Whale-optimized elman neural network for predicting moisture content during seaweed drying in a v-groove hybrid solar dryer
Abstract
Traditional sun-drying methods for seaweed face many challenges, such as moisture content, weather conditions, and inconsistent drying rates. This study addresses the needs of Malaysian seaweed farmers for a dependable and effective drying process by a v-Groove Hybrid Solar Dryer (v-GHSD). Data on seaweed was obtained using smart farming technology sensors attached to the v-GHSD. There are 29 main drying parameters, and by adding the second-order interaction, the parameters increased to 435 parameters to capture interaction effects. For non-linear and high-dimensional data, traditional models cannot handle the problem. Then, we applied the Elman Neural Network (ENN) based on the Whale Optimization Algorithm, support vector regression, ENN, and partial least squares regression methods to develop the predictive models. From the results, the hybrid WOA-ENN model is better, with the root mean square error of prediction of 0.0710, a correlation coefficient of 0.9974, and the relative percent deviation of 3.1165.
Related
- Neuroprotective Potential of the Edible Seaweed Pterocladiella capillacea: Bioactivity Coupled LC-MS/MS, Metabolomics Annotation, Validation, and Network Pharmacology
- Predicting brain tumours through transfer learning and optimized hyperparameters using the modified whale’s algorithm
- An EfficientNet hybrid deep learning detection framework of network intrusion with an optimized mixture-of-experts architecture
- Cardiovascular disease prediction and mortality risk assessment using a QSAO‑optimized BP neural network.
- Predicting clonal mutations from tumour spatial transcriptomics data using a graph convolutional neural network
BibTeX
@article{ibidoja2026whaleoptimized,
title = {{Whale-optimized elman neural network for predicting moisture content during seaweed drying in a v-groove hybrid solar dryer}},
author = {Olayemi Joshua Ibidoja and Wan Rosli Wan Ishak and Majid Khan Majahar Ali and Nurraihana Hamzah},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-65129-9},
url = {https://www.nature.com/articles/s41598-026-65129-9},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - Whale-optimized elman neural network for predicting moisture content during seaweed drying in a v-groove hybrid solar dryer
AU - Olayemi Joshua Ibidoja
AU - Wan Rosli Wan Ishak
AU - Majid Khan Majahar Ali
AU - Nurraihana Hamzah
PY - 2026
DA - 2026/10/21
JO - Scientific Reports
DO - 10.1038/s41598-026-65129-9
UR - https://www.nature.com/articles/s41598-026-65129-9
AB - Traditional sun-drying methods for seaweed face many challenges, such as moisture content, weather conditions, and inconsistent drying rates. This study addresses the needs of Malaysian seaweed farmers for a dependable and effective drying process by a v-Groove Hybrid Solar Dryer (v-GHSD). Data on seaweed was obtained using smart farming technology sensors attached to the v-GHSD. There are 29 main drying parameters, and by adding the second-order interaction, the parameters increased to 435 parameters to capture interaction effects. For non-linear and high-dimensional data, traditional models cannot handle the problem. Then, we applied the Elman Neural Network (ENN) based on the Whale Optimization Algorithm, support vector regression, ENN, and partial least squares regression methods to develop the predictive models. From the results, the hybrid WOA-ENN model is better, with the root mean square error of prediction of 0.0710, a correlation coefficient of 0.9974, and the relative percent deviation of 3.1165.
SN - 2045-2322
ER -