EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

BAOS-CNN: A novel deep neuroevolution algorithm for multispecies seagrass detection

Md Kislu Noman iD, Syed Mohammed Shamsul Islam iD, Seyed Mohammad Jafar Jalali, Jumana Abu-Khalaf, Paul Lavery

PLOS ONE · 25.06.2024 · 19 (6) · e0281568

DOI: 10.1371/journal.pone.0281568 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 25.06.2024. Verfasst von Md Kislu Noman und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Science, Edith Cowan University, Perth, Australia. Hauptthemen laut MEDLINE: Algorithms, Neural Networks, Computer, Deep Learning. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Australian Government Research Training Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning, a subset of machine learning that utilizes neural networks, has seen significant advancements in recent years. These advancements have led to breakthroughs in a wide range of fields, from natural language processing to computer vision, and have the potential to revolutionize many industries or organizations. They have also demonstrated exceptional performance in the identification and mapping of seagrass images. However, these deep learning models, particularly the popular Convolutional Neural Networks (CNNs) require architectural engineering and hyperparameter tuning. This paper proposes a Deep Neuroevolutionary (DNE) model that can automate the architectural engineering and hyperparameter tuning of CNNs models by developing and using a novel metaheuristic algorithm, named ‘Boosted Atomic Orbital Search (BAOS)’. The proposed BAOS is an improved version of the recently proposed Atomic Orbital Search (AOS) algorithm which is based on the principle of atomic model and quantum mechanics. The proposed algorithm leverages the power of the Lévy flight technique to boost the performance of the AOS algorithm. The proposed DNE algorithm (BAOS-CNN) is trained, evaluated and compared with six popular optimisation algorithms on a patch-based multi-species seagrass dataset. This proposed BAOS-CNN model achieves the highest overall accuracy (97.48%) among the seven evolutionary-based CNN models. The proposed model also achieves the state-of-the-art overall accuracy of 92.30% and 93.5% on the publicly available four classes and five classes version of the ‘DeepSeagrass’ dataset, respectively. This multi-species seagrass dataset is available at: https://ro.ecu.edu.au/datasets/141/ .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsNeural Networks, ComputerDeep Learning

Autor:innen und Institutionen

  • School of Science, Edith Cowan University, Perth, Australia.

ORCID-Profile: Md Kislu Noman, Syed Mohammed Shamsul Islam

Förderung

  • Australian Government Research Training Program

Zitieren

APA

Noman, M. K., Shamsul Islam, S. M., Jafar Jalali, S. M., Abu-Khalaf, J., & Lavery, P. (2024). BAOS-CNN: A novel deep neuroevolution algorithm for multispecies seagrass detection. PLOS ONE, 19(6), e0281568. https://doi.org/10.1371/journal.pone.0281568

Vancouver

Noman MK, Shamsul Islam SM, Jafar Jalali SM, Abu-Khalaf J, Lavery P. BAOS-CNN: A novel deep neuroevolution algorithm for multispecies seagrass detection. PLOS ONE. 2024;19(6):e0281568. doi:10.1371/journal.pone.0281568

BibTeX
@article{Noman2024,
  author = {Noman, Md Kislu and Shamsul Islam, Syed Mohammed and Jafar Jalali, Seyed Mohammad and Abu-Khalaf, Jumana and Lavery, Paul},
  title = {BAOS-CNN: A novel deep neuroevolution algorithm for multispecies seagrass detection},
  journal = {PLOS ONE},
  year = {2024},
  volume = {19},
  number = {6},
  pages = {e0281568},
  doi = {10.1371/journal.pone.0281568}
}
Kostenlos starten →