Slow Cortical Potential BCI Classification Using Sparse Variational Bayesian Logistic Regression with Automatic Relevance Determination

Abstract

Detecting P300 slow-cortical ERPs poses a considerable challenge in signal processing due to the complex and non-stationary characteristics of a single-trial EEG signal. EEG-based neurofeedback training is a possible strategy to improve the social abilities in Autism-Spectrum Disorder (ASD) subjects. This paper presents a BCI P300 ERPs based protocol optimization used for the enhancement of joint-attention skills in ASD subjects, using a robust logistic regression with Automatic Relevance Determination based on full Variational Bayesian inference (VB-ARD). The performance of the proposed approach was investigated utilizing the IFMBE 2019 Scientific Challenge Competition dataset, which consisted of 15 ASD subjects who underwent a total of 7 BCI sessions spread over 4 months. The results showed that the proposed VB-ARD approach eliminates irrelevant channels and features effectively, producing a robust sparse model with 81.5 ± 0.12 % accuracy in relatively short modeling computational time 19.3 ± 1.4 sec, and it outperforms the standard regularized logistic regression in terms of accuracy and speed needed to produce the BCI model. This paper demonstrated the effectiveness of the probabilistic approach using Bayesian inference for the production of a robust BCI model. Considering the good classification accuracy over sessions and fast modeling time the proposed method could be a useful tool used for the BCI based protocol for the improvement of joint-attention ability in ASD subjects.

BCIAUT-P300: A Multi-Session and Multi-Subject Benchmark Dataset on Autism for P300-Based Brain-Computer-Interfaces

“…ID-6 : AM, Miloš Ajćević, Giulia Silveri, Gaia Ciacchi, Giulietta Morra, Joanna Jarmolowska, Piero Paolo Battaglini and Agostino Accardo ( Miladinović et al, 2020 ).…”

“…• ID-1: DB, Silvia Fantozzi and Elisa Magosso (Borra et al, 2020a • ID-5: DK, Sebastian Michelmann, Matthias Treder and Lorena Santamaria (Krzemiński et al, 2020). • ID-6: AM, Miloš Ajćević, Giulia Silveri, Gaia Ciacchi, Giulietta Morra, Joanna Jarmolowska, Piero Paolo Battaglini and Agostino Accardo (Miladinović et al, 2020). • ID-7: Bipra Chatterjee, Ramaswamy Palaniappan and Cota Navin Gupta (Chatterjee et al, 2020).…”

A Big-Data Variational Bayesian Framework for Supporting the Prediction of Functional Outcomes in Wake-Up Stroke Patients

“…Currently, there is no study on clinical features and models to predict functional outcome measured by mRS in thrombolysis treated WUS patients. Bayesian techniques are becoming very popular in the field of data analysis in medicine [ 37 – 39 ]. In this preliminary study we proposed a method based on Bayesian inference for functional outcome prediction in terms of mRS in WUS as a challenging subtype of stroke.…”

Transfer Learning improves MI BCI models classification accuracy in Parkinson's disease patients

“…Among many other applications, MI BCI technology may be used for neurorehabilitation. Indeed, it has been shown to positively affect motor execution, cognitive capabilities, and coordination, in healthy individuals, as well as in patients, such as post-Stroke patients, Parkinson's disease and Autism spectrum disorders [1]- [3]. Furthermore, since no peripherals (muscles and nerves) are involved, it can be applied in assistive technologies for paralyzed patients both for rehabilitation and as and for communication.…”