On the Use of GPU Computing for Accelerating EEG Preprocessing

Electroencephalography (EEG) records have multiple applications in Medicine, such as epilepsy seizure detection. Massive datasets with EEG signals are also used for training Machine Learning models. However, these data are usually stored in large files in a complex format called EDF, and processing this kind of file can be extremely computationally demanding. This study describes a novel approach combining a high-speed EDF file reader library developed in C++ with accelerated Fast Fourier Transform (FFT) on GPUs. It enhances the computational efficiency of working with this kind of file and outperforms the existing solutions for this purpose. Besides, the integrated FFT processing capabilities allow for simplifying EDF data and selecting sampling frequencies efficiently. These combined enhancements improve data handling and processing by reducing file reading time by approximately 30 times, compressing data by up to 99%, and accelerating preprocessing times for large files by hundreds of times when using the GPU.