Individual finger movement decoding using a novel ultra-high-density electroencephalography-based brain-computer interface system

Lee, Hyemin S.; Schreiner, Leonhard; Jo, Seong-Hyeon; Sieghartsleitner, Sebastian; Jordan, Michael I.; Pretl, Harald; Guger, Christoph; Park, Hyung Soon

doi:10.3389/fnins.2022.1009878

Cited by 28 publications

(18 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar features could be shown for team behavior in volleyball [32], [33], soccer [34], [35], or basketball [36], [37]. Typical parameters investigated are biomechanical data from video recordings [38], force plates [39]- [41], pressure insoles [42], [43], EMG [44], [45], and brain signals [46], [47]. Besides these, wearable sensors are becoming increasingly popular [48].…”

Section: Introductionmentioning

confidence: 80%

Identifying underlying individuality across running, walking, and handwriting patterns with conditional cycle–consistent generative adversarial networks

Burdack¹,

Giesselbach²,

Simak³

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>In recent years, the analysis of movement patterns has increasingly focused on the individuality of movements. After long speculations about weak individuality, strong individuality is now accepted, and the first situation–dependent fine structures within it are already identified. Methodologically, however, only signals of same movements have been compared so far. The goal of this work is to detect cross-movement commonalities of individual walking, running, and handwriting patterns using data augmentation. 17 healthy adults (35.8 ± 11.1 years, 8 females, 9 males) each performed 627.9 ± 129.0 walking strides, 962.9 ± 182.0 running strides, and 59.25 ± 1.8 handwritings. Using the conditional CycleGAN, conditioned on the participant’s class, a pairwise transformation between the vertical ground reaction force during walking and running and the vertical pen pressure during handwriting was learned in the first step. In the second step, the original data of the respective movements were used to artificially generate the other movement data. In the third step, it was tested whether the artificially generated data could be correctly assigned to a person via classification using a support vector machine trained with original data of the movement. The classification F1–score ranged from 46.8% for handwriting data generated from walking data to 98.9% for walking data generated from running data. Thus, cross–movement individual patterns could be identified. Therefore, the methodology presented in this study may help to enable cross–movement analysis and the artificial generation of larger amounts of data.</p>

show abstract

Section: Introductionmentioning

confidence: 80%

Identifying underlying individuality across running, walking, and handwriting patterns with conditional cycle–consistent generative adversarial networks

Burdack¹,

Giesselbach²,

Simak³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The beta‐decrement approach can be applied to not only MEG and low‐cost EEG systems but also the relatively new technology of optically pumped magnetometers that offer good signal‐to‐noise ratio, spatial resolution, and portability for measuring BCI task activities (Boto et al, 2018 ; Knappe et al, 2012 ). The ultra‐high‐density EEG system is another relatively new technology where beta decrements have shown excellent decoding accuracy for a finger movement BCI task (Lee et al, 2022 ). Comparing the two studies, the focus of our work was mainly to localize neural activity during mixed (motor and mental) imagery task responses and decode source activations, whereas the work by Lee et al ( 2022 ) focused on motor task activations at the channel level.…”

Section: Discussionmentioning

confidence: 99%

“…The ultra‐high‐density EEG system is another relatively new technology where beta decrements have shown excellent decoding accuracy for a finger movement BCI task (Lee et al, 2022 ). Comparing the two studies, the focus of our work was mainly to localize neural activity during mixed (motor and mental) imagery task responses and decode source activations, whereas the work by Lee et al ( 2022 ) focused on motor task activations at the channel level. MEG is less affected by sources of interference from outside the head, and due to its better spatial resolution, sources of brain activity can be localized more accurately in the brain.…”

Section: Discussionmentioning

confidence: 99%

“…This is important in BCI applications, where it is critical to determine the location of specific brain signals associated with motor or mental tasks. However, as suggested by the authors in the discussion section of Lee et al ( 2022 ), source reconstruction provides better reliability for decoding and analyzing high‐density EEG data. Ultra‐high‐density EEG technology has great potential for BCI applications, particularly in individuals with neurological impairments, and future studies may benefit from combining EEG and MEG data to improve the accuracy and localization of BCI systems.…”

Section: Discussionmentioning

confidence: 99%

“…work was mainly to localize neural activity during mixed (motor and mental) imagery task responses and decode source activations, whereas the work byLee et al (2022) focused on motor task activations at the channel level. MEG is less affected by sources of interference from outside the head, and due to its better spatial resolution, sources of brain activity can be localized more accurately in the brain.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Mapping and decoding cortical engagement during motor imagery, mental arithmetic, and silent word generation using MEG

Youssofzadeh

Roy²,

Chowdhury

et al. 2023

Human Brain Mapping

View full text Add to dashboard Cite

Accurate quantification of cortical engagement during mental imagery tasks remains a challenging brain‐imaging problem with immediate relevance to developing brain–computer interfaces. We analyzed magnetoencephalography (MEG) data from 18 individuals completing cued motor imagery, mental arithmetic, and silent word generation tasks. Participants imagined movements of both hands (HANDS) and both feet (FEET), subtracted two numbers (SUB), and silently generated words (WORD). The task‐related cortical engagement was inferred from beta band (17–25 Hz) power decrements estimated using a frequency‐resolved beamforming method. In the hands and feet motor imagery tasks, beta power consistently decreased in premotor and motor areas. In the word and subtraction tasks, beta‐power decrements showed engagements in language and arithmetic processing within the temporal, parietal, and inferior frontal regions. A support vector machine classification of beta power decrements yielded high accuracy rates of 74 and 68% for classifying motor‐imagery (HANDS vs. FEET) and cognitive (WORD vs. SUB) tasks, respectively. From the motor‐versus‐nonmotor contrasts, excellent accuracy rates of 85 and 80% were observed for hands‐versus‐word and hands‐versus‐sub, respectively. A multivariate Gaussian‐process classifier provided an accuracy rate of 60% for the four‐way (HANDS‐FEET‐WORD‐SUB) classification problem. Individual task performance was revealed by within‐subject correlations of beta‐decrements. Beta‐power decrements are helpful metrics for mapping and decoding cortical engagement during mental processes in the absence of sensory stimuli or overt behavioral outputs. Markers derived based on beta decrements may be suitable for rehabilitation purposes, to characterize motor or cognitive impairments, or to treat patients recovering from a cerebral stroke.

show abstract

Brain-Body Interfaces to Assist and Restore Motor Functions in People with Paralysis

Losanno,

Badi,

Roussinova

et al. 2024

SpringerBriefs in Electrical and Computer Engineering

View full text Add to dashboard Cite

Individual finger movement decoding using a novel ultra-high-density electroencephalography-based brain-computer interface system

Cited by 28 publications

References 84 publications

Identifying underlying individuality across running, walking, and handwriting patterns with conditional cycle–consistent generative adversarial networks

Identifying underlying individuality across running, walking, and handwriting patterns with conditional cycle–consistent generative adversarial networks

Mapping and decoding cortical engagement during motor imagery, mental arithmetic, and silent word generation using MEG

Brain-Body Interfaces to Assist and Restore Motor Functions in People with Paralysis

Contact Info

Product

Resources

About