Coleoptera Classification Using Convolutional Neural Network and Transfer Learning

Coleoptera Classification Using Convolutional Neural Network and Transfer Learning

© 2021 by IJETT Journal
Volume-69 Issue-5
Year of Publication : 2021
Authors : Jan Carlo T. Arroyo
DOI :  10.14445/22315381/IJETT-V69I5P201

How to Cite?

Jan Carlo T. Arroyo, "Coleoptera Classification Using Convolutional Neural Network and Transfer Learning," International Journal of Engineering Trends and Technology, vol. 69, no. 5, pp. 1-5, 2021. Crossref,

This study presents the use of convolutional neural networks and transfers learning for classifying Coleoptera specimens. The images used as a dataset in this study were gathered from previous research work and various repositories. Four classes were used to train the convolutional neural network, with the Buprestidae, Carabidae, Cerambycidae, and Coccinellidae families. Since the dataset was rather imbalanced, images were preprocessed to augment the dataset and minimize the probability of overfitting. Transfer learning was implemented by using the InceptionV3 pre-trained model. The final layer was retrained using the new dataset while retaining its prior knowledge base. After the training and validation of the new model, an average of 97% classification accuracy was attained.

Beetle Classification, Coleoptera, Convolutional Neural Network, Inception Network, Transfer Learning

[1] S.-Q. Zhang et al., Evolutionary history of Coleoptera revealed by an extensive sampling of genes and species, Nat. Commun., 9(1)(2018) 205, doi: 10.1038/s41467-017-02644-4.
[2] ?. Kajtoch, D. Kubisz, D. Lachowska-Cierlik, and M. A. Mazur, Conservation genetics of endangered leaf-beetle Cheilotoma musciformis populations in Poland, J. Insect Conserv., 17(1)(2013) 67–77 doi: 10.1007/s10841-012-9486-z.
[3] L. Drag and L. Cizek., Successful reintroduction of an endangered veteran tree specialist: conservation and genetics of the Great Capricorn beetle (Cerambyx cerdo), Conserv. Genet., 16(2)(2015) 267–276, doi: 10.1007/s10592-014-0656-2.
[4] M. Jonsell, Old park trees as habitat for saproxylic beetle species, Biodivers. Conserv., 21(3)(2012) 619–642, doi: 10.1007/s10531-011-0203-0.
[5] F. Della Rocca, G. Bogliani, F. T. Breiner, and P. Milanesi, Identifying hotspots for rare species under climate change scenarios: improving saproxylic beetle conservation in Italy, Biodivers. Conserv., 28(2)(2019) 433–449, doi: 10.1007/s10531-018-1670-3.
[6] S. Fattorini and D. M. P. Galassi., Role of urban green spaces for saproxylic beetle conservation: a case study of tenebrionids in Rome, Italy, J. Insect Conserv., 20(4)(2016) 737–745 doi: 10.1007/s10841-016-9900-z.
[7] D. Nolte, A. Schuldt, M. M. Gossner, W. Ulrich, and T. Assmann, Functional traits drive ground beetle community structures in Central European forests: Implications for conservation, Biol. Conserv., 213(2017) 5–12, doi: 10.1016/j.biocon.2017.06.038.
[8] C. Torrejos, A. Cabras, and M. N. Medina., Ground beetles collection ( Coleoptera : Carabidae ) in the Coleoptera Research Center, Davao City, Philippines, J. Trop. Coleopterol., 1(2020) 17–25.
[9] E. Ayan, H. Erbay, and F. Varç?n., Crop pest classification with a genetic algorithm-based weighted ensemble of deep convolutional neural networks, Comput. Electron. Agric., 179(2020) 105809, doi:
[10] C. Wen and D. Guyer., Image-based orchard insect automated identification and classification method, Comput. Electron. Agric., 89(2012) 110–115, doi:
[11] K. Buschbacher, D. Ahrens, M. Espeland, and V. Steinhage., Image-based species identification of wild bees using convolutional neural networks, Ecol. Inform., 55(2020) 101017, doi:
[12] D. Miloševi? et al., Application of deep learning in aquatic bioassessment: Towards automated identification of non-biting midges, Sci. Total Environ., 711(2020) 135160, 2020, doi:
[13] M. Martineau, D. Conte, R. Raveaux, I. Arnault, D. Munier, and G. Venturini, A survey on image-based insect classification, Pattern Recognit., 65(2017) 273–284, doi: 10.1016/j.patcog.2016.12.020.
[14] A. S. Almryad and H. Kutucu., Automatic identification for field butterflies by convolutional neural networks, Eng. Sci. Technol. an Int. J., (2020) 4–10, doi: 10.1016/j.jestch.2020.01.006.
[15] T. De Cesaro Júnior and R. Rieder, Automatic identification of insects from digital images: A survey, Comput. Electron. Agric., 178(2020) 105784, 1–7,doi: 10.1016/j.compag.2020.105784.
[16] M. Tuda and A. I. Luna-Maldonado., Image-based insect species and gender classification by trained, supervised machine learning algorithms, Ecol. Inform., 60(2020) 101135, doi:
[17] B. Maschler, S. Kamm, N. Jazdi, and M. Weyrich., Distributed Cooperative Deep Transfer Learning for Industrial Image Recognition, Procedia CIRP, 93(2020) 437–442, doi:
[18] T. Kasinathan, D. Singaraju, and S. R. Uyyala., Insect classification and detection in field crops using modern machine learning techniques, Inf. Process. Agric., 2020, doi:
[19] Y. Shen, H. Zhou, J. Li, F. Jian, and D. S. Jayas., Detection of stored-grain insects using deep learning, Comput. Electron. Agric., 145(2017) 319–325 (2018), doi: 10.1016/j.compag.2017.11.039.
[20] Y. Kaya and L. Kayci., Application of artificial neural network for automatic detection of butterfly species using color and texture features, Vis. Comput., 30(1)(2014) 71–79 doi: 10.1007/s00371-013-0782-8.
[21] L. Wu et al., A deep learning model to recognize food contaminating beetle species based on elytra fragments, Comput. Electron. Agric., 166(2019) 105002, doi:
[22] C. F. Z. R. Hull, C. N. S. Quiñon, and C. E. Dumdumaya., E-Beetle: A Cross-platform Resource Application for Philippine Coleopterological Network with Image Recognition and Classification using Machine Learning through OpenCV and TensorFlow, Davao City, (2020).
[23] Iowa State University, BugGuide,(2020).
[24] Center for Invasive Species and Ecosystem Health, Invasive Species 101 - An Introduction to Invasive Species., (2018).
[25] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, Dropout: A Simple Way to Prevent Neural Networks from Overfitting, J. Mach. Learn. Res.,15(1)(2014) 1929–1958.
[26] C. Zhang, P. Zhou, C. Li, and L. Liu, A Convolutional Neural Network for Leaves Recognition Using Data Augmentation, in 2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing, (2015) 2143–2150, doi: 10.1109/CIT/IUCC/DASC/PICOM.2015.318.
[27] S. Ye and D. Ke, Application of convolutional neural network in the classification of autofluorescence image of diabetic retina fundus, IJETT Int. J. Eng. Trends Technol., 68(12)(2020) 54–57, 2020, doi: 10.14445/22315381/IJETT-V68I12P210.
[28] S. R. L. Suganthi, U. K. Sneha, and S. Shwetha, Diabetic retinopathy classification using machine learning techniques, IJETT Int. J. Eng. Trends Technol., 68(1)(2020) 51–56, doi: 10.14445/22315381/IJETT-V68I1P207.
[29] M. Vardhana, N. Arunkumar, S. Lasrado, E. Abdulhay, and G. Ramirez-Gonzalez., Convolutional neural network for biomedical image segmentation with hardware acceleration, Cogn. Syst. Res., 50(2018) 10–14, doi: 10.1016/j.cogsys.2018.03.005.
[30] K. Simonyan and A. Zisserman., Very deep convolutional networks for large-scale image recognition., 3rd Int. Conf. Learn. Represent. ICLR 2015 - Conf. Track Proc., (2015) 1–14.
[31] C. Szegedy et al., Going deeper with convolutions, in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2015)1–9, doi: 10.1109/CVPR.2015.7298594.
[32] K. He, X. Zhang, S. Ren, and J. Sun., Deep Residual Learning for Image Recognition, in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2016) 770–778, doi: 10.1109/CVPR.2016.90.
[33] J. Deng, W. Dong, R. Socher, L. Li, K. Li, and L. Fei-Fei, ImageNet: A large-scale hierarchical image database, in 2009 IEEE Conference on Computer Vision and Pattern Recognition, (2009), 248–255, doi: 10.1109/CVPR.2009.5206848.
[34] K. You, M. Long, J. Wang, and M. I. Jordan., How does learning rate decay help modern neural networks?, arXiv, (2019).
[35] A. J. P. Delima, A. M. Sison, and R. P. Medina., A Modified Genetic Algorithm with a New Crossover Mating Scheme, Indones. J. Electr. Eng. Informatics, 7(2)(2019) 165–181, doi: 10.11591/ijeei.v7i2.1047.