Application of the Stockwell Transform to Electroencephalographic Signal Analysis during Gait Cycle

Abstract

The analysis of electroencephalographic signals in frequency is usually not performed by transforms that can extract the instantaneous characteristics of the signal. However, the non-steady state nature of these low voltage electrical signals makes them suitable for this kind of analysis. In this paper a novel tool based on Stockwell transform is tested, and compared with techniques such as Hilbert-Huang transform and Fast Fourier Transform, for several healthy individuals and patients that suffer from lower limb disability. Methods are compared with the Weighted Discriminator, a recently developed comparison index. The tool developed can improve the rehabilitation process associated with lower limb exoskeletons with the help of a Brain-Machine Interface.

Prediction of gait intention from pre-movement EEG signals: a feasibility study

“…Another study reported in [23] achieved an accuracy of 72.91% with 71.81±11.48% true positive rate and 4.56 ±1.84 FP/ min for start detection and accuracy, TPR and FP/min of 80.65±11.49%, 57.38 ±12.03% and 2.10 ±1.20 for stop detection. In a more recent study [52], the accuracy, sensitivity and FP/min were reported as 78.61±11.20%, 76.90±11.75% and 3.52±1.82 for start detection and 84.36±10.19%, 68.68±14.69% and 2.06±1.12 for stop detection. It is to be noted though that these studies used a very large detection window of 4s containing data from two seconds before the starting and stopping event to two seconds after the occurrence of the event.…”

“…Thus, the recent technologies have shown promise to make possible innovations in experimental designs for a lot of BCI systems. In addition to that, traditional spatial filtering techniques including Laplacian filtering and common average referencing are also available as alternative [22,23,52]. These filters aim to minimize the contribution of the rest of the EEG electrodes to each channel thus better isolating the information from each of the electrodes.…”

“…This data segmentation procedure was inspired by similar approaches reported in [22,23,52] The resting and walking times were chosen by taking equidistant points from two adjacent gait starting and stopping times. After marking all crucial time points, data windows of different lengths, and relative positions corresponding to those events were taken for further processing and feature extraction.…”

Estudio preliminar de evaluación de la creatividad artística mediante el análisis de señales electroencefalográficas

“…Al contrario que en otras investigaciones previas realizadas [12,13], donde las señales se utilizan para generar un modelo independiente por sujeto de pruebas, esta investigación requiere de una comparación de los parámetros extraídos entre sujetos. Por ello, es necesario llevar a cabo una normalización que nos permita comparar en una misma escala los datos extraídos.…”

Analysis of the EEG Rhythms Based on the Empirical Mode Decomposition During Motor Imagery When Using a Lower-Limb Exoskeleton. A Case Study

“…In these paradigms, the extraction of features is usually accomplished by the filtering of the frequency bands, associated with the rhythms related to the brain activity being analyzed. Although the features are generally extracted using traditional signal processing filters, there are other alternatives in the literature based on time vs. frequency analysis techniques, such as the wavelet transform (Xu and Song, 2008 ; Yang et al, 2010 ; Kant et al, 2019 ) and the Stockwell transform (Ortiz et al, 2017 ). However, they have not been used in conjunction with an exoskeleton (He et al, 2018 ).…”