Pollen Grains Classification with a Deep Learning System GPU-Trained
Keywords:
Convolutional Neural Network, Deep Learning, Graphics Processing Unit, Transfer LearningAbstract
Traditional approaches to automatic classification of pollen grains consisted of classifiers working with feature extractors designed by experts, which modeled pollen grains aspects of special importance for biologists. Recently, a Deep Learning (DL) algorithm called Convolutional Neural Network (CNN) has shown a great improvement in performance in many computer vision tasks such as classification, due to this great performance the computational requirements have increased considerably; therefore, it is advisable to use new platforms such as the Graphics Processing Unit (GPU), which offer large computational resources for the development of new systems with CNN. This paper presents the GPU-Trained implementation of a DL system with the CNN algorithm, proposing a CNN model capable of running on a GPU in real-time for the automatic classification of 19 different pollen grains belonging to 14 different families, which are found in high concentrations in Mexico, and which are large interest in areas such as beekeeping, paleoecology, botany, allergology, agriculture among others. These areas seek to improve the collection of palynological data in terms of time and accuracy. In order to evaluate our model, evaluation tests were performed in the NVIDIA Jetson TX2 Developer Kit GPU. Experimental results achieves around 90% in CCR and Sensitivity in the proposed model. Additionally, the proposed model works at a processing speed of 6,826 Frames Per Second (FPS) and has approximately 50% fewer parameters than reported in related works.
Downloads
References
M. B. Ruiz Zapata and M. García Anton, “La Palinología y su Aplicación al Estudio de la Reconstrucción de la Vegetación durante el Cuaternario: Consideraciones Generales,” Revista de Geología, no.1, pp. 77-84, 1987. [Online]. Available: https://ebuah.uah.es/dspace/handle/10017/9596
M. A. Magaña Magaña, L. L. Salazar Barrientos, J. R. Sanginés García and M. E. Tavera Cortés, “Productividad de la Apicultura en México y su Impacto sobre la Rentabilidad,” Revista Mexicana de Ciencias Agrícolas, vol.7, no.5, August 2016. [Online]. Available: http://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S2007-09342016000501103
E. Ramírez-Arriaga, A. Martínez-Bernal, N. Ramírez Maldonado and E. Martínez-Hernández, “Análisis Palinológico de Mieles y Cargas de Polen de Apis mellifera (Apidae) de la Región Centro y Norte del Estado de Guerrero, México,” Botanical Sciences, vol.94, no.1, pp. 141-156, March 2016. [Online]. Available: http://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S2007-42982016000100141
F. M. Salinas-Márquez, J. G. Flores-Trujillo, J. Helenes, M. A. Téllez-Duarte and F. J. Aranda-Manteca, “Paleoecología y Cronoestratigrafía de las Diatomeas del Miembro Los Indios en la Mesa La Misión, del Mioceno de Baja California, México,” Sociedad Geológica Mexicana & Instituto de Geología UNAM, vol.68, no.3, pp. 537-552, December 2016. [Online]. Available: http://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S1405-33222016000300537
E. Ortiz-Torres, A. Carballo-Carballo, A. Muñoz-Orozco and F. B. González-Cossio, “Efecto de la Dispersión de Polen en la Producción de Semilla de Maíz, en Texcoco, México,” Agronomía Mesoamericana, vol. 21, no. 2, pp.289-297. December 2010. [Online]. Available: https://www.scielo.sa.cr/scielo.php?pid=S1659-13212010000200008&script=sci_arttext
T. González-Mendoza, M. Bedolla-Barajas, T. R. Bedolla-Pulido, J. Morales-Romero, N. A. Pulido-Guillén, S. Lerma-Partida and C. Meza-López, “La Prevalencia de Rinitis Alérgica y Dermatitis Atópica en Adolescentes Tardíos Difiere de Acuerdo con el Sexo,” Revista Alergia México, vol. 66, no. 2, pp.147-153, June 2019. [Online]. Available: http://revistaalergia.mx/ojs/index.php/ram/article/view/521
World Allergy Organization. “In-Depth Review of Allergic Rhinitis,” WAO, Milwaukee, MI, USA, Jun. 2015. [Online]. Available: https://www.worldallergy.org/education-and-programs/education/allergic-disease-resource-center/professionals/in-depth-review-of-allergic-rhinitis
O. Pfaar, K. Karatzas, K. Bastl, U. Werger, J. Buters, U. Darsow, P. Demoly, S. Durham, C. Galán, R. Gehrig, R. van Wijk, L. Jacobsen, N. Katsifarakis, L. Klimek, A. Saarto, M. Sofiev, M. Thibaudon, B. Werchan and K. Bergmann, “Pollen season is reflected on symptom load for grass and birch pollen-induced allergic rhinitis in different geographic areas-An EAACI Task Force Report ,” Allergy, vol. 75, no. 5, pp. 1099-1106, May 2020.
K. A. Holt and K. D. Bennett, “Principles and Methods for Automated Palynology,” New Phytologist Trust, vol. 203, pp. 735-742, April 2014.
S. S. Alotaibi, S. M. Sayed, M. Alosaimi, R. Alharthi, A. Banjar, N. Abdulqader and R. Alhamed, “Pollen Molecular Biology: Applications in the Forensic Palynology and Future Prospects: A Review,” Saudi Journal of Biological Sciences, vol. 27, no. 5, pp. 1185-1190, May 2020.
Ian Goodfellow, Yoshua Bengio, Aaron Courville, “Convolutional Networks,” in Deep Learning, Cambridge, Massachusetts, USA, MIT Press 2016, Cap. 9, pp. 326-366. [Online]. Available: http://www.deeplearningbook.org
J. Salas, F. Vidal, and J. Martinez-Trinidad, “Deep Learning: Current State,” IEEE Latin America Transactions, vol. 17, no. 12, pp. 1925-1945 December 2019.
Y. Le Cun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard and L. D. Jackel, “Handwritten Digit Recognition with a Back-Propagation Network,” in Advances in Neural Information Processing Systems 2 (NIPS), 1990, pp. 396-404.
A. Krizhevsky, I. Sutskever and G. E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," in Advances in Neural Information Processing Systems (NIPS), 2012, pp. 1097-1105.
C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke and A. Rabinovich, "Going Deeper with Convolutions," in Proceedings IEEE Conference on Computer Vision and Pattern Recognition, June 2015, pp. 1-9.
K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” arXiv preprint arXiv 1409.1556, 2014.
M. D. Zeiler and R. Fergus, “Visualizing and Understanding Convolutional Networks,” in European Conference on Computer Vision. Springer, 2014, vol. 8689, pp. 818-833.
J. Liu, F. Chen, C. Pan, M. Zhu, X. Zhang, L. Zhang and H. Liao, “A Cascaded Deep Convolutional Neural Network for Joint Segmentation and Genotype Prediction of Brainstem Gliomas,” IEEE Transactions on Biomedical Engineering, vol.65, pp. 1943-1952, September 2018.
A. Cabrera-Ponce, L. Rojas-Pérez, J. Carrasco-Ochoa, J. Martínez-Trinidad and J. Martínez-Carranza, “Gate Detection for Micro Aerial Vehicles Using a Single Shot Detector,” IEEE Latin America Transactions, vol. 17, no. 12, pp. 2045-2052, December 2019.
R. da Silva and A. de Carvalho, “Automatic Classification of Breast Lesions Using Transfer Learning,” IEEE Latin America Transactions, vol. 17, no. 12, pp. 1964-1969 December 2019.
P. Dhabe, P. Vyas, D. Ganeriwal and A. Pathak, “Pattern Classification Using Updated Fuzzy Hyper-Line Segment Neural Network and It’s GPU Parallel Implementation for Large Datasets Using CUDA,” in International Conference on Computing, Analytics and Security Trends (CAST), pp. 24-29, December 2016.
D. S. da Silva, L. N. Balta Quinta, A. Barbosa Gonçalves, H. Pistori and M. R. Borth, “Application of Wavelet Transform in the Classification of Pollen Grains,” African Journal of Agricultural Research, vol. 9, no. 10, pp. 908-913, March 2014.
S. W. Punyasena, D. K. Tcheng, C. Wesseln and P. G. Mueller, “Classifying Black and White Spruce Pollen Using Layered Machine Learning,” New Phytologist Trust, vol. 196, pp. 937-944, September 2012.
M. K. Sobol, L. Scott, S. A. Finkelstein, “Reconstructing Past Biomes States Using Machine Learning and Modern Pollen Assemblages: A Case Study from Southern Africa,” Quaternary Science Reviews, vol. 212, pp. 1-17, April 2019.
C. N. M. Rodrigues, A. Barbosa Gonçalves, G. G. da Silva and H. Pistori, “Evaluation of Machine Learning and Bag of Visual Words Techniques for Pollen Grains Classification,” IEEE Latin America Transactions, vol. 13, no. 10, pp. 3498-3504 October 2015.
A. B. Gonçalves, J. S. Souza, G. G. da Silva, M. P. Cereda, A. Pott, M. H. Naka and H. Pistori, “Feature Extraction and Machine Learning for the Classification of Brazilian Savannah Pollen Grains,” PLoS ONE, vol. 6, no. 11, pp. 1-20, June 2016.
H. Menad, F. Ben-Naoum and A. Amine, “Deep Convolutional Neural Network for Pollen Grains Classification,” in Journée d’Etude sur la Recherche en Informatique (JERI), pp. 22-32, April 2019.
A. Daood, E. Ribeiro and M. Bush, “Pollen Grain Recognition Using Deep Learning,” in International Symposium on Visual Computing, vol. 10072, pp. 321-330, December 2016.
V. Sevillano, K. Holt and J. L. Aznarte, “Precise Automatic Classification of 46 Different Pollen Types with Convolutional Neural Networks,” PLoS ONE , vol. 15, no. 6, pp. 1-15, June 2020.
K. Holt, G. Allen, R. Hodgson, S. Marsland and J. Flenley, “Progress towards an automated trainable pollen location and classifier system for use in the palynology laboratory,” Review of Palaeobotany and Palynology, vol. 167, pp. 175-183, August 2011.
A. R. de Geus, C. A. Barcelos, M. A. Batista and S. F. da Silva, “Large-Scale Pollen Recognition with Deep Learning,” in 27th European Signal Processing Conference (EUSIPCO), 2019, pp. 1-5.
A. Daood, E. Ribeiro and M. Bush, “Sequential Recognition of Pollen Grain Z-Stacks by Combining CNN and RNN,” in The Thirty-First International Florida Artificial Intelligence Research Society Conference (FLAIRS-31), pp. 8-13, 2018.
N. Khanzhina, E. Putin, A. Filchenkov and E. Zamyatina, “Pollen Grain Recognition Using Convolutional Neural Network,” in European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), pp. 409-414, April 2018.
J. Schiele, F. Rabe, M. Schmitt, M. Glaser, F. Häring, J. O. Brunner, B. Bauer, B. Schuller, C. Traidl-Hoffmann and A. Damialis, “Automated Classification of Airborne Pollen using Neural Networks,” in 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 4474-4478, July 2019.
A. Barbosa Gonçalves, (2015): POLEN23E. figshare. Dataset. [Online]. Available: https://doi.org/10.6084/m9.figshare.1525086.v1
A. Rosas-Alvarado, M. Bautista-Huerta and G. Velázquez-Sámano, “Atlas de los Pólenes Alergénicos de Mayor Relevancia en México,” Revista Alergia México, vol. 58, no.3, pp. 162-170. July 2011. [Online]. Available: https://www.elsevier.es/es-revista-revista-alergia-mexico-336-pdf-X0002515111345183
Universidad Nacional Autónoma de México (2019): Red Mexicana de Aerobiología (REMA). [Online]. Available: http://rema.atmosfera.unam.mx/rema/REMA_SEMAFORO.aspx
N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever and R. Salakhutdinov, “Dropout: A Simple Way to Prevent Neural Networks from Overfitting,” Journal of Machine Learning Research, vol. 15, no. 56, pp. 1929-1958, June 2014.
University of California Berkeley (2020): Berkeley Artificial Intelligence Research (BAIR). [Online]. Available:http://dl.caffe.berkeleyvision.org/bvlc_alexnet.caffemodel
Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama and T. Darrell, “Caffe: Convolutional Architecture for Fast Feature Embedding,” arXiv preprint arXiv 1408.5093, August 2014.