Page 184 - Kỷ yếu hội thảo khoa học lần thứ 12 - Công nghệ thông tin và Ứng dụng trong các lĩnh vực (CITA 2023)

168

used a simple CNN model with 3 convolutional layers as feature extractor and then
they are built on the same network architecture with respective different classifiers.
All of them are employed in the same training, validation and test set of weather
images. The outcomes of experiments show that the CNN-XGBoost has the best
performance among other 5 models in the problem of weather image classification.

References

1. Xiao, H., Zhang, F., Shen, Z., Wu, K., & Zhang, J.: Classification of weather phenomenon
from images by using deep convolutional neural network. Earth and Space Science, 8,
https://doi.org/10.1029/2020EA001604 (2021).
2. Mohammad F. N. & Selvia F. K.: Weather image classification using convolutional neural
network with transfer learning. AIP Conference Proceedings, Volume 2470, Issue 1,
https://doi.org/10.1063/5.0080195 (2022).
3. Mohamed R. I, James H. and Tao C.: WeatherNet: Recognising Weather and Visual
Conditions from Street-Level Images Using Deep Residual Learning. International Journal
of Geo-Information, ISSN: 2220-9964, ISPRS - International Society for Photogrammetry
and Remote Sensing (2019).
4. Khan, M.N.; Ahmed, M.M.: Weather and surface condition detection based on road-side
webcams: Application of pre-trained convolutional neural network. Int. J. Transp. Sci.
Technol. vol. 11, pp. 468-483 (2021).
5. Minhas S, Khanam Z, Ehsan S, McDonald-Maier K, Hernández-Sabaté A.: Weather
Classification by Utilizing Synthetic Data. 22(9):3193. doi: 10.3390/s22093193. PMID:
35590881; (2022).
6. Thongsuwan S., Jaiyen S., Padcharoen A., Agarwal P.: ConvXGB: A new deep learning
model for classification problems based on CNN and XGBoost. Nuclear Engineering and
Technology, ISSN 1738-5733, Vol 53, Issue 2, Page: 522-531 (2021).
7. Thiyagarajan Sahana: Performance Comparison of Hybrid CNN-SVM and CNN-XGBoost
models in Concrete Crack Detection. Theses Masters, Technological University Dublin,
https://arrow.tudublin.ie/scschcomdis/195/ (2019).
8. Huang, G-L, He, J, Xu, Z, Huang, G.: A combination model based on transfer learning for
waste classification, Concurrency Computat Pract Exper, https://doi.org/10.1002/cpe.5751
(2020).
9. Chen and Guestrin: XGBoost: A Scalable Tree Boosting System.
nd
the 22 ACM SIGKDD International Conference on Knowledge Discovery and Data
Mining, Pages 785 794, https://doi.org/10.1145 /2939672.2939785 (2016).
10. Xiao, Haixia, "Weather phenomenon database (WEAPD)", https://doi.org/10.7910
/DVN/M8JQCR, Harvard Dataverse, V1 (2021).

CITA 2023 ISBN: 978-604-80-8083-9