1992
DOI: 10.1016/0013-4694(92)90086-w
|View full text |Cite
|
Sign up to set email alerts
|

Automated interictal EEG spike detection using artificial neural networks

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
54
0

Year Published

1994
1994
2012
2012

Publication Types

Select...
5
3
1

Relationship

0
9

Authors

Journals

citations
Cited by 150 publications
(54 citation statements)
references
References 5 publications
0
54
0
Order By: Relevance
“…ANNs have been trained using either raw data (Ko & Chung, 2000;Ozdamar & Kalayci, 1998;Pang, Upton, Shine, & Kamath, 2003;Webber, et al, 1994) or select features (Acir, Oztura, Kuntalp, Baklan, & Guzelis, 2005;Castellaro et al, 2002;Gabor & Seyal, 1992;Liu, Zhang, & Yang, 2002;Pang, et al, 2003;Tzallas, Karvelis, et al, 2006;Webber, et al, 1994) to detect spikes. In the first case, windows of raw EEG data are fed into an ANN.…”
Section: F Methods Based On Artificial Neural Networkmentioning
confidence: 99%
“…ANNs have been trained using either raw data (Ko & Chung, 2000;Ozdamar & Kalayci, 1998;Pang, Upton, Shine, & Kamath, 2003;Webber, et al, 1994) or select features (Acir, Oztura, Kuntalp, Baklan, & Guzelis, 2005;Castellaro et al, 2002;Gabor & Seyal, 1992;Liu, Zhang, & Yang, 2002;Pang, et al, 2003;Tzallas, Karvelis, et al, 2006;Webber, et al, 1994) to detect spikes. In the first case, windows of raw EEG data are fed into an ANN.…”
Section: F Methods Based On Artificial Neural Networkmentioning
confidence: 99%
“…This problem increases the number of false detections that commonly plague all automatic detection systems [4,5]. Due to these reasons, many studies using artificial neural network (ANN) approach have been reported [5][6][7][8][9][10][11][12][13][14]. The ANN based detection systems basically use either of two different input representations: (i) the extracted EEG features or (ii) the raw EEG signal.…”
Section: Introductionmentioning
confidence: 99%
“…The first approach uses pre-extracted parameters as input data to the ANN detection system. Such an approach has been used by many researchers with fairly successful results (21)(22)(23)(24). Generally two types of parameters are used; (1) waveform parameters, such as amplitude, width, slope, and sharpness, which are extracted from epileptic discharges, and (2) context parameters, such as EEG variance, and baseline crossings, which are extracted from the EEG surrounding the epileptiform discharges.…”
Section: Introductionmentioning
confidence: 99%