article · Biomimetics
Machine learning models combined with binary particle swarm optimisation can predict COVID-19 case patterns across geographically distinct environments. The study examined two different regions in Saudi Arabia, comparing high-altitude conditions in Taif city against sea-level conditions in Jeddah city. Using feature selection through an optimised binary particle swarm algorithm, three machine learning techniques were trained and tested: random forest, gradient boosting, and naive Bayes. Performance varied depending on the geographic characteristics of the location. For the high-altitude dataset from Taif, the gradient boosting algorithm achieved the strongest predictive performance with an accuracy of 94.6 percent. In contrast, the random forest model performed best on the coastal dataset from Jeddah, delivering an accuracy of 95.5 percent. Overall, predictive accuracy was higher for the sea-level region than for the high-altitude region across standard evaluation metrics.
Infectious disease outbreaks often spread unevenly across different geographical environments, including coastal and mountainous regions. Showing that distinct computational algorithms perform best in different environmental settings helps analysts choose the right analytical tools for specific locations. Tailoring predictive algorithms to local regional characteristics can improve the precision of infection tracking and support more targeted health resource planning.
The research represents early-stage, applied algorithmic development tested on retrospective city-level datasets. Potential end users could include public health agencies and epidemiological monitoring teams developing regional outbreak forecasting tools. The abstract indicates computational testing rather than deployment, so practical application would require further software integration, validation on live public health streams, and testing across other geographic zones.
AI-generated from the published abstract. Always read the original work before citing.
During the pandemic of the coronavirus disease (COVID-19), statistics showed that the number of affected cases differed from one country to another and also from one city to another. Therefore, in this paper, we provide an enhanced model for predicting COVID-19 samples in different regions of Saudi Arabia (high-altitude and sea-level areas). The model is developed using several stages and was successfully trained and tested using two datasets that were collected from Taif city (high-altitude area) and Jeddah city (sea-level area) in Saudi Arabia. Binary particle swarm optimization (BPSO) is used in this study for making feature selections using three different machine learning models, i.e., the random forest model, gradient boosting model, and naive Bayes model. A number of predicting evaluation metrics including accuracy, training score, testing score, F-measure, recall, precision, and receiver operating characteristic (ROC) curve were calculated to verify the performance of the three machine learning models on these datasets. The experimental results demonstrated that the gradient boosting model gives better results than the random forest and naive Bayes models with an accuracy of 94.6% using the Taif city dataset. For the dataset of Jeddah city, the results demonstrated that the random forest model outperforms the gradient boosting and naive Bayes models with an accuracy of 95.5%. The dataset of Jeddah city achieved better results than the dataset of Taif city in Saudi Arabia using the enhanced model for the term of accuracy.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/biomimetics8060457
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
