Title :
Classification of escherichia coli bacteria by artificial neural networks
Author :
Avci, Mutlu ; Yildirim, T.
Author_Institution :
Electron. & Commun. Eng. Dept., Yildiz Tech. Univ., Istanbul, Turkey
Abstract :
Through this paper, four different neural network structures which are: multilayer perceptron, radial basis function, general regression neural network and probabilistic neural network are applied to the escherichia coli bacteria benchmark and the most efficient neural network architecture for this data has been obtained. Better classification accuracy than the reference work using the ad hoc structured probability model was achieved by a probabilistic neural network.
Keywords :
biology computing; classification; microorganisms; multilayer perceptrons; neural net architecture; probability; radial basis function networks; ad hoc structured probability model; backpropagation; escherichia coli bacteria classification; general regression neural network; multilayer perceptron; neural network architecture; probabilistic neural network; radial basis function neural net; Artificial neural networks; Bayesian methods; Benchmark testing; Biomembranes; Classification tree analysis; Decision trees; Microorganisms; Neural networks; Telephony; Training data;
Conference_Titel :
Intelligent Systems, 2002. Proceedings. 2002 First International IEEE Symposium
Print_ISBN :
0-7803-7134-8
DOI :
10.1109/IS.2002.1042578
