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...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9382253/ |
| _version_ | 1818737372779511808 |
|---|---|
| author | Ung Yang Seungwon Oh Seung Gon Wi Bok-Rye Lee Sang-Hyun Lee Min-Soo Kim |
| author_facet | Ung Yang Seungwon Oh Seung Gon Wi Bok-Rye Lee Sang-Hyun Lee Min-Soo Kim |
| author_sort | Ung Yang |
| collection | DOAJ |
| description | 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 <inline-formula> <tex-math notation="LaTeX">$30\times30$ </tex-math></inline-formula> 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. |
| first_indexed | 2024-12-18T00:52:00Z |
| format | Article |
| id | doaj.art-7059f321b827439282acc4cce6c8d98c |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-18T00:52:00Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-7059f321b827439282acc4cce6c8d98c2022-12-21T21:26:38ZengIEEEIEEE Access2169-35362021-01-019459934599910.1109/ACCESS.2021.30676779382253Classification of Germination Images of Pear Pollen Using Random Forest and Convolution Neural Network ModelsUng Yang0https://orcid.org/0000-0001-8412-4518Seungwon Oh1https://orcid.org/0000-0003-3757-7631Seung Gon Wi2https://orcid.org/0000-0002-0731-8674Bok-Rye Lee3https://orcid.org/0000-0002-1912-0390Sang-Hyun Lee4https://orcid.org/0000-0003-4895-1123Min-Soo Kim5https://orcid.org/0000-0001-7391-9411Asian Pear Research Institute, Chonnam National University, Gwangju, South KoreaDepartment of Mathematics and Statistics, Chonnam National University, Gwangju, Republic of KoreaAsian Pear Research Institute, Chonnam National University, Gwangju, South KoreaAsian Pear Research Institute, Chonnam National University, Gwangju, South KoreaAsian Pear Research Institute, Chonnam National University, Gwangju, South KoreaDepartment of Mathematics and Statistics, Chonnam National University, Gwangju, Republic of KoreaVerifying 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 <inline-formula> <tex-math notation="LaTeX">$30\times30$ </tex-math></inline-formula> 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.https://ieeexplore.ieee.org/document/9382253/ClassificationCNNimagepollenRFvariables |
| spellingShingle | Ung Yang Seungwon Oh Seung Gon Wi Bok-Rye Lee Sang-Hyun Lee Min-Soo Kim Classification of Germination Images of Pear Pollen Using Random Forest and Convolution Neural Network Models IEEE Access Classification CNN image pollen RF variables |
| title | Classification of Germination Images of Pear Pollen Using Random Forest and Convolution Neural Network Models |
| title_full | Classification of Germination Images of Pear Pollen Using Random Forest and Convolution Neural Network Models |
| title_fullStr | Classification of Germination Images of Pear Pollen Using Random Forest and Convolution Neural Network Models |
| title_full_unstemmed | Classification of Germination Images of Pear Pollen Using Random Forest and Convolution Neural Network Models |
| title_short | Classification of Germination Images of Pear Pollen Using Random Forest and Convolution Neural Network Models |
| title_sort | classification of germination images of pear pollen using random forest and convolution neural network models |
| topic | Classification CNN image pollen RF variables |
| url | https://ieeexplore.ieee.org/document/9382253/ |
| work_keys_str_mv | AT ungyang classificationofgerminationimagesofpearpollenusingrandomforestandconvolutionneuralnetworkmodels AT seungwonoh classificationofgerminationimagesofpearpollenusingrandomforestandconvolutionneuralnetworkmodels AT seunggonwi classificationofgerminationimagesofpearpollenusingrandomforestandconvolutionneuralnetworkmodels AT bokryelee classificationofgerminationimagesofpearpollenusingrandomforestandconvolutionneuralnetworkmodels AT sanghyunlee classificationofgerminationimagesofpearpollenusingrandomforestandconvolutionneuralnetworkmodels AT minsookim classificationofgerminationimagesofpearpollenusingrandomforestandconvolutionneuralnetworkmodels |