Artifcial neural networks in online semiautomated pest discriminability: an applied case with 2 Trips species

In conclusion, the use of an optimal 3-layer ANN architecture (17, 4, 1) enables fast andreliable 100% classifcation as proven during the extensive verifcation process.

📌 3 Key Takeaways

🎯

Objective & Hypothesis:Being faced with practical problems in pest identifcation, we present a methodical paper based on artifcial neural networksto discriminate morphologically very similar species, Trips sambuci Heeger, 1854 and Trips fuscipennis Haliday, 1836 (Tysanoptera:Tripinae), as an applied case for more general use.

📊

Key Findings & Data:Statistical analysis of 17characters, measured or determined for each Trips 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, andvisualize diferences between the studied taxa.

💡

Conclusion & Impact:In conclusion, the use of an optimal 3-layer ANN architecture (17, 4, 1) enables fast andreliable 100% classifcation as proven during the extensive verifcation process.

🔬Design:Modeling & Simulation

📍Scope:Comprehensive Sample

⚙️Variables:Domain Parameters

Abstract

Being faced with practical problems in pest identifcation, we present a methodical paper based on artifcial neural networksto discriminate morphologically very similar species, Trips sambuci Heeger, 1854 and Trips fuscipennis Haliday, 1836 (Tysanoptera:Tripinae), as an applied case for more general use. Te artifcially intelligent system may be successfully applied as a credible, online,semiautomated identifcation tool that extracts hidden information from noisy data, even when the standard characters have muchoverlap and the common morphological keys hint at the practical problem of high morphological plasticity. Statistical analysis of 17characters, measured or determined for each Trips 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, andvisualize diferences between the studied taxa. Te computational strategy applied in this study includes a set of statistical tools (factoranalysis, correlation analysis, principal component analysis, and linear discriminant analysis) followed by the application of a multilayerperceptron artifcial neural network system, which models functions of almost arbitrary complexity. Tis complex approach has proventhe existence of 2 separate species: T. fuscipennis and T. sambuci. All the specimens could be clearly distinguished with 2 distinctsubgroups for each species, determined by sex. In conclusion, the use of an optimal 3-layer ANN architecture (17, 4, 1) enables fast andreliable 100% classifcation as proven during the extensive verifcation process.

🔖

Cite This Article

PROKOP, P., MENDEZ, E. M. P., KUCHARCZYK, H., VANHARA, J., HAVEL, J., DORICOVA, M., FEDOR, P. (2022). Artifcial neural networks in online semiautomated pest discriminability: an applied case with 2 Trips species. Turkish Journal of Agriculture and Forestry, Cilt: 38 - Sayı: 1, 111–124. https://ajindex.com/articles/599490

📄 Full Text PDF Viewer

Open in New Tab ↗

↗New Tab

📄

PDF görüntüleyici hazırlanıyor...

References (1)

Aldrich BT, Magirang EB, Dowell FE, Kambhampati S (2007). Identifcation of termite species and subspecies of the genus Zootermopsis using near-infrared refectance 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. Enfeld, NH, USA: Science Publishers, pp. 123. 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: 2736. Bilgili M (2011). Te use of artifcial neural networks for forecasting the monthly mean soil temperatures in Adana, Turkey. Turk J Agric For 35: 8393. Brunner PC, Fleming C, Frey JE (2002). A molecular identifcation key for economically important thrips species (Tysanoptera: Tripidae) using direct sequencing and a PCR-RFLP-based approach. Agr Forest Entomol 4: 127136. Chiapella J (2000). Te Deschampsia cespitosa complex in central and northern Europe: morphological analysis. Bot J Linn Soc 134: 495512. Clark JY (2003). Artifcial neural networks for species identifcation by taxonomists. Biosystems 72: 131147. Do MT, Harp JM, Norris KC (1999). A test of a pattern recognition system for identifcation of spiders. B Entomol Res 89: 217224. Esteban LG, Fernández FG, de Palacios P, Romero RM, Cano NN (2009). Artifcial neural networks in wood identifcation: the case of two Juniperus species from the Canary islands. IAWA J 30: 8794. Fausett L (1994). Fundamentals of Neural Networks: Architectures, Algorithms and Applications. New York, NY, USA: Prentice Hall. Fedor P, Malenovský I, Vaňhara J, Sierka W, Havel J (2008). Trips (Tysanoptera) identifcation using artifcial neural networks. B Entomol Res 98: 437447. Fedor P, Vaňhara J, Havel J, Malenovský I, Spellerberg I (2009). Artifcial intelligence in pest insect monitoring. Syst Entomol 34: 398400. Frantz G, Mellinger HC (1997). THRIPS, a computerized knowledgebase for the identifcation and management of Trips infesting vegetables in the United States. Proc Fla State Hort Soc 128: 14. Freeman JA, Skapura DM (1992). Neural Network: Algorithm, Applications, and Programming Techniques. Reading, MA, USA: Addison-Wesley. Gaston KJ, ONeill MA (2004). Automated species identifcation: why not? Philos T Roy Soc B 359: 655667. Han R, He Y, Li