Phyllometric parameters and artificial neural networks for the identification of Banksia accessions
Giuseppe Messina A B , Camilla Pandolfi A , Sergio Mugnai A C , Elisa Azzarello A , Kingsley Dixon B and Stefano Mancuso AA Department of Horticulture, University of Florence, Viale delle Idee 30, 50019 Sesto Fiorentino (FI), Italy.
B School of Plant Biology, University of Western Australia, 35 Stirling Highway, Crawley, WA 6907, Australia.
C Corresponding author. Email: sergio.mugnai@unifi.it
Australian Systematic Botany 22(1) 31-38 https://doi.org/10.1071/SB08003
Submitted: 15 January 2008 Accepted: 19 January 2009 Published: 11 March 2009
Abstract
Taxonomic identification is traditionally carried out with dichotomous keys, or at least computer-based identification keys, often on the basis of subjective visual assessment and frequently unable to detect small differences at subspecies and varietal ranks. The aims of the present work were to (1) clearly discriminate a wide group of accessions (species, subspecies and varieties) belonging to the genus Banksia on the basis of 14 phyllometric parameters determined by image analysis of the leaves, and (2) unequivocally identify the accessions with a relatively simple back-propagation neural-network (BPNN) architecture (single hidden layer) in order to develop a complementary method for fast botanical identification. The results indicate that this kind of network could be effectively and successfully used to discriminate among Banksia accessions, as the BPNN enabled a 93% unequivocal and correct simultaneous identification. Our BPNN had the advantage of being able to resolve subtle associations between characters, and of making incomplete data (i.e. absence of Banksia flower parameters such as the colour or size of styles) useful in species diagnostics. This method is relatively useful; it is easy to execute as no particular competences are necessary, equipment is low cost (scanner connected to a PC and software available as freeware) and data acquisition is fast and effective.
Acknowledgements
The authors thank Kings Park and Botanic Garden staff (Dr Matthew Barrett, Russell Barrett, Mr Bob Dixon) and the institution for hosting this project (providing plant material, scanner, travelling expenses) and for assistance with the identification of Banksia; Mr and Mrs Collins, owners of ‘The Banksia Farm’, for access to their collection of Banksia species from eastern Australia.
Al-Haddad L,
Morris CW, Boddy L
(2000) Training radial basis function neural networks: effects of training set size and imbalanced training sets. Journal of Microbiological Methods 43, 33–44.
| Crossref | GoogleScholarGoogle Scholar |
CAS |
PubMed |
Balfoort HW,
Snoek J,
Smits JRM,
Breedveld LW,
Hofstraat JW, Ringelberg J
(1992) Automatic identification of algae: neural network analysis of flow cytometric data. Journal of Plankton Research 14, 575–589.
| Crossref | GoogleScholarGoogle Scholar |
Boddy L,
Morris CW,
Wilkins MF,
Al-Haddad L,
Tarran GA,
Jonker RR, Burkill PH
(2000) Identification of 72 phytoplankton species by radial basis function neural network analysis of flow cytometric data. Marine Ecology Progress Series 195, 47–59.
| Crossref | GoogleScholarGoogle Scholar |
Chesmore D, Ohya E
(2004) Automated identification of field-recorded songs of four British grasshoppers using bioacoustic signal recognition. Bulletin of Entomological Research 94, 319–330.
| Crossref | GoogleScholarGoogle Scholar |
CAS |
PubMed |
Clark JY
(2003) Artificial neural network for species identification by taxonomists. Biosystems 72, 131–147.
| Crossref | GoogleScholarGoogle Scholar | PubMed |
Clark JY, Warwick K
(1998) Artificial keys for botanical identification using a multilayer perceptron neural network (MLP). Artificial Intelligence Review 12, 95–115.
| Crossref | GoogleScholarGoogle Scholar |
Do MT,
Harp JM, Norris KC
(1999) A test of a pattern recognition system for identification of spiders. Bulletin of Entomological Research 89, 217–224.
| Crossref | GoogleScholarGoogle Scholar |
Du JX,
Huang DS,
Wang XF, Gu X
(2007) Shape recognition based on neural networks trained by differential evolution algorithm. Neurocomputing 70, 896–903.
Gaston KJ, O’Neill MA
(2004) Automated species identification: why not? Philosophical Transactions of the Royal Society of London. B 359, 655–667.
| Crossref | GoogleScholarGoogle Scholar |
George AS
(1981) The genus Banksia L.f. (Proteaceae). Nuytsia 3, 239–473.
George AS
(1988) New taxa and notes on Banksia L.f. (Proteaceae). Nuytsia 6, 309–317.
Giacomini M,
Ruggiero C,
Calegari L, Bertone S
(2000) Artificial neural network based identification of environmental bacteria by gas-chromatographic and electrophoretic data. Journal of Microbiological Methods 43, 45–54.
| Crossref | GoogleScholarGoogle Scholar |
CAS |
PubMed |
Ginoris YP,
Amaral AL,
Nicolau A,
Ferreira EC, Coelho MAZ
(2007) Recognition of protozoa and metazoa using image analysis tools, discriminant analysis, neural networks and decision trees. Analytica Chimica Acta 595, 160–169.
| Crossref | GoogleScholarGoogle Scholar |
CAS |
PubMed |
Hernández-Borges J,
Corbella-Tena R,
Rodriguez-Delgado MA,
Garcia-Montelongo FJ, Havel J
(2004) Content of aliphatic hydrocarbons in limpets as a new way for classification of species using artificial neural networks. Chemosphere 54, 1059–1069.
| Crossref | GoogleScholarGoogle Scholar | PubMed |
Mancuso S
(2002) Discrimination of grapevine (Vitis vinifera L.) leaf shape by fractal spectrum. Vitis 41, 137–142.
Mancuso S, Nicese FP
(1999) Identifying olive (Olea europaea L.) cultivars using artificial neural networks. Journal of the American Society for Horticultural Science 124, 527–531.
Mancuso S,
Ferrini F, Nicese FP
(1999) Chestnut (Castanea sativa L.) genotype identification: an artificial neural network approach. Journal of Horticultural Science & Biotechnology 74, 777–784.
Mariño SI, Tressens SG
(2001) Artificial neural networks application in the identification of three species of Rollinia (Annonaceae). Annales Botanici Fennici 38, 215–224.
Mast AR, Givnish TJ
(2002) Historical biogeography and the origin of stomatal distributions in Banksia and Dryandra (Proteaceae) based on their cpDNA phylogeny. American Journal of Botany 89, 1311–1323.
| Crossref | GoogleScholarGoogle Scholar |
CAS |
Mast AR, Thiele K
(2007) The transfer of Dryandra R.Br. to Banksia L.f. (Proteaceae). Australian Systematic Botany 20, 63–71.
| Crossref | GoogleScholarGoogle Scholar |
Mast AR,
Jones EH, Havery SP
(2005) An assessment of old and new DNA sequence evidence for the paraphyly of Banksia with respect to Dryandra (Proteaceae). Australian Systematic Botany 18, 75–88.
| Crossref | GoogleScholarGoogle Scholar |
CAS |
Morgan A,
Boddy L,
Mordue JEM, Morris CW
(1998) Evaluation of artificial neural networks for fungal identification, employing morphometric data from spores of Pestalotiopsis species. Mycological Research 102, 975–984.
| Crossref | GoogleScholarGoogle Scholar |
Morris CW,
Boddy L, Allman R
(1992) Identification of basidiomycete spores by neural network analysis of flow cytometry data. Mycological Research 96, 697–701.
| Crossref |
Mouwen DJM,
Capita R,
Alonso-Calleja C,
Prieto-Gómez J, Prieto M
(2006) Artificial neural network based identification of Campylobacter species by Fourier transform infrared spectroscopy. Journal of Microbiological Methods 67, 131–140.
| Crossref | GoogleScholarGoogle Scholar |
CAS |
PubMed |
Mugnai S,
Pandolfi C,
Azzarello E,
Masi E, Mancuso S
(2008) Camellia japonica L. genotypes identified by an artificial neural network based on phyllometric and fractal parameters. Plant Systematics and Evolution 270, 95–108.
| Crossref | GoogleScholarGoogle Scholar |
Sahin N, Aydin S
(2006) Identification of oxalotrophic bacteria by neural network analysis of numerical phenetic data. Folia Microbiologica 51, 87–91.
| Crossref | GoogleScholarGoogle Scholar |
CAS |
PubMed |
Smits JRM,
Breedveld LW,
Derksen MJW,
Kateman G,
Balfoort HW,
Snoek J, Hofstraat JW
(1992) Pattern classification with artificial neural networks: classification of algae, based upon flow cytometer data. Analytica Chimica Acta 258, 11–25.
| Crossref | GoogleScholarGoogle Scholar |
CAS |
Thiele K, Ladiges PY
(1994) The Banksia integrifolia L.f. species complex (Proteaceae). Australian Systematic Botany 7, 393–408.
| Crossref | GoogleScholarGoogle Scholar |
Thiele K, Ladiges PY
(1996) A cladistic analysis of Banksia (Proteaceae). Australian Systematic Botany 9, 661–733.
| Crossref | GoogleScholarGoogle Scholar |
Vaňhara J,
Muráriková N,
Malenovský I, Havel J
(2007) Artificial neural networks for fly identification: a case study from the genera Tachina and Ectophasia (Diptera, Tachinidae). Biologia 62, 462–469.
| Crossref | GoogleScholarGoogle Scholar |
Weeks PJD, Gaston KJ
(1997) Image analysis, neural networks, and the taxonomic impediment to biodiversity studies. Biodiversity and Conservation 6, 263–274.
| Crossref | GoogleScholarGoogle Scholar |
Wilkins MF,
Boddy L,
Morris CW, Jonker RR
(1999) Identification of phytoplankton from flow cytometry data by using radial basis function neural networks. Applied and Environmental Microbiology 65, 4404–4410.
|
CAS |
PubMed |
