Modified osprey algorithm for optimizing capsule neural network in leukemia image recognition DOI Creative Commons

Bingying Yao,

Chao Li, Mehdi Asadi

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: July 4, 2024

Abstract The diagnosis of leukemia is a serious matter that requires immediate and accurate attention. This research presents revolutionary method for diagnosing using Capsule Neural Network (CapsNet) with an optimized design. CapsNet cutting-edge neural network effectively captures complex features spatial relationships within images. To improve the CapsNet's performance, Modified Version Osprey Optimization Algorithm (MOA) has been utilized. Thesuggested approach tested on ALL-IDB database, widely recognized dataset image classification. Comparative analysis various machine learning techniques, including Combined combine MobilenetV2 ResNet18 (MBV2/Res) network, Depth-wise convolution model, hybrid model combines genetic algorithm ResNet-50V2 (ResNet/GA), SVM/JAYA demonstrated superiority our in different terms. As result, proposed robust powerful tool from medical

Language: Английский

FocusAugMix: A Data Augmentation Method for Enhancing Acute Lymphoblastic Leukemia Classification DOI Creative Commons
Tanzilal Mustaqim, Chastine Fatichah, Nanik Suciati

et al.

Intelligent Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 200512 - 200512

Published: March 1, 2025

Language: Английский

Citations

0
Modified osprey algorithm for optimizing capsule neural network in leukemia image recognition DOI Creative Commons

Bingying Yao,

Chao Li, Mehdi Asadi

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: July 4, 2024

Abstract The diagnosis of leukemia is a serious matter that requires immediate and accurate attention. This research presents revolutionary method for diagnosing using Capsule Neural Network (CapsNet) with an optimized design. CapsNet cutting-edge neural network effectively captures complex features spatial relationships within images. To improve the CapsNet's performance, Modified Version Osprey Optimization Algorithm (MOA) has been utilized. Thesuggested approach tested on ALL-IDB database, widely recognized dataset image classification. Comparative analysis various machine learning techniques, including Combined combine MobilenetV2 ResNet18 (MBV2/Res) network, Depth-wise convolution model, hybrid model combines genetic algorithm ResNet-50V2 (ResNet/GA), SVM/JAYA demonstrated superiority our in different terms. As result, proposed robust powerful tool from medical

Language: Английский

Citations

0