2022
DOI: 10.3991/ijoe.v18i02.27321
|View full text |Cite
|
Sign up to set email alerts
|

Cross Validation Analysis of Convolutional Neural Network Variants with Various White Blood Cells Datasets for the Classification Task

Abstract: 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 gen… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2022
2022
2025
2025

Publication Types

Select...
5

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(4 citation statements)
references
References 20 publications
0
4
0
Order By: Relevance
“…It is a type of CNN implemented especially for mobile vision systems and in-vehicle applications. The basic idea behind MobileNet is to use deep separable convolutions to compose simpler and lightweight deep neural networks that can have low latency for mobile and embedded devices [23] DenseNet201. It is a type of CNN that uses dense connections between these different layers, through dense blocks, where all the layers are directly connected with each other.…”
Section: Results Comparisonmentioning
confidence: 99%
“…It is a type of CNN implemented especially for mobile vision systems and in-vehicle applications. The basic idea behind MobileNet is to use deep separable convolutions to compose simpler and lightweight deep neural networks that can have low latency for mobile and embedded devices [23] DenseNet201. It is a type of CNN that uses dense connections between these different layers, through dense blocks, where all the layers are directly connected with each other.…”
Section: Results Comparisonmentioning
confidence: 99%
“…Additionally, [2] projected a deep learning-based classification model using the RDO-GDRL network, which [3] utilized CNN for WBC identification and achieved an accuracy of 96.78%. [4] compared different CNN models, where Alexnet outperformed others with high accuracy across multiple datasets. [5] delved into the application of CNN in radiology tasks and discussed future directions and challenges.…”
Section: Related Workmentioning
confidence: 99%
“…The average of the values obtained in each division is the performance metric given by the k-fold cross validation. This technique is computationally expensive, but it does not waste a lot of data (unlike defining an arbitrary validation set) and has huge advantages in problems such as inverse inference or in situations where we have a dataset with small number of samples [31].…”
Section: Stratified Cross Validationmentioning
confidence: 99%