Abstract
This study implements ensemble deep learning models for weather image classification. Firstly, this study check the performance of 9 pre-train models, namely Xception, ResNet152, MobileNet, RegNetX002, InceptionV3, ResNet50, DenseNet201, ConvNeXtBase, VGG19 to find out top 3 models. Secondly, the best 3 pre-trained models are VGG19, InceptionV3 and MobileNet which are stacked to become an ensemble model. We also applied some methods as regularization, hyper-parameters tuning to find out the best model. The comparison on accuracy among stacked ensemble model, transfer learning on individual model and a combined model of VGG16-XGBoost show that the ensemble model gives the highest at 91.47%.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
