Applying Dimensionality Reduction as Precursor to LSTM-CNN Models for Classifying Imagery and Motor Signals in ECoG-Based BCIs
This work addresses motor dysfunction rehabilitation through BCIs, but appears incremental as it combines existing dimensionality reduction and deep learning techniques.
The researchers tackled the problem of optimizing motor imagery classification in Brain-Computer Interfaces (BCIs) for motor rehabilitation by applying UMAP dimensionality reduction as a preprocessing step before LSTM-CNN models, finding that participants with high KNN scores after UMAP also achieved high accuracy in supervised deep learning models.
Motor impairments, frequently caused by neurological incidents like strokes or traumatic brain injuries, present substantial obstacles in rehabilitation therapy. This research aims to elevate the field by optimizing motor imagery classification algorithms within Brain-Computer Interfaces (BCIs). By improving the efficiency of BCIs, we offer a novel approach that holds significant promise for enhancing motor rehabilitation outcomes. Utilizing unsupervised techniques for dimensionality reduction, namely Uniform Manifold Approximation and Projection (UMAP) coupled with K-Nearest Neighbors (KNN), we evaluate the necessity of employing supervised methods such as Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNNs) for classification tasks. Importantly, participants who exhibited high KNN scores following UMAP dimensionality reduction also achieved high accuracy in supervised deep learning (DL) models. Due to individualized model requirements and massive neural training data, dimensionality reduction becomes an effective preprocessing step that minimizes the need for extensive data labeling and supervised deep learning techniques. This approach has significant implications not only for targeted therapies in motor dysfunction but also for addressing regulatory, safety, and reliability concerns in the rapidly evolving BCI field.