Classification of Germination Images of Pear Pollen Using Random Forest and Convolution Neural Network Models

Verifying pollen germination using microscopic images is a difficult task. It is usually time-consuming and may entail reduced accuracy and reproducibility. Therefore, in this study, we used random forest (RF) and convolutional neural network (CNN) models to perform image classification on raw data corresponding to pollens with different germination rates; the data were obtained via flow cytometry. A heat map, which was based on the RF analysis results, showed that the variables that significantly influenced the classification decision between NG and 60G categories were mainly located in the center and top-right regions of the $30\times30$ pixel image. Additionally, a variable importance plot showed that among the 900 input variables, pixel_316 was the variable that contributed the most toward prediction. Gradient-weighted class activation mapping was used to visualize the class activation maps of the CNN model. The bottom-left region of the activation map was activated in the NG image. However, the 60G image showed that not only the bottom-left region but also the top-right region was activated. Both the models classified the input images into NG and 60G categories with high accuracy. However, considering that the RF model does not reflect the characteristics of adjacent variables, the CNN model is more appropriate for classifying pollen germination images corresponding to pollen with various germination rates into distinct classes. Taken together, these results suggest that the CNN model can provide a reliable method for verifying the pollen performance.

[1]  Gerard V. Trunk,et al.  A Problem of Dimensionality: A Simple Example , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Ricardo Navares,et al.  Geographical Imputation of Missing Poaceae Pollen Data via Convolutional Neural Networks , 2019, Atmosphere.

[3]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[4]  S. Wi,et al.  Evaluation of Pear Pollen Germination through Colorimetric and Cytometric Analyses , 2019, Korean Journal of Horticultural Science and Technology.

[5]  Megan Kurka,et al.  Machine Learning Interpretability with H2O Driverless AI , 2019 .

[6]  Abhishek Das,et al.  Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[7]  Andrey Filchenkov,et al.  Pollen grain recognition using convolutional neural network , 2018, ESANN.

[8]  David Boho,et al.  Pollen analysis using multispectral imaging flow cytometry and deep learning. , 2020, The New phytologist.

[9]  P. Brain,et al.  Insect pollinators of conference pear (Pyrus communis L.) and their contribution to fruit quality , 2019 .

[10]  N. Isaac,et al.  Widespread losses of pollinating insects in Britain , 2019, Nature Communications.

[11]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[12]  A. Dafni,et al.  Pollen viability and longevity: Practical, ecological and evolutionary implications , 2000, Plant Systematics and Evolution.

[13]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[14]  Bernd Bischl,et al.  Visualizing the Feature Importance for Black Box Models , 2018, ECML/PKDD.

[15]  J. Biesmeijer,et al.  Global pollinator declines: trends, impacts and drivers. , 2010, Trends in ecology & evolution.

[16]  Gian Luca Foresti,et al.  Meta Random Forests , 2006 .

[17]  José Luis Aznarte,et al.  Precise automatic classification of 46 different pollen types with convolutional neural networks , 2020, bioRxiv.

[18]  Víctor Sevillano,et al.  Improving classification of pollen grain images of the POLEN23E dataset through three different applications of deep learning convolutional neural networks , 2018, PloS one.

[19]  B. Kapralos,et al.  An introduction to digital image processing , 1990 .

[20]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[21]  M. Aizen,et al.  The impact of honey bee colony quality on crop yield and farmers’ profit in apples and pears , 2017 .

[22]  J. Kerr,et al.  Climate change contributes to widespread declines among bumble bees across continents , 2020, Science.

[23]  V. Pinillos,et al.  Artificial Pollination in Tree Crop Production , 2008 .

[24]  Miguel Macías Macías,et al.  Precise Pollen Grain Detection in Bright Field Microscopy Using Deep Learning Techniques , 2019, Sensors.

[25]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[26]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..