Rubio-Solis, A;
Musah, A;
Dos Santos, WP;
Massoni, T;
Birjovanu, G;
Kostkova, P;
(2019)
ZIKA Virus: Prediction of Aedes Mosquito Larvae Occurrence in Recife (Brazil) using Online Extreme Learning Machine and Neural Networks.
In: Kostkova, P and Wood, C and Bosman, A and Grasso, F and Edelstein, M, (eds.)
DPH2019: Proceedings of the 9th International Conference on Digital Public Health.
(pp. pp. 101-110).
Association for Computing Machinery (ACM): New York, NY, USA.
Preview |
Text
Musah_ZIKA_Prediction_fp04-2.pdf - Accepted Version Download (4MB) | Preview |
Abstract
Geographical maps showing the abundance of the Aedes species (\textitA. Aegypti andA. Albopictus ) in Latin America plays a crucial role in the fight against the Zika Virus (ZIKV). They aid in the identification of sites that promotes mosquito breeding and transmission of ZIKV. In the case of Brazil, one of the greatest factors that favours rapid mosquito reproduction is the presence of stagnated water in the environment. This could be in the form of non-flowing water filled in tanks, barrels, discarded tires, and many other containers situated in human dwellings. After the ZIKV outbreak from 2015, the environmental agency in Brazil have intensively been engaged with routine surveillance of water bodies present in households and the environment to destroy mosquito breeding hotspots as public health measure to prevent vector-to-human transmission of ZIKV. The objective of this study is to use data from their routine surveillance to showcase how our predictive framework based on Neural Networks and Online Extreme Learning Machine (OELM) can predict for Recife (Brazil) at a health district-level the following: firstly, the spatial distribution of the number of properties with water containers contaminated with the Aedes mosquito larvae responsible for ZIKV; and secondly, the spatial distribution of properties with the Aedes mosquito larvae stratified by type of water container. The ultimate goal for this research is to subsequently implement these models to their real-time surveillance data so as an early warning system is present to flag-out spatially the mosquito hotspots on the fly. This system will be built to guide policy makers for directing resources for controlling the mosquito populations thereby limiting transmission to humans.
| Type: | Proceedings paper |
|---|---|
| Title: | ZIKA Virus: Prediction of Aedes Mosquito Larvae Occurrence in Recife (Brazil) using Online Extreme Learning Machine and Neural Networks |
| Event: | 9th International Conference on Digital Public Health (DPH) |
| Location: | Marseille, FRANCE |
| Dates: | 20 November 2019 - 23 November 2019 |
| ISBN-13: | 9781450372084 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1145/3357729.3357738 |
| Publisher version: | https://doi.org/10.1145/3357729.3357738 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Inst for Risk and Disaster Reduction UCL > Provost and Vice Provost Offices > UCL SLASH UCL > Provost and Vice Provost Offices > UCL SLASH > Faculty of S&HS UCL > Provost and Vice Provost Offices > UCL SLASH > Faculty of S&HS > Dept of Geography |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10101535 |
Archive Staff Only
 |
View Item |
