1992
DOI: 10.1016/0013-4694(92)90112-u
|View full text |Cite
|
Sign up to set email alerts
|

Prediction of the side of hand movements from single-trial multi-channel EEG data using neural networks

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
23
0
1

Year Published

1994
1994
2012
2012

Publication Types

Select...
4
2
2

Relationship

1
7

Authors

Journals

citations
Cited by 62 publications
(24 citation statements)
references
References 9 publications
0
23
0
1
Order By: Relevance
“…Since also be evoked by experimental stimuli and reflects the contribution of MRPs is the same, this difference in cognitive processes [1,2,28]. In addition, induced alpha wave forms indicate a 'smearing out' of the cognitive activity, which occurs when alpha desynchronization is not components due to RT variability which results in intime-locked to an exogenous event, as it is the case in the creased jittering when averaging response locked (backendogenous condition of the present study, can still be wards) as compared to averaging stimulus-locked (formeasured [49]. The total alpha activity reported in this wards).…”
Section: Oscillatory Activitymentioning
confidence: 68%
“…Since also be evoked by experimental stimuli and reflects the contribution of MRPs is the same, this difference in cognitive processes [1,2,28]. In addition, induced alpha wave forms indicate a 'smearing out' of the cognitive activity, which occurs when alpha desynchronization is not components due to RT variability which results in intime-locked to an exogenous event, as it is the case in the creased jittering when averaging response locked (backendogenous condition of the present study, can still be wards) as compared to averaging stimulus-locked (formeasured [49]. The total alpha activity reported in this wards).…”
Section: Oscillatory Activitymentioning
confidence: 68%
“…In practice, several groups have shown that such 'thoughts' as mentally answering 'yes' and 'no' [1], intention to move a j~stick [2] or planning of hand movement [3,4] can be discriminated based on the recorded EEG with surprising accuracy. These findings have led to the idea to exploit the EEG for control in cases where other means of control are either impossible, e.g.…”
Section: Introductionmentioning
confidence: 99%
“…With respect the recognition scores obtained here, other Authors have been able to perform successful recognition scores of patterns associated with the preparation of performed movements with linear classification technique based on the Common Spatial Patterns as high as 90% (CSP) [15] as well as non linear classifiers as high as 84% [11][12][13] in the Brain Computer Interface area. However, the use of CSP methods required the use of a larger set of EEG recording electrodes than those reported here.…”
Section: B Implication For the Brain Computer Interfacementioning
confidence: 91%
“…Another key factor in the BCI researches is to develop methods for reliable EEG classification that do not involve lengthy training procedures, in order to reduce the time spent by the user in the unsuccessful interactions with the final device. In this respect, many algorithms involving non linear and linear classifiers have been suggested in literature [11][12][13][14][15]. With these problematic in mind, we explored the possibilities offered by simple quadratic classifiers, based on the concept of Mahalanobis distance, for the recognition of EEG patterns sampled with a low number of scalp electrodes (2 or 4).…”
Section: Introductionmentioning
confidence: 99%