Colin Morris

• University of South Wales

Biological identification poses many problems which are not commonly met in other areas where artificial neural networks (ANNs) are applied. One such problem is that the number of possible classes is often unbounded and it is necessary to be able to deal with novel categories (taxa) either by rejecting them or retraining to allow for them. Where it...

Analytical flow cytometry (AFC), by quantifying sometimes more than 10 optical parameters on cells at rates of approximately 10(3) cells/s, rapidly generates vast quantities of multidimensional data, which provides a considerable challenge for data analysis. We review the application of multivariate data analysis and pattern recognition techniques...

Artificial neural networks (ANNs) have been shown to be valuable in the analysis of analytical flow cytometric (AFC) data in aquatic ecology. Automated extraction of clusters is an important first stage in deriving ANN training data from field samples, but AFC data pose a number of challenges for many types of clustering algorithm. The fuzzy k-mean...

Background Analytical flow cytometry (AFC), by quantifying sometimes more than 10 optical parameters on cells at rates of approximately 10³ cells/s, rapidly generates vast quantities of multidimensional data, which provides a considerable challenge for data analysis. We review the application of multivariate data analysis and pattern recognition te...

Background Artificial neural networks (ANNs) have been shown to be valuable in the analysis of analytical flow cytometric (AFC) data in aquatic ecology. Automated extraction of clusters is an important first stage in deriving ANN training data from field samples, but AFC data pose a number of challenges for many types of clustering algorithm. The f...

A common task in microbiology involves determining the composition of a mixed population of individuals by drawing a sample from the population and using some procedure to identify the individuals in the sample. There may be a significant probability that the identification procedure misidentifies some members of the sample (for example, because th...

Obtaining training data for constructing artificial neural networks (ANNs) to identify microbiological taxa is not always easy. Often, only small data sets with different numbers of observations per taxon are available. Here, the effect of both size of the training data set and of an imbalanced number of training patterns for different taxa is inve...

Missing parameters are a common problem when trying to make biological identifications, either using traditional taxonomic characters or parameters measured by high tech equipment. Different ways of coping with missing parameters are evaluated. Identification success when missing parameter values are estimated as the mean or by a maximum likelihood...

Radial basis function artificial neural networks (ANNs) were trained to discriminate between phytoplankton species based on 7 flow cytometric parameters measured on axenic cultures. Comparison was made between the performance of networks restricted to using radially-symmetric basis functions and networks using more general arbitrarily oriented elli...

We describe here the application of a type of artificial neural network, the Gaussian radial basis function (RBF) network, in the identification of a large number of phytoplankton strains from their 11-dimensional flow cytometric characteristics measured by the European Optical Plankton Analyser instrument. The effect of network parameters on optim...

The use of artificial neural networks (ANNs) for recognising patterns in biological data is explained. The architecture and training of back propagation (multilayer perceptron), radial basis function (RBF) and learning vector quantization ANNs are described, as examples of ANNs which employ supervised learning and which are appropriate for biologic...

The relative abilities of the multilayer perceptron, radial basis function, asymmetric radial basis function and learning vector quantization artificial neural networks (ANNs) and two non-neural methods to identify fungal spores were compared. ANNs were trained on morphometric data from spores of Pestalotiopsis spp. and a few species in the related...

Identification problems in the biological domain present difficulties many of which are not commonly met in other problem domains. One such difficulty is that the number of possible classes is often unbounded and it is necessary to be able to deal with novel classes either by rejecting them or retraining to allow for them. Where it is necessary to...

Four artifcial neural network paradigms (multilaver perceptron networks, learning vector quantization networks, and radial and asymmetric basis function networks) and two statistical methods (parametric statistical classification by modelling each class with Gaussian distributions, and non-parametric density estimation via the K-nearest neighbour m...

Identification problems in biology and medicine are often unbounded with the number of possible classes unknown. Often it is more important to reject patterns from classes upon which a network has not been trained than to classify them incorrectly. The ability of radial basis function networks to do this is examined using flow cytometry fingerprint...

The EurOPA instrument is a purpose-built marine flow cytometer to be taken to sea for rapid analysis of seawater samples for phytoplankton content. To take advantage of the potentially high rate of data capture, neural network classifiers will be incorporated into the package to provide an integrated approach to plankton analysis

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, B...

Flow cytometry data (time of flight, horizontal and vertical forward light scatter, 90 degrees light scatter, and "red" and "orange" integral fluorescence) were collected for laboratory cultures of 40 species of marine phytoplankton, from the following taxonomic classes, the Dinophyceae, Bacillariophyceae, Prymnesiophyceae, Cryptophyceae, and other...

Flow cytometry can be used to obtain simultaneous measurements of multiple cellular parameters, e.g. size, RNA, DNA, chlorophyll and protein content, of phytoplankton (microscopic algae), and if a suitable combination of characters is selected a 'fingerprint' unique to a particular species can be obtained. Since flow cytometers can commonly measure...

Fungal species are traditionally identified on the basis of characteristics of the reproductive structures, commonly by employing dichotomous keys. However, a major problem with the latter lies in the fact that if any character employed in the key is missing or incorrectly assessed then a species identification will be impossible to make or will be...

Flow cytometry can measure several variables (typically between three and eight) on cells very rapidly (often in excess of 103 per second). Hence it is a major challenge to analyse the data produced. Currently, we are aware of four published studies employing neural computing techniques to distinguish between different cell types on the basis of fl...

The potential of back-error propagation neural networks for identifying fungal species from flow cytometric measurements of spores was evaluated. Neural networks consisting of two, three, four, six and eight hidden nodes (processing elements) were successfully trained to discriminate between Megacollybia platyphylla, Oudemansiella radicata, Phallus...