DeepDengue is a collection of deep learning models trained for the estimation of dengue fever cases in geographic locations, using only street-level and aerial images as input. This work was developed during my Doctorate degree in Computer Science, at Federal University of Pelotas (UFPel). The full-text of my Thesis is available at ResearchGate.

To use RioSat21, RioStreet and RioStreetSat21, cite using:

Andersson, V. O., Cechinel, C., & Araujo, R. M. (2019, July). Combining Street-level and Aerial Images for Dengue Incidence Rate Estimation. In 2019 International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). IEEE.

@inproceedings{AnderssonIJCNN2019,
	title={Combining Street-level and Aerial Images for Dengue Incidence Rate Estimation},
	author={Andersson, Virginia Ortiz and Cechinel, Cristian and Araujo, Ricardo Matsumura},
	booktitle={2019 International Joint Conference on Neural Networks (IJCNN)},
	pages={1--8},
	year={2019},
	organization={IEEE}
}

or for any other model in this repository, cite using:

@phdthesis{AnderssonThesis2019,
	author = {Andersson, Virginia Ortiz},
	title = {Dengue Incidence Rate Estimation Using Aerial and Street-level Urban Imagery with Deep Learning Models},
	school = {Federal University of Pelotas (UFPel)},
	year = {2019},
	month = {12},
	pages = {154},
	doi = {10.13140/RG.2.2.31562.93124}
}

Full-text available at ResearchGate.

If the use of the models are intended for publishing purposes and academic papers, please cite as above mentioned and provide the link from this repository as reference. THIS MATERIAL IS PROVIDED AS IS, WITH ABSOLUTELY NO WARRANTY EXPRESSED OR IMPLIED! ANY USE IS AT YOUR OWN RISK!