Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Sep 30;14(1):22651.
doi: 10.1038/s41598-024-72884-0.

Training artificial neural networks using self-organizing migrating algorithm for skin segmentation

Quoc Bao Diep  1 , Thanh-Cong Truong  2 , Ivan Zelinka  3   4
Affiliations

Training artificial neural networks using self-organizing migrating algorithm for skin segmentation

Quoc Bao Diep et al. Sci Rep. .

Abstract

This study presents an application of the self-organizing migrating algorithm (SOMA) to train artificial neural networks for skin segmentation tasks. We compare the performance of SOMA with popular gradient-based optimization methods such as ADAM and SGDM, as well as with another evolutionary algorithm, differential evolution (DE). Experiments are conducted on the skin dataset, which consists of 245,057 samples with skin and non-skin labels. The results show that the neural network trained by SOMA achieves the highest accuracy (93.18%), outperforming ADAM (84.87%), SGDM (84.79%), and DE (91.32%). The visual evaluation also reveals the SOMA-trained neural network's accurate and reliable segmentation capabilities in most cases. These findings highlight the potential of incorporating evolutionary optimization algorithms like SOMA into the training process of artificial neural networks, significantly improving performance in image segmentation tasks.

Keywords: Artificial neural networks; Computer vision; Optimization algorithm; SOMA; Skin segmentation; Swarm intelligence.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Summary of the operating process of the SOMA algorithm, including three main processes and eleven sub-steps.
Fig. 2
Fig. 2
The weights and biases between the input and hidden layers, as well as those of the output layer, are flattened.
Fig. 3
Fig. 3
The perceptual image dataset for visual evaluation is displayed in a resolution of formula image pixels for each one.
Fig. 4
Fig. 4
A shallow neural network architecture is used to solve the problem of skin image segmentation in RGB color space.
Fig. 5
Fig. 5
The confusion matrices reflect the accuracy of the four investigated algorithms in the skin segmentation problem.
Fig. 6
Fig. 6
Visual comparison results in the skin segmentation problem using an artificial neural network trained by the SOMA algorithm.
Fig. 7
Fig. 7
Visual comparison results: ANN trained by the SOMA, DE, ADAM, and SGDM respectively (from the top to the boottom).
See this image and copyright information in PMC

References

    1. Chen, H., Geng, L., Zhao, H., Zhao, C. & Liu, A. Image recognition algorithm based on artificial intelligence. Neural Comput. Appl.10.1007/s00521-021-06058-8 (2022). - PubMed
    1. Smith, T. B., Vacca, R., Mantegazza, L. & Capua, I. Natural language processing and network analysis provide novel insights on policy and scientific discourse around sustainable development goals. Sci. Rep.11, 22427. 10.1038/s41598-021-01801-6 (2021). - PMC - PubMed
    1. Bilal, A. et al. Bc-qnet: A quantum-infused elm model for breast cancer diagnosis. Comput. Biol. Med.175, 108483. 10.1016/j.compbiomed.2024.108483 (2024). - PubMed
    1. Bilal, A. et al. Breast cancer diagnosis using support vector machine optimized by improved quantum inspired grey wolf optimization. Sci. Rep.14, 10714. 10.1038/s41598-024-61322-w (2024). - PMC - PubMed
    1. Khan, A. Q. et al. A novel fusion of genetic grey wolf optimization and kernel extreme learning machines for precise diabetic eye disease classification. PLoS ONE19, 1–45. 10.1371/journal.pone.0303094 (2024). - PMC - PubMed

LinkOut - more resources