Ensemble Voting-Based Multichannel EEG Classification in a Subject-Independent P300 Speller

Abstract

Classification of brain signal features is a crucial process for any brain–computer interface (BCI) device, including speller systems. The positive P300 component of visual event-related potentials (ERPs) used in BCI spellers has individual variations of amplitude and latency that further changse with brain abnormalities such as amyotrophic lateral sclerosis (ALS). This leads to the necessity for the users to train the speller themselves, which is a very time-consuming procedure. To achieve subject-independence in a P300 speller, ensemble classifiers are proposed based on classical machine learning models, such as the support vector machine (SVM), linear discriminant analysis (LDA), k-nearest neighbors (kNN), and the convolutional neural network (CNN). The proposed voters were trained on healthy subjects’ data using a generic training approach. Different combinations of electroencephalography (EEG) channels were used for the experiments presented, resulting in single-channel, four-channel, and eight-channel classification. ALS patients’ data represented robust results, achieving more than 90% accuracy when using an ensemble of LDA, kNN, and SVM on four active EEG channels data in the occipital area of the brain. The results provided by the proposed ensemble voting models were on average about 5% more accurate than the results provided by the standalone classifiers. The proposed ensemble models could also outperform boosting algorithms in terms of computational complexity or accuracy. The proposed methodology shows the ability to be subject-independent, which means that the system trained on healthy subjects can be efficiently used for ALS patients. Applying this methodology for online speller systems removes the necessity to retrain the P300 speller.

Enhancing P300-Based Brain-Computer Interfaces with Hybrid Transfer Learning: A Data Alignment and Fine-Tuning Approach

“…To evaluate the effectiveness of our method, we utilize two state-of-the-art P300 speller-based datasets. This is because P300-based event-related potentials are subject-dependent [39,40] and are commonly used in neuromuscular patient studies [6,41,42]. Therefore, reducing calibration time is a crucial factor in these cases, and our approach offers practical implications for the development and application of P300 speller-based BCI systems.…”

Bridging the BCI illiteracy gap: a subject-to-subject semantic style transfer for EEG-based motor imagery classification

“…Soft voting has been demonstrated to yield better performance and results than hard voting since it utilizes an average of probabilities (Saqlain et al, 2019 ). As such, soft voting has been widely used in many BCI studies due to its potential to improve the classification performance (Mussabayeva et al, 2021 ; Tasnim et al, 2022 ; Mehtiyev et al, 2023 ). In addition, soft voting-based ensembles are effective in compensating for the weaknesses of individual classifiers and can achieve even better performance when combining classifiers trained on different features.…”