Abstract
A method is shown for the description and recognition of patterns in stochastic signals such as electroencephalograms. For pattern extraction the signal is segmented at times of minimum amplitudes. The describing features consist of geometric values of the so defined patterns. The classification algorithm is based on the regression analysis, which is well known in the field of character recognition. For an economic classification a method is proposed which reduces the number of features. The quality of this pattern recognition method is demonstrated by the detection of spike wave complexes in electroencephalograms. The pattern description and recognition are provided for processing on a digital computer. (DE)
Flik, T
[1]
- Technische Univ. Berlin (F.R. Germany). Informatik-Forschungsgruppe Rechnerorganisation und Schaltwerke
Citation Formats
Flik, T.
Description and recognition of patterns in stochastic signals. [Electroencephalograms].
Germany: N. p.,
1975.
Web.
Flik, T.
Description and recognition of patterns in stochastic signals. [Electroencephalograms].
Germany.
Flik, T.
1975.
"Description and recognition of patterns in stochastic signals. [Electroencephalograms]."
Germany.
@misc{etde_7295912,
title = {Description and recognition of patterns in stochastic signals. [Electroencephalograms]}
author = {Flik, T}
abstractNote = {A method is shown for the description and recognition of patterns in stochastic signals such as electroencephalograms. For pattern extraction the signal is segmented at times of minimum amplitudes. The describing features consist of geometric values of the so defined patterns. The classification algorithm is based on the regression analysis, which is well known in the field of character recognition. For an economic classification a method is proposed which reduces the number of features. The quality of this pattern recognition method is demonstrated by the detection of spike wave complexes in electroencephalograms. The pattern description and recognition are provided for processing on a digital computer. (DE)}
journal = []
volume = {10}
journal type = {AC}
place = {Germany}
year = {1975}
month = {Oct}
}
title = {Description and recognition of patterns in stochastic signals. [Electroencephalograms]}
author = {Flik, T}
abstractNote = {A method is shown for the description and recognition of patterns in stochastic signals such as electroencephalograms. For pattern extraction the signal is segmented at times of minimum amplitudes. The describing features consist of geometric values of the so defined patterns. The classification algorithm is based on the regression analysis, which is well known in the field of character recognition. For an economic classification a method is proposed which reduces the number of features. The quality of this pattern recognition method is demonstrated by the detection of spike wave complexes in electroencephalograms. The pattern description and recognition are provided for processing on a digital computer. (DE)}
journal = []
volume = {10}
journal type = {AC}
place = {Germany}
year = {1975}
month = {Oct}
}