Cross validation analysis of convolutional neural network variants with various white blood cells datasets for the classification task
White Blood Cells (WBCs) analysis is an important procedure to detect diseases is that closely related to human immunity system. Manual WBCs analysis is laborious and hence computer aided system (CAD) is a better option to alleviate the shortcoming. Since conventional segmentation�classificati...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/6898/1/J14007_ae0dfb382d7a292ca03249e26f23cd8c.pdf |
| _version_ | 1825710274891481088 |
|---|---|
| author | Mohd Safuan, Syadia Nabilah Md Tomari, Mohd Razali Wan Zakaria, Wan Nurshazwani |
| author_facet | Mohd Safuan, Syadia Nabilah Md Tomari, Mohd Razali Wan Zakaria, Wan Nurshazwani |
| author_sort | Mohd Safuan, Syadia Nabilah |
| collection | UTHM |
| description | White Blood Cells (WBCs) analysis is an important procedure to
detect diseases is that closely related to human immunity system. Manual
WBCs analysis is laborious and hence computer aided system (CAD) is a better
option to alleviate the shortcoming. Since conventional segmentation�classification approach is tedious to configure, a Convolutional Neural Network
(CNN) become recent trend for WBCs classification. Previously, there are
many works proposed for WBCs identification. However, the models that can
be generalised to works well among various datasets is remain vague. In this
paper, an analysis of various CNN models which are simple Alexnet, embedded
friendly Mobilenet, inception based Googlenet, systematic architecture VGG�16 and skip connection based model (Resnet & Densenet), are tested with three
major WBCs datasets (Kaggle, LISC and IDB-2). From the rigorous experi�ments, it can be concluded that simple CNN model of Alexnet performs well
across all three datasets with 98.08% accuracy on Kaggle, 96.34% accuracy on
IDB-2 and 84.52% on LISC. This outcome can be utilise as a basis to improve
the CNN classification model that can be generalize to works under various
WBCs datasets. |
| first_indexed | 2024-03-05T21:55:08Z |
| format | Article |
| id | uthm.eprints-6898 |
| institution | Universiti Tun Hussein Onn Malaysia |
| language | English |
| last_indexed | 2024-03-05T21:55:08Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | uthm.eprints-68982022-04-12T06:36:45Z http://eprints.uthm.edu.my/6898/ Cross validation analysis of convolutional neural network variants with various white blood cells datasets for the classification task Mohd Safuan, Syadia Nabilah Md Tomari, Mohd Razali Wan Zakaria, Wan Nurshazwani TP248.13-248.65 Biotechnology White Blood Cells (WBCs) analysis is an important procedure to detect diseases is that closely related to human immunity system. Manual WBCs analysis is laborious and hence computer aided system (CAD) is a better option to alleviate the shortcoming. Since conventional segmentation�classification approach is tedious to configure, a Convolutional Neural Network (CNN) become recent trend for WBCs classification. Previously, there are many works proposed for WBCs identification. However, the models that can be generalised to works well among various datasets is remain vague. In this paper, an analysis of various CNN models which are simple Alexnet, embedded friendly Mobilenet, inception based Googlenet, systematic architecture VGG�16 and skip connection based model (Resnet & Densenet), are tested with three major WBCs datasets (Kaggle, LISC and IDB-2). From the rigorous experi�ments, it can be concluded that simple CNN model of Alexnet performs well across all three datasets with 98.08% accuracy on Kaggle, 96.34% accuracy on IDB-2 and 84.52% on LISC. This outcome can be utilise as a basis to improve the CNN classification model that can be generalize to works under various WBCs datasets. 2022 Article PeerReviewed text en http://eprints.uthm.edu.my/6898/1/J14007_ae0dfb382d7a292ca03249e26f23cd8c.pdf Mohd Safuan, Syadia Nabilah and Md Tomari, Mohd Razali and Wan Zakaria, Wan Nurshazwani (2022) Cross validation analysis of convolutional neural network variants with various white blood cells datasets for the classification task. International Journal of Online and Biomedical Engineering, 18 (2). pp. 123-140. |
| spellingShingle | TP248.13-248.65 Biotechnology Mohd Safuan, Syadia Nabilah Md Tomari, Mohd Razali Wan Zakaria, Wan Nurshazwani Cross validation analysis of convolutional neural network variants with various white blood cells datasets for the classification task |
| title | Cross validation analysis of convolutional neural network variants with various white blood cells datasets for the classification task |
| title_full | Cross validation analysis of convolutional neural network variants with various white blood cells datasets for the classification task |
| title_fullStr | Cross validation analysis of convolutional neural network variants with various white blood cells datasets for the classification task |
| title_full_unstemmed | Cross validation analysis of convolutional neural network variants with various white blood cells datasets for the classification task |
| title_short | Cross validation analysis of convolutional neural network variants with various white blood cells datasets for the classification task |
| title_sort | cross validation analysis of convolutional neural network variants with various white blood cells datasets for the classification task |
| topic | TP248.13-248.65 Biotechnology |
| url | http://eprints.uthm.edu.my/6898/1/J14007_ae0dfb382d7a292ca03249e26f23cd8c.pdf |
| work_keys_str_mv | AT mohdsafuansyadianabilah crossvalidationanalysisofconvolutionalneuralnetworkvariantswithvariouswhitebloodcellsdatasetsfortheclassificationtask AT mdtomarimohdrazali crossvalidationanalysisofconvolutionalneuralnetworkvariantswithvariouswhitebloodcellsdatasetsfortheclassificationtask AT wanzakariawannurshazwani crossvalidationanalysisofconvolutionalneuralnetworkvariantswithvariouswhitebloodcellsdatasetsfortheclassificationtask |