were used to evaluate the proposed methods for both subject-specific and non-subject-specific strategies, obtaining encouraging results for MI recognition. |
|---|