Prediction of epileptic seizures by CNN with linear weight functions

Kunz, R.; Niederhofer, C.; Tetzlaff, Ronald

doi:10.1109/cnna.2002.1035059

Cited by 10 publications

(6 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4 which have been proposed in previous publications. 4 Firstly the analysis of a certain patient's recordings show which pattern exhibits the considered occurrence behaviour which possibly could be regarded as precursors of an impending seizure. The real-time detection of one of these possible precursors can be performed by using a CNN-UM chip.…”

Section: Resultsmentioning

confidence: 99%

“…In this paper we have presented new results for the pattern detection algorithm proposed by Kunz et al,4 which was implemented by a CNN-UM chip simulation. These new results confirm the previous observations 10 and the detected distinct changes of the pattern occurence could possibly be interpreted as a precursor for an impending epileptic seizure.…”

Section: Discussionmentioning

confidence: 97%

See 1 more Smart Citation

Pattern detection by CNN in epilepsy: recent results

2003

View full text Add to dashboard Cite

0.5% of the world population is suffering from a focal epilepsy. 1 Several actual investigations showed that methods in nonlinear signal processing are important for the derivation of new feature extraction methods to enable the realisation of a portable epilepsy warning system. In this contribution we will present recent results for the pattern detection algorithm which we have proposed in previous investigations. Furthermore the pattern detection algorithm has been transformed in order to run on the first realization of a possible warning device, which had been presented by Laiho et. al.. 2 A detailed discussion of the results will be given in the paper.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 97%

Pattern detection by CNN in epilepsy: recent results

2003

View full text Add to dashboard Cite

show abstract

“…The most challenging problem for the realization of an implantable system simply giving a warning before the onset of an epileptic seizure is the derivation of appropriate feature extraction methods allowing reliable precursor detection with high sensitivity and specificity 6 . In comparison to a classical analysis of EEG signals which has been performed in several investigations 29 e.g.…”

Section: Feature Extractionmentioning

confidence: 99%

Intelligent implantable medical devices: the epilepsy problem (Keynote Paper)

2005

View full text Add to dashboard Cite

In this paper we present our work analysing electroencephalographic (EEG) signals for the detection of seizure precursors in epilepsy. Volterra-systems and Cellular Nonlinear Networks are considered for a multidimensional signal analysis which is called the feature extraction problem throughout this contribution. Recent results obtained by applying a pattern detection algorithm and a nonlinear prediction of brain electrical activity will be discussed in detail. The aim of this interdisciplinary project is the realization of an implantable seizure warning and preventing system.

show abstract

“…The use of genetic algorithm for optimal feature selection [10], the performance of Boolean CNN with linear weight functions as a feature extractor [17], the variance-based methods [14], the use of Blind Source Separation [9], the wavelet-based nonlinear similarity index (WNSI) [6] and Singular Spectrum Analysis are some of the techniques for extracting the valuable information out of EEG time-series data for epileptic seizure detection. In addition to the above, it has reviewed in [12] that the correlation function time domain analysis, frequency domain analysis, time-frequency domain analysis, artificial neural network based analysis and fuzzy logic based analysis are also some of the methods that are used by the researchers in this domain.…”

Section: Introductionmentioning

confidence: 99%

Epileptic seizure detection using PCA on wavelet subbands

Sheoran

Saini

2014

2014 5th International Conference - Confluence the Next Generation Information Technology Summit (Confluence)

View full text Add to dashboard Cite

The detection and classification of epileptic seizures using the Electroencephalography (EEG) signal has been an active field of research from past few decades. EEG is a nonstationary signal that represents electrical activity along the scalp containing very useful information about normal or epileptic brain states. In this paper, principal component analysis is performed on the wavelets subbands of normal & epileptic signals using discrete wavelet transform. This method is applied to two different groups of EEG signals, i.e., (1) Healthy states (2) Epileptic states, during a seizure (ictal EEG). The features extracted from the principal components that are evaluated from the wavelet subbands, differentiate between these two states. Further, t-student statistical distribution is applied to determine the measure of distinguishing between different subjects. The method of principal component analysis on wavelet subbands can discriminate between ictal & non-ictal subjects with 99.99% pvalue (eye open) and 99.96% p-value (eye closed) using the delta subband. The results presented here are much better than the results of previous researches.

show abstract

Prediction of epileptic seizures by CNN with linear weight functions

Cited by 10 publications

References 4 publications

Pattern detection by CNN in epilepsy: recent results

Pattern detection by CNN in epilepsy: recent results

Intelligent implantable medical devices: the epilepsy problem (Keynote Paper)

Epileptic seizure detection using PCA on wavelet subbands

Contact Info

Product

Resources

About