Application of weak classifier architectures to protein structure classification.
In: Prochazka, A and Uhlir, J and Sovka, P, (eds.)
SIGNAL ANALYSIS & PREDICTION I.
(pp. 383 - 386).
The 'combination of weak classifiers' method of pattern classification is extended from its original two-class formulation to deal with the separation of multiple pattern types, and the method is applied to the problem of classifying proteins into structural types on the basis of their amino acid composition. Results are presented which compare very favourably with those obtained using a standard statistical procedure commonly used by structural molecular biologists.
|Title:||Application of weak classifier architectures to protein structure classification|
|Event:||1st European Conference on Signal Analysis and Prediction (ECSAP-97)|
|Location:||PRAGUE, CZECH REPUBLIC|
|Dates:||1997-06-24 - 1997-06-27|
|UCL classification:||UCL > School of BEAMS > Faculty of Engineering Science > Computer Science|
Archive Staff Only