GPU Implementation of the Improved CEEMDAN Algorithm for Fast and Efficient EEG Time–Frequency Analysis

Abstract

Time–frequency analysis of EEG data is a key step in exploring the internal activities of the human brain. Studying oscillations is an important part of the analysis, as they are thought to provide the underlying mechanism for communication between neural assemblies. Traditional methods of analysis, such as Short-Time FFT and Wavelet Transforms, are not ideal for this task due to the time–frequency uncertainty principle and their reliance on predefined basis functions. Empirical Mode Decomposition and its variants are more suited to this task as they are able to extract the instantaneous frequency and phase information but are too time consuming for practical use. Our aim was to design and develop a massively parallel and performance-optimized GPU implementation of the Improved Complete Ensemble EMD with the Adaptive Noise (CEEMDAN) algorithm that significantly reduces the computational time (from hours to seconds) of such analysis. The resulting GPU program, which is publicly available, was validated against a MATLAB reference implementation and reached over a 260× speedup for actual EEG measurement data, and provided predicted speedups in the range of 3000–8300× for longer measurements when sufficient memory was available. The significance of our research is that this implementation can enable researchers to perform EMD-based EEG analysis routinely, even for high-density EEG measurements. The program is suitable for execution on desktop, cloud, and supercomputer systems and can be the starting point for future large-scale multi-GPU implementations.

DEMA: A Deep Learning-Enabled Model for Non-Invasive Human Vital Signs Monitoring Based on Optical Fiber Sensing

“…After the heartbeat interval sequence has been preprocessed, data points that fall within a five-minute window are considered a sample, and the characteristics of the sample data in the frequency and temporal domains are retrieved. To reduce the total forward and backward prediction error power, the order of the autoregressive (AR) model is set at 16 using mathematical statistics techniques [26]. To estimate the power spectrum and get the AR coefficient, Levenson Durbin recursion is used.…”