Classification of Long-Term EEG Recordings

Kosar, Karel; Lhotská, Lenka; Krajča, Vladimı́r

doi:10.1007/978-3-540-30547-7_33

Cited by 9 publications

(8 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When the photon arrival rate has statistically significant change, the signal should be splitted at border of the change to analyse the behaviour of the object (Scargle 1998;Gustafsson 2000). As another example, in processing long-term electroencephalograms, the signal is initially segmented into small epochs to consider them stationary signals as there are many techniques for analysing such signals (Krajca et al 1991;Agarwal and Gotman 1999;Kirlangic et al 2001;Kosar et al 2004;Hassanpour and Shahiri 2007;Anisheh 2009;Anisheh and Hassanpour 2009). Therefore, it is necessary to employ a proper segmentation algorithm to detect the boundaries.…”

Section: Introductionmentioning

confidence: 97%

“…In many signal processing applications, the signal of interest is initially segmented into small epochs to consider the signal as piece-wise stationary (Krajca, Petranek, Patakova, and Varri 1991;Scargle 1998;Agarwal and Gotman 1999;Gustafsson 2000;Kirlangic et al 2001;Kosar, Lhotska, and Krajca 2004;Hassanpour and Shahiri 2007;Anisheh 2009;Anisheh and Hassanpour 2009). For example, tracking the brightness changes of galactic objects is an important subject in astronomy (Scargle 1998;Gustafsson 2000).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Designing an adaptive approach for segmenting non-stationary signals

Anisheh

Hassanpour

2011

International Journal of Electronics

View full text Add to dashboard Cite

Signal analysis tools such as Fourier transform are often applicable on data with a limited length. Segmentation is an important pre-processing step in many signal processing applications. Statistical characteristics of the signal in a segment are often preferred to be similar. This characteristic, stationarity, improves performance of signal analysis technique. This article develops an adaptive segmentation method based on wavelet transform and fractal dimension from two aspects. One is to use discrete stationary wavelet transform in pre-processing step instead of using classical wavelet transform. The other is to choose the optimal parameters. Two parameters are needed to calculate the fractal dimension of a decomposed signal, window length and percentage overlapping of the successive windows, which affect the performance of the proposed approach. These parameters are optimally set using the particle swarm optimisation algorithm. Performance of the proposed method is compared with three other existing segmentation methods using both synthetic signal and real data. The results indicate the superiority of the proposed technique in terms of accuracy compared to existing methods.

show abstract

Section: Introductionmentioning

confidence: 97%

Section: Introductionmentioning

confidence: 99%

Designing an adaptive approach for segmenting non-stationary signals

Anisheh

Hassanpour

2011

International Journal of Electronics

View full text Add to dashboard Cite

show abstract

“…In constant segmentation a signal is segmented into epochs with constant duration [3,4]. Although this method has a simple processing but its performance is extremely low.…”

Section: Introductionmentioning

confidence: 99%

An Improved Signal Segmentation Method using Genetic Algorithm

Azami¹,

Mohammadi²,

Hassanpour³

2011

IJCA

View full text Add to dashboard Cite

In many signal processing application, the signal of interest is often divided into epochs. In these applications, the segmented signal is preferred to have no change on the statistical characteristics of the epochs. Modified Varri is among the segmentation methods with an acceptable accuracy. There are three parameters affecting on the accuracy of this method. These parameters are set experimentally. Hence, they may not be optimal for any signal segmentation application. We have used Genetic Algorithm (GA) in this research to choose appropriate values for these parameters in any signal segmentation application. The proposed technique was applied on both synthetic signal and Electroencephalography (EEG) to evaluate its performance. The results indicate superiority of the proposed method in signal segmentation compared to the original approach.

show abstract

“…For example, an EEG signal recorded from an epileptic patient may be divided into three segments of preictal, ictal, and postictal segments and each of which may have a different time duration [1]. There are a number of methods to segment signals [3][4][5][6][7][8][9].…”

Section: Introductionmentioning

confidence: 99%

“…This method, which is based on mean value and standard deviation of a signal, was used as a preprocessing step for classification of long-term EEG recordings [4].…”

Section: Introductionmentioning

confidence: 99%

Combination of signal segmentation approaches using fuzzy decision making

Azami

Escudero

2015

2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

Abstract-Segmentation is an important stage in signal analysis, and its performance plays a significant role in the efficiency of the subsequent steps, such as extraction of descriptive features and classification. There are a large number of approaches to segment signals. The performance of each of them remarkably varies when the signal changes. In this present study, two novel algorithms, which use the probability and fuzzy concepts, are proposed to combine several well-known existing signal segmentation approaches. The simulation results confirm the efficiency of the proposed approaches using the synthetic and real electroencephalogram signals.

show abstract

Classification of Long-Term EEG Recordings

Cited by 9 publications

References 11 publications

Designing an adaptive approach for segmenting non-stationary signals

Designing an adaptive approach for segmenting non-stationary signals

An Improved Signal Segmentation Method using Genetic Algorithm

Combination of signal segmentation approaches using fuzzy decision making

Contact Info

Product

Resources

About