Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Planning trajectory for UAVs using the self-organizing migrating algorithm.

PloS one·2025
Same author

Vibration-based gearbox fault diagnosis using a multi-scale convolutional neural network with depth-wise feature concatenation.

PloS one·2025
Same author

Crossmixed convolutional neural network for digital speech recognition.

PloS one·2024
Same author

Secrecy Outage Probability of a NOMA Scheme and Impact Imperfect Channel State Information in Underlay Cooperative Cognitive Networks.

Sensors (Basel, Switzerland)·2020
Same author

Chaos enhanced differential evolution in the task of evolutionary control of selected set of discrete chaotic systems.

TheScientificWorldJournal·2014

Related Experiment Video

Updated: Jun 11, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

376

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

Quoc Bao Diep1, Thanh-Cong Truong2, Ivan Zelinka3,4

  • 1Faculty of Mechanical - Electrical and Computer Engineering, School of Technology, Van Lang University, Ho Chi Minh City, Vietnam. bao.dq@vlu.edu.vn.

Scientific Reports
|September 30, 2024
PubMed
Summary
This summary is machine-generated.

The self-organizing migrating algorithm (SOMA) trained artificial neural networks for skin segmentation, achieving 93.18% accuracy. This evolutionary approach outperformed gradient-based methods and differential evolution for improved image segmentation.

Keywords:
Artificial neural networksComputer visionOptimization algorithmSOMASkin segmentationSwarm intelligence

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
08:59

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

7.1K

Related Experiment Videos

Last Updated: Jun 11, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

376
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
08:59

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

7.1K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Machine Learning

Background:

  • Accurate skin segmentation is crucial for various applications, including medical imaging and augmented reality.
  • Training artificial neural networks (ANNs) often relies on gradient-based optimization, which can face challenges like local optima.
  • Evolutionary algorithms offer alternative optimization strategies for training complex models.

Purpose of the Study:

  • To evaluate the effectiveness of the self-organizing migrating algorithm (SOMA) for training ANNs in skin segmentation.
  • To compare SOMA's performance against established gradient-based optimizers (ADAM, SGDM) and another evolutionary algorithm (DE).

Main Methods:

  • The self-organizing migrating algorithm (SOMA) was applied to train an ANN for skin segmentation.
  • Performance was benchmarked using the skin dataset (245,057 samples) against ADAM, SGDM, and differential evolution (DE).
  • Quantitative accuracy metrics and qualitative visual evaluations were conducted.

Main Results:

  • The SOMA-trained ANN achieved the highest accuracy at 93.18%.
  • SOMA significantly outperformed ADAM (84.87%), SGDM (84.79%), and DE (91.32%).
  • Visual assessment confirmed the SOMA-trained model's reliable segmentation capabilities.

Conclusions:

  • The self-organizing migrating algorithm (SOMA) is a highly effective optimizer for training ANNs in skin segmentation tasks.
  • Evolutionary optimization presents a promising alternative to gradient-based methods for improving image segmentation performance.
  • SOMA demonstrates potential for enhancing the accuracy and reliability of deep learning models in computer vision.