Document Detail


A comparison of Radial Basis Function and backpropagation neural networks for identification of marine phytoplankton from multivariate flow cytometry data.
MedLine Citation:
PMID:  7922685     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
Two artificial neural network classifiers, the well-known Multi-layer Perception (MLP) (also known as the 'backpropagation network'), and the more recently developed Radial Basis Function (RBF) network, were evaluated and compared for their ability to identify multivariate flow cytometric data from five North Sea plankton groups (Dinoflagellidae, Bacillariophyceae, Prymnesiomonadida, Cryptomonadida, and other flagellates). RBF networks generally performed similarly to MLPs, and slightly better in cases where the data were markedly multimodal; RBF networks also have much shorter training times. The performance of MLPs was improved greatly by the use of a symmetrical bipolar 'transfer function' as opposed to the commonly-used asymmetric form. The issues of network optimisation and computational efficiency in use are discussed.
Authors:
M F Wilkins; C W Morris; L Boddy
Related Documents :
20619075 - Development of an individual-based model for polioviruses: implications of the selectio...
15340175 - Quantitative information management for the biochemical computation of cellular networks.
19365645 - Trade-offs between efficiency and robustness in bacterial metabolic networks are associ...
19162775 - Stdas: sensing task and data aggregation scheduling for astronaut health monitoring usi...
25457605 - The rubber plantation environment and lassa fever epidemics in liberia, 2008-2012: a sp...
22173205 - Tracer kinetic modelling in mri: estimating perfusion and capillary permeability.
Publication Detail:
Type:  Comparative Study; Journal Article; Research Support, Non-U.S. Gov't    
Journal Detail:
Title:  Computer applications in the biosciences : CABIOS     Volume:  10     ISSN:  0266-7061     ISO Abbreviation:  Comput. Appl. Biosci.     Publication Date:  1994 Jun 
Date Detail:
Created Date:  1994-11-18     Completed Date:  1994-11-18     Revised Date:  2007-11-15    
Medline Journal Info:
Nlm Unique ID:  8511758     Medline TA:  Comput Appl Biosci     Country:  ENGLAND    
Other Details:
Languages:  eng     Pagination:  285-94     Citation Subset:  IM    
Affiliation:
School of Pure and Applied Biology, University of Wales, Cardiff, UK.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Evaluation Studies as Topic
Flow Cytometry
Multivariate Analysis
Neural Networks (Computer)*
Nonlinear Dynamics
Phytoplankton / classification*

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  MULTICOMP: a program for preparing sequence data for phylogenetic analysis.
Next Document:  Steady-state modelling of metabolic flux between the tricarboxylic acid cycle and the glyoxylate byp...