Advanced CNN Architectures for Pollen Classification: Design and Comprehensive Evaluation

References

• Beggs, P. J. 2017. Allergen aerosol from pollen-nucleated precipitation: A novel thunderstorm asthma trigger. Atmospheric environment 152:455–61. doi:10.1016/j.atmosenv.2016.12.045.
   Web of Science ®Google Scholar
• Bennett, K. D., and K. J. Willis. 2002. Pollen. In Tracking environmental change using lake sediments. developments in paleoenvironmental research, J. P. Smol, H. J. B. Birks, W. M. Last, R. S. Bradley, and K. Alverson. ed., vol. 3, Dordrecht: Springer. 10.1007/0-306-47668-1\_2
   Google Scholar
• Boldeanu, M., H. Cucu, C. Burileanu, and L. Marmureanu. 2021. Multi-Input convolutional neural networks for automatic pollen classification. Applied Sciences 11 (24):11707. doi:10.3390/app112411707.
   Google Scholar
• Boldeanu, M., M. González-Alonso, H. Cucu, C. Burileanu, J. M. Maya-Manzano, and J. T. M. Buters. 2022. Automatic pollen classification and segmentation using u-nets and synthetic data. IEEE Access 10:73675–84. doi:10.1109/ACCESS.2022.3189012.
   Web of Science ®Google Scholar
• Burbach, G. J., L. M. Heinzerling, G. Edenharter, C. Bachert, C. Bindslev-Jensen, S. Bonini, J. Bousquet, L. Bousquet-Rouanet, P. J. Bousquet, M. Bresciani, et al. 2009. GA2LEN skin test study II: Clinical relevance of inhalant allergen sensitizations in Europe. Allergy. 64(10):1507–15. doi:10.1111/j.1398-9995.2009.02089.x.
   PubMed Web of Science ®Google Scholar
• Buters, J. T. M., C. Antunes, A. Galveias, K. C. Bergmann, M. Thibaudon, C. Galan, C. Schmidt-Weber, and J. Oteros. 2018. Pollen and spore monitoring in the world. Clinical and Translational Allergy 8 (1):9. PMID: 29636895; PMCID: PMC5883412. doi:10.1186/s13601-018-0197-8.
   PubMedGoogle Scholar
• Buters, J., B. Clot, C. Galán, R. Gehrig, S. Gilge, F. Hentges, D. O’Connor, B. Sikoparija, C. Skjoth, F. Tummon, et al. 2022. Automatic detection of airborne pollen: An overview. Aerobiologia. doi:10.1007/s10453-022-09750-x.
   Web of Science ®Google Scholar
• Crouzy, B., G. Lieberherr, F. Tummon, and B. Clot. 2022. False positives: Handling them operationally for automatic pollen monitoring. Aerobiologia 38 (3):429–32. doi:10.1007/s10453-022-09757-4.
   Web of Science ®Google Scholar
• Culley, T. M., S. G. Weller, and A. K. Sakai. 2002. The evolution of wind pollination in angiosperms. Trends in Ecology & Evolution 17 (8):361–69. doi:10.1016/S0169-5347(02)02540-5.
   Web of Science ®Google Scholar
• Dahl, A., C. Galán, L. Hajkova, A. Pauling, B. Sikoparija, M. Smith, and D. Vokou. 2013. The onset, course and intensity of the pollen season. In Allergenic pollen: A review of the production, release, distribution and health impacts, ed. M. Sofiev and C.-K. Bergman, 29–70. pp272. Springer Verlag. doi: 10.1007/978-94-007-4881-1\_3.
   Google Scholar
• D’Amato, G., L. Cecchi, S. Bonini, C. Nunes, I. Annesi-Maesano, H. Behrendt, G. Liccardi, T. Popov, and P. van Cauwenberge. 2007. Allergenic pollen and pollen allergy in Europe. Allergy 62 (9):976–90. doi:10.1111/j.1398-9995.2007.01393.x.
   PubMed Web of Science ®Google Scholar
• de Weger, L. A., P. T. W. van Hal, B. Bos, F. Molster, M. Mostert, and P. S. Hiemstra. 2021. Personalized pollen monitoring and symptom scores: A feasibility study in grass pollen allergic patients. Frontiers in Allergy 2:628400. doi:10.3389/falgy.2021.628400.
   PubMedGoogle Scholar
• He, K., X. Zhang, S. Ren, and J. Sun. 2016. Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770–78. doi: 10.1109/cvpr.2016.90
   Google Scholar
• Hirst, J. M. 1952. An automatic volumetric spore trap. The Annals of Applied Biology 39 (2):257–65. doi:10.1111/j.1744-7348.1952.tb00904.x.
   Web of Science ®Google Scholar
• Hsiao, T. Y., Y. C. Chang, H. H. Chou, and C. T. Chiu. 2019. Filter-based deep-compression with global average pooling for convolutional networks. Journal of Systems Architecture 95:9–18. doi:10.1016/j.sysarc.2019.02.008.
   Web of Science ®Google Scholar
• Huffman, J. A., A. E. Perring, N. J. Savage, B. Clot, B. Crouzy, F. Tummon, O. Shoshanim, B. Damit, J. Schneider, V. Sivaprakasam, et al. 2019. Real-time sensing of bioaerosols: Review and current perspectives. Aerosol Science and Technology. 54(5):1–56. doi:10.1080/02786826.2019.166472.
   Web of Science ®Google Scholar
• Kasprzyk, I., B. Ortyl, and A. Dulska-Jez. 2014. Relationships among weather parameters, airborne pollen and seed crops of Fagus and Quercus in Poland. Agricultural and Forest Meteorology 197:111–22. doi:10.1016/j.agrformet.2014.05.015.
   Web of Science ®Google Scholar
• Kawashima, S., B. Clot, T. Fujita, Y. Takahashi, and K. Nakamura. 2007. An algorithm and a device for counting airborne pollen automatically using laser optics. Atmospheric Environment, 41(36), 7987–7993. doi:10.1016/j.atmosenv.2007.09.019
   Web of Science ®Google Scholar
• Krizhevsky, A., I. Sutskever, and G. E. Hinton. 2012. ImageNet classification with deep convolutional neural networks. Proceedings of the 2012 Advances in Neural Information Processing Systems 25 (NIPS). doi:10.1145/3065386.
   Google Scholar
• Larsson, G., M. Maire, and G. Shakhnarovich. 2016. FractalNet: Ultra-Deep Neural Networks Without Residuals doi:10.48550/arXiv.1605.07648.
   Google Scholar
• Matavulj, P., S. Brdar, M. Racković, B. Sikoparija, and I. N. Athanasiadis. 2021. Domain adaptation with unlabeled data for model transferability between airborne particle identifiers. 17th International Conference on Machine Learning and Data Mining (MLDM 2021), New York, USA. doi: 10.5281/zenodo.5574164
   Google Scholar
• Matavulj, P., A. Cristofori, F. Cristofolini, E. Gottardini, S. Brdar, and B. Sikoparija. 2022. Integration of reference data from different rapid-E devices supports automatic pollen detection in more locations. The Science of the Total Environment 158234. doi:10.1016/j.scitotenv.2022.158234.
   PubMed Web of Science ®Google Scholar
• O’Connor, D. J., D. A. Healy, S. Hellebust, J. T. M. Buters, and J. R. Sodeau. 2014. Using the wibs-4 (waveband integrated bioaerosol sensor) technique for the on-line detection of pollen grains. Aerosol Science and Technology 48 (4):341–49. doi: 10.1080/02786826.2013.872768.
   Web of Science ®Google Scholar
• Oteros, J., F. Orlandi, H. García-Mozo, F. Aguilera, A. B. Dhiab, T. Bonofiglio, M. Abicou, L. Ruiz-Valenzuela, M. Mar Del Trigo, C. Diaz de la Guardia, et al. 2014. Better prediction of Mediterranean olive production using pollen-based models. Agronomy for Sustainable Development 34:685–94. doi:10.1007/s13593-013-0198-x.
   Web of Science ®Google Scholar
• Oteros, J., A. Weber, S. Kutzora, J. Rojo, S. Heinze, C. Herr, R. Gebauer, C. B. Schmidt-Weber, and J. T. M. Buters. 2020. An operational robotic pollen monitoring network based on automatic image recognition. Environmental Research 191:110031. doi:10.1016/j.envres.2020.110031.
   PubMed Web of Science ®Google Scholar
• Plaza, M. P., F. Kolek, V. Leier-Wirtz, J. O. Brunner, C. Traidl-Hoffmann, and A. Damialis. 2022. Detecting airborne pollen using an automatic, real-time monitoring system: Evidence from two sites. International Journal of Environmental Research and Public Health 19 (4):2471. doi:10.3390/ijerph19042471.
   PubMed Web of Science ®Google Scholar
• Sauliene, I., L. Šukienė, G. Daunys, G. Valiulis, L. Vaitkevičius, P. Matavulj, S. Brdar, M. Panic, B. Sikoparija, B. Clot, et al. 2019. Automatic pollen recognition with the rapid-E particle counter: The first-level procedure, experience and next steps, atmos. Atmospheric Measurement Techniques. 12(6):3435–52. doi:10.5194/amt-12-3435-2019.
   Web of Science ®Google Scholar
• Sauvageat, E., Y. Zeder, K. Auderset, B. Calpini, B. Clot, B. Crouzy, T. Konzelmann, G. Lieberherr, F. Tummon, and K. Vasilatou. 2020. Real-time pollen monitoring using digital holography. Atmospheric Measurement Techniques 13 (3):1539–50. doi:10.5194/amt-13-1539-2020.
   Web of Science ®Google Scholar
• Schiele, J., F. Rabe, M. Schmitt, M. Glaser, F. Haring, J. O. Brunner, B. Bauer, B. Schuller, C. Traidl-Hoffmann, and A. Damialis. 2019. Automated classification of airborne pollen using neural networks. 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). doi: 10.1109/embc.2019.8856910
   Google Scholar
• Sikoparija, B., P. Matavulj, G. Mimić, M. Smith, Ł. Grewling, and Z. Podrascanin. 2022. Real-time automatic detection of starch particles in ambient air. Agricultural and Forest Meteorology 323:109034. doi:10.1016/j.agrformet.2022.109034.
   PubMed Web of Science ®Google Scholar
• Sikoparija, B., G. Mimic, P. Matavulj, M. Panic, I. Simovic, and S. Brdar. 2019. Short communication: Do we need continuous sampling to capture variability of hourly pollen concentrations? Aerobiologia 36 (1):3–7. doi:10.1007/s10453-019-09575-1.
   Web of Science ®Google Scholar
• Simonyan, K., and A. Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. Proceedings of The International Conference on Learning Representations (ICLR). 75, 6:398–406. doi: 10.48550/arXiv.1409.1556
   Google Scholar
• Sofiev, M. 2019. On possibilities of assimilation of near-real-time pollen data by atmospheric composition models. Aerobiologia 35 (3):523–31. doi:10.1007/s10453-019-09583-1.
   Web of Science ®Google Scholar
• Sothe, C., C. M. De Almeida, M. B. Schimalski, L. E. C. La Rosa, J. D. B. Castro, R. Q. Feitosa, M. Dalponte, C. L. Lima, V. Liesenberg, G. T. Miyoshi, et al. 2020. Comparative performance of convolutional neural network, weighted and conventional support vector machine and random forest for classifying tree species using hyperspectral and photogrammetric data. GIScience & Remote Sensing. 57(3):1–26. doi:10.1080/15481603.2020.1712102.
   Web of Science ®Google Scholar
• Srivastava, R. K., K. Greff, and J. Schmidhuber. 2015. Training very deep networks. In proceedings of the 2015 Advances in Neural Information Processing Systems (NIPS). doi: 10.48550/arXiv.1507.06228
   Google Scholar
• Szegedy, C., W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. 2015. Going deeper with convolutions. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). doi: 10.1109/cvpr.2015.7298594
   Google Scholar
• Szegedy, C., V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna. 2016. Rethinking the inception architecture for computer vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). doi:10.1109/cvpr.2016.308
   Google Scholar
• Tesendic, D., D. Boberic-Krsticev, P. Matavulj, S. Brdar, M. Panic, V. Minic, and B. Sikoparija. 2020. RealForall: Real-time system for automatic detection of airborne pollen. Enterprise Information Systems 16 (5). doi:10.1080/17517575.2020.1793391.
   Web of Science ®Google Scholar
• Tummon, F., S. Adamov, B. Clot, B. Crouzy, M. Gysel-Beer, S. Kawashima, G. Lieberherr, J. Manzano, E. Markey, A. Moallemi, et al. 2021. A first evaluation of multiple automatic pollen monitors run in parallel. Aerobiologia. doi:10.1007/s10453-021-09729-0.
   Web of Science ®Google Scholar
• Viertel, P., and M. König. 2022. Pattern recognition methodologies for pollen grain image classification: A survey. Machine Vision and Applications 33 (1):18. doi:10.1007/s00138-021-01271-w.
   Web of Science ®Google Scholar
• Xie, S., R. Girshick, P. Dollar, Z. Tu, and K. He. 2017. Aggregated residual transformations for deep neural networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). doi: 10.1109/cvpr.2017.634
   Google Scholar
• Zagoruyko, S., and N. Komodakis. 2016. Wide residual networks. Proceedings the British Machine Vision Conference .87.1–12. doi:10.48550/arXiv.1605.07146.
   Google Scholar
• Ziska, L., K. Knowlton, C. Rogers, D. Dalan, N. Tierney, M. A. Elder, W. Filley, J. Shropshire, L. B. Ford, C. Hedberg, et al. 2011. Recent warming by latitude associated with increased length of ragweed pollen season in central North America. Proceedings of the National Academy of Sciences. 108(10):4248e4251. doi:10.1073/pnas.1014107108.
   Web of Science ®Google Scholar