Decoding EEG rhythms offline and online during motor imagery for standing and sitting based on a brain-computer interface

Triana-Guzman, Nayid; Orjuela-Cañón, Álvaro David; Jutinico, Andrés L.; Mendoza-Montoya, Omar; Antelis, Javier M.

doi:10.3389/fninf.2022.961089

Cited by 7 publications

(9 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For the classification of lower-limb AM, Liu et al [40] proposed a study for the identification of ankle plantar flexion MI using 1.5 s time windows, a filter between 4-48Hz, and 32 EEG channels, obtaining an Acc of approximately 0.81. Whereas Triana-Guzman et al designed a system that managed to identify standing tasks, with Accs close to 0.90 [41]. On the other hand, both gait and gait have been involved in classification tasks, where an Acc above 0.80 have been reported by several authors [42,43].…”

Section: Discussionmentioning

confidence: 99%

Evaluation of temporal, spatial and spectral filtering in CSP-based methods for decoding pedaling-based motor tasks using EEG signals

Blanco-Díaz,

Guerrero-Mendez,

Delisle-Rodriguez

et al. 2024

Biomed. Phys. Eng. Express

View full text Add to dashboard Cite

Stroke is a neurological syndrome that usually causes a loss of voluntary control of lower/upper body movements, making it difficult for affected individuals to perform Activities of Daily Living (ADLs). Brain-Computer Interfaces (BCIs) combined with robotic systems, such as Motorized Mini Exercise Bikes (MMEB), have enabled the rehabilitation of people with disabilities by decoding their actions and executing a motor task. However, Electroencephalography (EEG)-based BCIs are affected by the presence of physiological and non-physiological artifacts. Thus, movement discrimination using EEG become challenging, even in pedaling tasks, which have not been well explored in the literature. In this study, Common Spatial Patterns (CSP)-based methods were proposed to classify pedaling motor tasks. To address this, Filter Bank Common Spatial Patterns (FBCSP) and Filter Bank Common Spatial-Spectral Patterns (FBCSSP) were implemented with different spatial filtering configurations by varying the time segment with different filter bank combinations for the three methods to decode pedaling tasks. An in-house EEG dataset during pedaling tasks was registered for 8 participants. As results, the best configuration corresponds to a filter bank with two filters (8–19 Hz and 19–30 Hz) using a time window between 1.5 and 2.5 s after the cue and implementing two spatial filters, which provide accuracy of approximately 0.81, False Positive Rates lower than 0.19, and \textit{Kappa} index of 0.61. This work implies that EEG oscillatory patterns during pedaling can be accurately classified using machine learning. Therefore, our method can be applied in the rehabilitation context, such as MMEB-based BCIs, in the future.

show abstract

Section: Discussionmentioning

confidence: 99%

Evaluation of temporal, spatial and spectral filtering in CSP-based methods for decoding pedaling-based motor tasks using EEG signals

Blanco-Díaz,

Guerrero-Mendez,

Delisle-Rodriguez

et al. 2024

Biomed. Phys. Eng. Express

View full text Add to dashboard Cite

show abstract

“…Our research group conducted a study that focused on the classification of tasks associated with brain activity from standing to sitting tasks using only MI signals (Triana-Guzman et al, 2022). That research used standard methods such as Common Spatial Patterns (CSP) based methods for the identification of MI experiments in the standing and sitting tasks in online and offline sessions with an accuracy above 80%.…”

Section: Discussionmentioning

confidence: 99%

“…For this, the Morlet Wavelet was used to calculate the power of the signals for the generated time-frequency representations configured with seven cycles and using the Hanning time window. The setup and use of Morlet Wavelets were implemented following previous recommendations in the literature to analyze the dynamic response of EEG signals (Pfurtscheller & Neuper, 2001;Qin & He, 2005;Triana-Guzman et al, 2022). The ERDS is presented as percentages, considering the relative power of the experiment with the baseline period.…”

Section: Event Related Desynchronization and Synchronization (Erds)mentioning

confidence: 99%

“…Ma et al, 2017). Currently, only a few studies have been conducted on sit-to-stand and stand-to-sit transitions (Chaisaen et al, 2020;Kanokwan et al, 2019;Triana-Guzman, Orjuela-Cañon, Jutinico, Mendoza-Montoya, & Antelis, 2022). Therefore, due to the lack of these studies, as well as the fact that there is few investigations related to the complexity of tasks in the transition from sitting to standing and vice versa, an open challenge for the scientific community remains to examine the EEG SMR modulations to categorize the information related to the MI and ME of these types of movements.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exploring Motor Imagery and Execution of Lower Limb Tasks: EEG Analysis during Transitions from Sitting to Standing

Triana-Guzman,

Guerrero-Mendez,

Moreno-Arevalo

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Purpose: Motor Imagery (MI) and Motor Execution (ME) of the upper limbs have been extensively studied in the literature, whereas research on MI and ME of lower limb movements remains comparatively scarce, especially in tasks related to those involved in Activities of Daily Living (ADLs), such as standing and sitting. Therefore, in this study, the temporal and frequency features of EEG signals recorded by healthy subjects with no previous experience in recording Electroencephalography (EEG) signals were analyzed. Methods: The roles of MI and ME were investigated in a paradigm based on standing and sitting transitions tasks guided by visual cues presented on a screen, by randomizing MI and ME. Sensorimotor Rhythms (SMR) were analyzed using power spectral modulation and Event Related Synchronization/Desynchronization (ERDS) features. Results: As a result, Alpha waves (7-13 Hz) are more discriminant between MI and ME than Beta waves (14-35 Hz). Significant differences were observed between the standing and sitting MI and ME groups. In addition, the sitting task was found to have higher power spectral than the standing task. Conclusion: EEG analyses during the evaluation of complex and natural tasks, such as standing and sitting in inexperienced subjects, could serve as a basis for more effective interventions. In addition, novel strategies for motor rehabilitation could be applied, as well as increasing the understanding of the Central Nervous System (CNS) related to standing and sitting transitions tasks.

show abstract

“…To compare the cognitive task performance between the AOMI and MI-based BCI groups, online classification accuracy was utilized. On each training day, we counted the number of times participants were able to activate FES in response to the AOMI or MI task and converted that number to a percentage using the following equation ( 2) [49,50].…”

Section: Outcome Measuresmentioning

confidence: 99%

Applying Action Observation During a Brain-Computer Interface on Upper Limb Recovery in Chronic Stroke Patients

et al. 2023

View full text Add to dashboard Cite

the study aimed to compare the effects of combined action observation and motor imagery (AOMI) and motor imagery (MI)-based brain-computer interface (BCI) training on upper limb recovery, cortical excitation, and cognitive task performance in chronic stroke patients. 17 chronic stroke patients were recruited and randomly assigned to AOMI-based BCI (n = 9) and MI-based BCI groups (n = 8). The AOMIbased BCI group received AOMI-based BCI training via functional electrical stimulation (FES) feedback, whereas the MI-based BCI group obtained MI-based BCI training via FES feedback. Both groups participated in training for 12 sessions (3 days/week, consecutive four weeks). To evaluate upper limb function recovery, the Fugl-Meyer Assessment for upper extremity (FMA-UE) was employed. Event-related desynchronization (ERD) and online classification accuracy were utilized to measure cortical excitation of the affected sensorimotor hand region and cognitive task performance, respectively. Both AOMI and MI-based BCI training improved upper limb function in chronic stroke patients. However, the AOMI-based BCI group showed significantly greater motor gain than the MI-based BCI group. In addition, the AOMI-based BCI group demonstrated significantly greater cortical excitation of the affected sensorimotor hand region and cognitive task performance. The correlation analysis revealed that higher cognitive task performance during AOMI-based BCI training may promote greater cortical excitation of the affected sensorimotor hand region, which contributes to greater upper limb function improvement compared to MI-based BCI training.

show abstract

Decoding EEG rhythms offline and online during motor imagery for standing and sitting based on a brain-computer interface

Cited by 7 publications

References 65 publications

Evaluation of temporal, spatial and spectral filtering in CSP-based methods for decoding pedaling-based motor tasks using EEG signals

Evaluation of temporal, spatial and spectral filtering in CSP-based methods for decoding pedaling-based motor tasks using EEG signals

Exploring Motor Imagery and Execution of Lower Limb Tasks: EEG Analysis during Transitions from Sitting to Standing

Applying Action Observation During a Brain-Computer Interface on Upper Limb Recovery in Chronic Stroke Patients

Contact Info

Product

Resources

About