Transforming EEG Signals into Images for Motor Imagery Classification Using a YOLO11-Based Model

Brain–Computer Interface (BCI) systems allow communication between the brain and some kind of external device, which can be used for assistive technologies, smart living environments, and health care. One of the main challenges in these systems is the detection and processing of electrodes (EEG) signals, especially those that pertain to Motor Imagery (MI) and the classification of those signals, due to the complexity and variability of the raw EEG data. The current study proposes a new method for the classification of MI-EEG signals. The method consists of converting EEG signals into RGB images and then applying the images to the classification algorithm based on the segmentation neural network (YOLO11-L-cls). This

method was thoroughly tested on the BCI Competition IV Dataset 2b (BCICIV2b) and Dataset III, both of which the researchers of this work ensured adhered to the subject-independent evaluation methodology. The results for the proposed method framework were quite positive, resulting in a classification accuracy of 99% for BCICIV2b and 97.5% for Dataset III. The classification accuracy of the proposed method framework was compared to some of the traditional machine learning methods such as Random Forest (RF) and Linear Discriminant Analysis (LDA) and even with some deep learning methods such as Convolutional Neural Networks (CNNs) classification methods, demonstrating the effectiveness and robustness of the proposed method of combining EEG-to-image with

the classification approach using YOLO11 for motor imagery classification tasks.

Message: Hi FE, I need help with “Transforming EEG Signals into Images for Motor Imagery Classification Using a YOLO11-Based Model” in “Biotechnology & Biomedical Engineering”