Hilbert-transform based predictions of hand movements from EEG measurements

Medl, A.; Flotzinger, Doris; Pfurtscheller, Gert

doi:10.1109/iembs.1992.5761577

Cited by 11 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We extend the results of [37] with these experiments and show that the location of a neural frequency peak on the frequency axis can be used as a reliable feature for BCI decoding across paradigms and neural frequency bands, and further that it is stable to standard spatial filtering approaches. We found that across both paradigms, and independent of standard spatial filtering approaches, the joint feature space substantially increases the cross-validated accuracy over healthy subjects.…”

Section: Discussionsupporting

confidence: 57%

“…However, they only attempt the Hilbert transform on the intrinsic modes themselves; we here show that it is unnecessary to use the decomposition first. Last, a paper by Medl et al [37] did look at intrinsic, task-related frequency shifts over 25 years ago, in a visionary work that considered the instantaneous frequency and envelope as possible features for a BCI. However this work was never expanded past an exploratory analysis, an expansion which we attempt here.…”

Section: Related Workmentioning

confidence: 99%

“…In previous BCI applications, both of these have been used as features for a classifier [20,44,45]. However, as with [37], we are not interested in the phase, but rather the instantaneous frequency. This can be computed in general as the derivative of the phase, though for discrete signals we can use the difference operator as follows:…”

Section: Amplitude Modulationmentioning

confidence: 99%

See 2 more Smart Citations

Task-induced frequency modulation features for brain-computer interfacing

et al. 2017

View full text Add to dashboard Cite

show abstract

Section: Discussionsupporting

confidence: 57%

Section: Related Workmentioning

confidence: 99%

Section: Amplitude Modulationmentioning

confidence: 99%

See 1 more Smart Citation

Task-induced frequency modulation features for brain-computer interfacing

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Researches have shown that the ERD of contralateral hemispheric is combined with an instantaneous frequency increase [3][4]. We choose a trial of left-hand motor imagery to verify.…”

Section: Hilbert Transformmentioning

confidence: 99%

Envelope Extraction Algorithms and the Application in Motor Imagery

Gong

Guo

et al. 2013

AMM

View full text Add to dashboard Cite

The envelope information is an important feature in EEG signal processing. This paper analyses the application of Hilbert transform and sliding window Infomax algorithm in envelope detection of EEG signals from different respects, and compares the classification results in left and right hand motor imagery. From the results, we see that, the signal envelope extracted by Hilbert transform is more accurate than sliding window Infomax algorithm, but the latter is superior in signal denoising, real-time ability and the richness of characteristics, sliding window Infomax algorithm has greater application potential.

show abstract

“…After this, their envelopes were calculated using a Hilbert transformation [18], which has widely been used to obtain envelopes in other BCIs [19], [20]. The Hilbert transformû m (t) or H as a function of time u m (t) was defined by…”

Section: Classificationmentioning

confidence: 99%

Movement-Imagery Brain-Computer Interface: EEG Classification of Beta Rhythm Synchronization Based on Cumulative Distribution Function

Sasayama

Kobayashi

2011

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYWe developed a novel movement-imagery-based braincomputer interface (BCI) for untrained subjects without employing machine learning techniques. The development of BCI consisted of several steps. First, spline Laplacian analysis was performed. Next, timefrequency analysis was applied to determine the optimal frequency range and latencies of the electroencephalograms (EEGs). Finally, trials were classified as right or left based on β-band event-related synchronization using the cumulative distribution function of pretrigger EEG noise. To test the performance of the BCI, EEGs during the execution and imagination of right/left wrist-bending movements were measured from 63 locations over the entire scalp using eight healthy subjects. The highest classification accuracies were 84.4% and 77.8% for real movements and their imageries, respectively. The accuracy is significantly higher than that of previously reported machine-learning-based BCIs in the movement imagery task (paired t-test, p < 0.05). It has also been demonstrated that the highest accuracy was achieved even though subjects had never participated in movement imageries. key words: electroencephalogram (EEG), brain-machine interface (BCI), event-related synchronization (ERS), spline Laplacian, Hilbert transform

show abstract

Hilbert-transform based predictions of hand movements from EEG measurements

Cited by 11 publications

References 4 publications

Task-induced frequency modulation features for brain-computer interfacing

Task-induced frequency modulation features for brain-computer interfacing

Envelope Extraction Algorithms and the Application in Motor Imagery

Movement-Imagery Brain-Computer Interface: EEG Classification of Beta Rhythm Synchronization Based on Cumulative Distribution Function

Contact Info

Product

Resources

About