Deep Learning Methods for Improving Pollen Monitoring.

Elżbieta Kubera,Magdalena Skrzypiec,Krystyna Piotrowska-Weryszko,Agnieszka Kubik-Komar

doi:10.3390/s21103526

Abstract

The risk of pollen-induced allergies can be determined and predicted based on data derived from pollen monitoring. Hirst-type samplers are sensors that allow airborne pollen grains to be detected and their number to be determined. Airborne pollen grains are deposited on adhesive-coated tape, and slides are then prepared, which require further analysis by specialized personnel. Deep learning can be used to recognize pollen taxa based on microscopic images. This paper presents a method for recognizing a taxon based on microscopic images of pollen grains, allowing the pollen monitoring process to be automated. In this research, a deep CNN (convolutional neural network) model was built from scratch. Publicly available deep neural network models, pre-trained on image data (not including microscopic pictures), were also used. The results show that even a simple deep learning model produces quite good results when the classification of pollen grain taxa is performed directly from the images. The best deep learning model achieved 97.88% accuracy in the difficult task of recognizing three types of pollen grains (birch, alder, and hazel) with similar structures. The derived models can be used to build a system to support pollen monitoring experts in their work.

Highlights

Deep learning is used to recognize pollen taxa based on microscopic images
We evaluate the effectiveness of some convolutional neural network (CNN) by comparing their accuracy in recognizing pollen grains from microscopic images collected in the ABCPollen database
The results show that the proposed SimpleModel achieves 80% accuracy in the classification of the taxa

Summary

Introduction

Information on the amounts of these allergens in the air comes from pollen monitoring, where the volumetric method using Hirst-type samplers is employed [2]. This method is recommended by the International Association for Aerobiology, and is commonly used in pollen monitoring centers across Poland. Each piece of tape must be analyzed by appropriately trained staff, who identify and count the pollen grains under a microscope. This is a difficult and timeconsuming task, because the differences in the morphological structures of pollen grains of some taxa are very small. There is a need to automate, or at least facilitate, this process

Objectives

Methods

Discussion

Conclusion