Publications

2023

1. LADS

   EEG data for motor imagery brain-computer interface using low-cost equipment

   Gabriel Henrique de Souza , Gabriel Faria, Luciana Paixão Motta , and 2 more authors

   Latin American Data in Science, 2023

   Abs Bib

   EEG-based brain-computer interfaces (BCI) for motor imagery recognition can be used in many applications, including prosthesis control, post-stroke motor rehabilitation, communication, and videogames. Such BCIs usually need to be calibrated with EEG data before being used. The calibration can use data from either a single person, the same person who will use the equipment, or a group of different people. However, although BCIs are increasingly used in research and real-world problems, high equipment costs prevent their popularization in personal use applications. For this reason, there are many ongoing efforts to create more affordable BCI devices. Nevertheless, most public datasets for motor imagery EEG-BCIs still use expensive equipment. Therefore, our work presents a dataset for EEG-based motor imagery BCIs focused on personal use applications. Using a low-cost 16-electrode EEG OpenBCI Cyton+Daisy Biosensing Board, we recorded the brain signals of 6 subjects while they imagined the movements of their hands, resulting in a dataset containing 960 trials of left and right-hand motor imagery. This dataset can be used to calibrate BCIs using similar low-cost equipment as well as study the signals generated by such equipment.

   @article{desouza2023datapaper,
     title = {{EEG} data for motor imagery brain-computer interface using low-cost equipment},
     volume = {2},
     doi = {10.53805/lads.v2i2.49},
     number = {2},
     journal = {Latin American Data in Science},
     author = {de{ }Souza, Gabriel Henrique and Faria, Gabriel and Motta, Luciana Paixão and Bernardino, Heder Soares and Vieira, Alex Borges},
     year = {2023},
     pages = {67--73}
   }

2022

1. BRACIS

   Feature extraction for a genetic programming-based brain-computer interface

   Gabriel Henrique de Souza , Gabriel Faria, Luciana Paixão Motta , and 2 more authors

   In Intelligent Systems , 2022

   Abs Bib

   Brain-Computer Interfaces (BCI) open a two-way communication channel between a computer and the brain: while the brain can control the computer, the computer can induce changes in the brain through feedback. This mechanism is used in post-stroke motor rehabilitation, in which a BCI provides feedback by classifying signals collected from a patient’s brain. Single Feature Genetic Programming (SFGP) can create classifiers for these signals. However, the Genetic Programming (GP) step in SFGP requires a set of extracted features to generate its model. To the best of our knowledge, the LogPower function is the only initial feature extraction function used in SFGP. Nevertheless, other functions can improve the quality of the generated classifiers. Thus, we analyze new initial feature extraction functions for GP in SFGP. We test the Common Spatial Patterns, Nonlinear Energy, Average Power Spectral Density, and Curve Length methods on two datasets suitable for post-stroke rehabilitation training. The results obtained show that the analyzed functions outperform LogPower in all our experiments, with a kappa value up to 25.20% better. We further test the proposed methods on a third dataset, created with low-cost equipment. In this case, we show that the Average Power Spectral Density function outperforms LogPower by 11.39% when three electrodes are used. Thus, we demonstrate that the new approach can be used with low-cost equipment and a small number of electrodes, reducing the financial costs of treatment and improving patients’ comfort.

   @inproceedings{desouza2022sfgp,
     author = {de{ }Souza, Gabriel Henrique and Faria, Gabriel and Motta, Luciana Paix{\~a}o and Bernardino, Heder Soares and Vieira, Alex Borges},
     editor = {Xavier-Junior, Jo{\~a}o Carlos and Rios, Ricardo Ara{\'u}jo},
     title = {Feature extraction for a genetic programming-based brain-computer interface},
     booktitle = {Intelligent Systems},
     year = {2022},
     publisher = {Springer International Publishing},
     address = {Cham},
     pages = {135--149},
     isbn = {978-3-031-21686-2}
   }

2. IJCNN

   Analyzing data augmentation methods for convolutional neural network-based brain-computer interfaces

   Gabriel Faria, Gabriel Henrique de Souza , Heder Soares Bernardino , and 2 more authors

   In International Joint Conference on Neural Networks (IJCNN) , 2022

   Abs Bib

   Brain-computer interfaces (BCI) are systems that use brain signals to communicate with and control devices, with applications ranging over multiple domains. In healthcare, one of the major applications of BCIs is neurorehabilitation. For example, BCIs help stroke patients recover motor abilities by providing sensory feedback based on imagined movement. Convolutional neural networks (CNN) can be used to classify such motor imagery electroencephalogram (EEG) signals and provide this kind of feedback. However, since these signals are usually noisy and can differ significantly over time and among people, it is frequently necessary to collect a large amount of data to train these models. This process can be time-consuming and fatiguing for the user, impairing the quality of neurorehabilitation treatments and other applications. This paper investigates how data augmentation can mitigate this problem by reducing the need for data and increasing feedback accuracy. We analyze five data augmentation methods from the literature on two motor imagery datasets. We apply data augmentation to a few-parameter CNN in varying settings of EEG electrodes, motor imagery tasks, and number of training samples. Our results show that data augmentation can reduce the amount of original data needed, leading to superior accuracy with 33.33% fewer training samples in some instances. They also show that combining different data augmentation methods can further improve accuracy.

   @inproceedings{faria2022augmentation,
     author = {Faria, Gabriel and de{ }Souza, Gabriel Henrique and Bernardino, Heder Soares and Motta, Luciana and Vieira, Alex Borges},
     booktitle = {International Joint Conference on Neural Networks (IJCNN)},
     title = {Analyzing data augmentation methods for convolutional neural network-based brain-computer interfaces},
     year = {2022},
     pages = {1--8},
     doi = {10.1109/IJCNN55064.2022.9891891}
   }