Peter FEDOR, Eladia Maria PEÑA-MÉNDEZ, Halina KUCHARCZYK, Jaromír VAŇHARA, Josef HAVEL, Martina DORIČOVÁ, Pavol PROKOP

Artificial neural networks in online semiautomated pest discriminability: an applied case with 2 Thrips species

Being faced with practical problems in pest identification, we present a methodical paper based on artificial neural networks to discriminate morphologically very similar species, Thrips sambuci Heeger, 1854 and Thrips fuscipennis Haliday, 1836 (Thysanoptera: Thripinae), as an applied case for more general use. The artificially intelligent system may be successfully applied as a credible, online, semiautomated identification tool that extracts hidden information from noisy data, even when the standard characters have much overlap and the common morphological keys hint at the practical problem of high morphological plasticity. Statistical analysis of 17 characters, measured or determined for each Thrips fuscipennis and T. sambuci specimen (reared from larvae in our laboratories), including 15 quantitative morphometric variables, was performed to elucidate morphological plasticity, detect eventual outliers, and visualize differences between the studied taxa. The computational strategy applied in this study includes a set of statistical tools (factor analysis, correlation analysis, principal component analysis, and linear discriminant analysis) followed by the application of a multilayer perceptron artificial neural network system, which models functions of almost arbitrary complexity. This complex approach has proven the existence of 2 separate species: T. fuscipennis and T. sambuci. All the specimens could be clearly distinguished with 2 distinct subgroups for each species, determined by sex. In conclusion, the use of an optimal 3-layer ANN architecture (17, 4, 1) enables fast and reliable 100% classification as proven during the extensive verification process.

Anahtar Kelimeler:

Key words: Artificial neural networks, online semiautomated pest identification, Thysanoptera

Artificial neural networks in online semiautomated pest discriminability: an applied case with 2 Thrips species

Keywords:

Key words: Artificial neural networks, online semiautomated pest identification, Thysanoptera,

PDF

___

Aldrich BT, Magirang EB, Dowell FE, Kambhampati S (2007). Identification of termite species and subspecies of the genus Zootermopsis using near-infrared reflectance spectroscopy. J Insect Sci 7: 18.
Ananthakrishnan TN (2005). Perspectives and dimensions of phenotypic plasticity in insects. In: Ananthakrishnan TN, Whitman D, editors. Insect Phenotypic Plasticity: Diversity of Responses. Enfield, NH, USA: Science Publishers, pp. 1–23.
Apuan DA, Torres MAJ, Demayo CG (2010). Describing variations and taxonomic status of earthworms collected from selected areas in Misamis Oriental, Philippines using principal component and parsimony analysis. Egypt Acad J Biolog Sci B Zoology 2: 27–36.
Bilgili M (2011). The use of artificial neural networks for forecasting the monthly mean soil temperatures in Adana, Turkey. Turk J Agric For 35: 83–93.
Brunner PC, Fleming C, Frey JE (2002). A molecular identification key for economically important thrips species (Thysanoptera: Thripidae) using direct sequencing and a PCR-RFLP-based approach. Agr Forest Entomol 4: 127–136.
Chiapella J (2000). The Deschampsia cespitosa complex in central and northern Europe: morphological analysis. Bot J Linn Soc 134: 495–512.
Clark JY (2003). Artificial neural networks for species identification by taxonomists. Biosystems 72: 131–147.
Do MT, Harp JM, Norris KC (1999). A test of a pattern recognition system for identification of spiders. B Entomol Res 89: 217–224.
Esteban LG, Fernández FG, de Palacios P, Romero RM, Cano NN (2009). Artificial neural networks in wood identification: the case of two Juniperus species from the Canary islands. IAWA J 30: 87–94.
Fausett L (1994). Fundamentals of Neural Networks: Architectures, Algorithms and Applications. New York, NY, USA: Prentice Hall.
Fedor P, Malenovskı I, Vaňhara J, Sierka W, Havel J (2008). Thrips (Thysanoptera) identification using artificial neural networks. B Entomol Res 98: 437–447.
Fedor P, Vaňhara J, Havel J, Malenovskı I, Spellerberg I (2009). Artificial intelligence in pest insect monitoring. Syst Entomol 34: 398–400.
Frantz G, Mellinger HC (1997). THRIPS, a computerized knowledgebase for the identification and management of Thrips infesting vegetables in the United States. Proc Fla State Hort Soc 128: 1–4.
Freeman JA, Skapura DM (1992). Neural Network: Algorithm, Applications, and Programming Techniques. Reading, MA, USA: Addison-Wesley.
Gaston KJ, O’Neill MA (2004). Automated species identification: why not? Philos T Roy Soc B 359: 655–667.
Han R, He Y, Liu F (2012). Feasibility study on a portable field pest classification system design based on DSP and 3G wireless communication technology. Sensors 12: 3118–3130.
Haralabous J, Georgakarakos S (1996). Artificial neural networks as a tool for species identification of fish schools. ICES J Mar Sci 53: 173–180.
Haykin S (1994). Neural Networks - A Comprehensive Foundation. New York, NY, USA: Macmillan College Publishing Company.
Henneberry TJ, Taylor EA, Smith FF (1961). Foliage and soil treatments for control of flower thrips in outdoor roses. J Econ Entomol 54: 233–235.
Isasi P, Galván IM (2004). Redes Neuronales Artificiales, un Enfoque Práctico. Madrid, Spain: Pearson Educación S.A. (in Spanish).
Jacobson RJ (1995). IPM in cucumbers – prevention of establishment of Frankliniella occidentalis. Mededelingen van de Faculteit van de Landbouwwntenschappen 60: 857–863.
Kavdır İ (2004). Discrimination of sunflower, weed and soil by artificial neural networks. Comput Electron Agr 44: 153–160.
Kucharczyk H (2010). Comparative Morphology of the Second Larval Instar of the Thrips Genus Species (Thysanoptera: Thripidae) Occurring in Poland. Olsztyn, Poland: Mantis.
Kucharczyk H, Kucharczyk M (2009). Thrips atratus Haliday, 1836 and Thrips montanus Priesner, 1920 (Thysanoptera: Thripidae) – one or two species? Comparative morphological studies. Acta Zool Acad Sci H 55: 349–364.
Kucharczyk H, Kucharczyk M, Stanislawek K, Fedor P (2012). Application of PCA in taxonomy research – Thrips (Insecta, Thysanoptera) as a model group. In: Sanguansat P, editor. Principal Component Analysis - Multidisciplinary Applications. New York, NY, USA: InTech, pp. 111–126.
Lilburn TG Garrity GM (2004). Exploring prokaryotic taxonomy. Int J Sys Evol Micr 54: 7–13.
Marini F, Zupan J, Magri A (2004). On the use of counterpropagation artificial neural networks to characterize Italian rice varieties. Anal Chim Acta 510: 231–240.
Mayo M, Watson AT (2007). Automatic species identification of live moths. Knowl-Based Sys 20: 195–202.
Mehle N, Trdan S (2012). Traditional and modern methods for the identification of thrips (Thysanoptera) species. J Pest Sci 85: 179–190.
Moore A, Miller RH (2002). Automated identification of optically sensed aphid (Homoptera: Aphidae) wingbeat waveforms. Ann Entomol Soc Am 95: 1–8.
Moritz G, Delker C, Paulsen M, Mound LA, Burgermeister W (2000). Modern methods for identification of Thysanoptera. EPPO Bulletin 30: 591–593.
Moritz G, Morris DC, Mound LA (2001). ThripsID – Pest Thrips of the World. CD ROM. Melbourne, Australia: ACIAR, CSIRO Publishing.
Moritz G, Mound LA, Morris DC, Goldarazena A (2004). Pest Thrips of the World, Visual and Molecular Identification of Pest Thrips. CD ROM. Brisbane, Australia: Centre for Biological Information Technology.
Mound LA (2005). Fighting, flight and fecundity: behavioural determinants of Thysanoptera structural diversity. In: Ananthakrishnan TN, Whitman D, editors. Insect Phenotypic Plasticity: Diversity of Responses. Enfield, NH, USA: Science Publishers, pp. 81–105.
Mound LA (2010). Species of the genus Thrips (Thysanoptera, Thripidae) from the Afro-tropical Region. Zootaxa 2423: 1–24.
Mound LA, Azidah AA (2009). Species of the genus Thrips
(Thysanoptera) from Peninsular Malaysia, with a checklist of recorded Thripidae. Zootaxa 2023: 55–68.
Mound LA, Kibby G (1998). Thysanoptera: An Identification Guide. Wallingford, UK: CAB International.
Mound LA, Masumoto M (2005). The genus Thrips (Thysanoptera, Thripidae) in Australia, New Caledonia and New Zealand. Zootaxa 1020: 1–64.
Mound LA, Minaei K (2010). Taxonomic problems in character state interpretation: variation in the wheat thrips Haplothrips tritici (Kurdjumov) (Thysanoptera, Phlaeothripidae) in Iran. Deut Entomol Z 57: 233–241.
Muráriková N, Vaňhara J, Tóthová A, Havel J (2011). Polyphasic approach applying artificial neural networks, molecular analysis and postabdomen morphology to West Palaearctic Tachina spp. (Diptera, Tachinidae). B Entomol Res 101: 165– 1
Nakahara S (1994). The Genus Thrips Linnaeus (Thysanoptera: Thripidae) of the New World. Technical Bulletin 1822. Washington, DC, USA: United States Department of Agriculture.
Patterson D (1996). Artificial Neural Networks: Theory and Applications. Singapore: Prentice Hall.
Priesner H (1964). Ordnung Thysanoptera (Fransenflügler, Thripse).
Berlin, Germany: Akademie-Verlag (in German). Ripley BD (1993). Statistical aspects of neural networks. In: BarndoffNielsen OE, Cox DR, Jensen JL, Kendall WS, editors. Chaos and Networks – Statistical and Probabilistic Aspects. London, UK: Chapman and Hall, pp. 40–123.
Rugman-Jones PF, Hoddle MS, Mound LA, Stouthamer R (2006). Molecular identification key for pest species of Scirtothrips (Thysanoptera: Thripidae). J Econ Entomol 99: 1813–1819.
Schliephake G (2001). Verzeichnis der Thysanoptera (Fransenflügler)
– Physopoda (Blasenfüße) – Thrips Deutschlands. Entomof Germ 5: 91–106 (in German). Schliephake G, Klimt K (1979). Thysanoptera. Die Tierwelt Deutschlands 66. Jena, Germany: G. Fisher Verlag (in German).
Schuetz I, Breitenstein A, Moritz G (2010). Computer-based identification key for pest thrips and tospoviruses by use of LucID 4, ITS-RFLP and low-density BioChip technology. In: Persley D, Wilson C, Thomas J, Sharman M, Tree D, editors. Proceedings of the IXth International Symposium on Thysanoptera and Tospoviruses, 31 August – 4 September, 200 J Insect Sci 10: 1–58.
Solis-Sanchez LO, Castañeda-Miranda R, García-Escalante JJ, Torres-Pacheco I, Guevara-González RG, Castañeda-Miranda CL, Alaniz-Lumbreras PD (2001). Scale invariant feature approach for insect monitoring. Comp Electron Agr 75: 92–99.
Taylor M (2010). Latest lucid identification tools. In: Persley D, Wilson C, Thomas J, Sharman M, Tree D, editors. Proceedings of the IXth International Symposium on Thysanoptera and Tospoviruses, 31 August – 4 September, 2009. J Insect Sci 10: 1–
Toda S, Komazaki S (2002). Identification of thrips species (Thysanoptera: Thripidae) on Japanese fruit trees by polymerase chain reaction and restriction fragment length polymorphism of the ribosomal ITS2 region. B Entomol Res 92: 359–363.
Tohidi M, Sadeghi M, Mousavi SR, Mireei SA (2012). Artificial neural network modeling of process and product indices in deep bed drying of rough rice. Turk J Agric For 36: 738–748.
Vaňhara J, Murárikova N, Malenovskı 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.
Vierbergen G, Kucharczyk H, Kirk WDJ (2010). A key to the second instar larvae of the Thripidae of the Western Palaearctic region (Thysanoptera). Tijdschr Entomol 153: 99–160.
Weeks PJD, Gaston KJ (1997). Image analysis, neural networks, and the taxonomic impediment to biodiversity studies. Biodivers Conserv 6: 263–274.
Zhang WJ, Barrion AT (2006). Function approximation and documentation of sampling data using artificial neural networks. Environ Monit Assessment 122: 185–201. zur Strassen R (2003). Die terebranten Thysanopteren Europas und des Mittelmeer-Gebietes. Die Tierwelt Deutschlands 74: 1–271 (in German).