Limits...
A novel constrained topographic independent component analysis for separation of epileptic seizure signals.

Jing M, Sanei S - Comput Intell Neurosci (2007)

Bottom Line: The TICA algorithm further improves the results if the desired signal sources have particular properties which can be exploited in the separation process as constraints.The performance is compared with those from the TICA and other conventional ICA algorithms.The superiority of the new constrained TICA has been validated in terms of signal-to-interference ratio and correlation measurement.

View Article: PubMed Central - PubMed

Affiliation: Centre of Digital Signal Processing, Cardiff University, Cardiff CF24 3AA, Wales, UK. jingm@cf.ac.uk

ABSTRACT
Blind separation of the electroencephalogram signals (EEGs) using topographic independent component analysis (TICA) is an effective tool to group the geometrically nearby source signals. The TICA algorithm further improves the results if the desired signal sources have particular properties which can be exploited in the separation process as constraints. Here, the spatial-frequency information of the seizure signals is used to design a constrained TICA for the separation of epileptic seizure signal sources from the multichannel EEGs. The performance is compared with those from the TICA and other conventional ICA algorithms. The superiority of the new constrained TICA has been validated in terms of signal-to-interference ratio and correlation measurement.

No MeSH data available.


Related in: MedlinePlus

Performancecomparison of TICA and CTICA.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC2267251&req=5

fig6: Performancecomparison of TICA and CTICA.

Mentions: The performance of the algorithm was evaluated by theaverage of five trials for both TICA and CTICA. The SIR was calculated based onthe definition given in (14). Figure 6 illustrates the separation performance(SIR) via the changes of the width of the neighborhood. It can be noticed thatthe SIR of TICA decreases with the increase of the neighborhood width. This isbecause the wider the neighborhood is, the more the source will be separatedbased on energy correlation. However, for the CTICA, due to the spatial andfrequency constraints, the SIR slightly decreases at the beginning, then staysapproximately at certain level. It shows that, generally, the CTICA has abetter performance than the TICA. It also works better than the TICA when thewidth of the neighborhood increases.


A novel constrained topographic independent component analysis for separation of epileptic seizure signals.

Jing M, Sanei S - Comput Intell Neurosci (2007)

Performancecomparison of TICA and CTICA.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC2267251&req=5

fig6: Performancecomparison of TICA and CTICA.
Mentions: The performance of the algorithm was evaluated by theaverage of five trials for both TICA and CTICA. The SIR was calculated based onthe definition given in (14). Figure 6 illustrates the separation performance(SIR) via the changes of the width of the neighborhood. It can be noticed thatthe SIR of TICA decreases with the increase of the neighborhood width. This isbecause the wider the neighborhood is, the more the source will be separatedbased on energy correlation. However, for the CTICA, due to the spatial andfrequency constraints, the SIR slightly decreases at the beginning, then staysapproximately at certain level. It shows that, generally, the CTICA has abetter performance than the TICA. It also works better than the TICA when thewidth of the neighborhood increases.

Bottom Line: The TICA algorithm further improves the results if the desired signal sources have particular properties which can be exploited in the separation process as constraints.The performance is compared with those from the TICA and other conventional ICA algorithms.The superiority of the new constrained TICA has been validated in terms of signal-to-interference ratio and correlation measurement.

View Article: PubMed Central - PubMed

Affiliation: Centre of Digital Signal Processing, Cardiff University, Cardiff CF24 3AA, Wales, UK. jingm@cf.ac.uk

ABSTRACT
Blind separation of the electroencephalogram signals (EEGs) using topographic independent component analysis (TICA) is an effective tool to group the geometrically nearby source signals. The TICA algorithm further improves the results if the desired signal sources have particular properties which can be exploited in the separation process as constraints. Here, the spatial-frequency information of the seizure signals is used to design a constrained TICA for the separation of epileptic seizure signal sources from the multichannel EEGs. The performance is compared with those from the TICA and other conventional ICA algorithms. The superiority of the new constrained TICA has been validated in terms of signal-to-interference ratio and correlation measurement.

No MeSH data available.


Related in: MedlinePlus