Projects

DSTN > Projects > AIRFARE EWS

Project investigators

  • ACE MITIC, Senegal
    • Dr. Dame Diongue, Gaston Berger University, Senegal
    • Prof. Maissa Mbaye, Gaston Berger University, Senegal
    • Dr. Nicolas Djighnoum Diouf, Gaston Berger University, Senegal
  • ACE CApIC, Nigeria
    • Prof. E. F. Adebiyi, Covenant University, Ota, Nigeria
    • Prof. E. Adetiba, CApIC-ACE, Covenant University, Ota, Nigeria
    • Dr. Joke A. Badejo, Covenant University, Ota, Nigeria

Other partners

  • Dr. Assane G. Fall, Institut Sénégalais de Recherches Agricoles, Sénégal
  • Dr Mamadou Ciss, Institut Sénégalais de Recherches Agricoles, Sénégal
  • Dr Modou Moustapha Lo, Institut Sénégalais de Recherches Agricoles, Sénégal
  • Dr. Ibrahima Ndao, Direction of Park and reserves, Saint-Louis, Sénégal
  • Dr. Seynabou Diack Sy, Veterinary services, Saint-Louis, Sénégal
DSTN > Projects > AIRFARE EWS

Title: Artificial Intelligence based Early Warning System for Rift Valley Fever detection

Project type : Development Project (2 years)

Abstract :
Rift Valley Fever (RVF) is a viral zoonosis that can cause serious disease in small ruminant animals and humans. It spans from eastern to southern Africa and into the Middle East. It caused massive epidemics in Egypt, Mauritania (2010, 2012), Senegal (2012, 2020) and in Madagascar. It can be transmitted is between humans and animals and has as main manifestation an abnormal rate of abortions in animals and can be deadly for human beings. Epidemic alert systems in African countries such as Senegal are challenging early detection of outbreaks to be efficient (data collection and forecast). Both livestock owners and laboratory technicians are exposed because of a probable manipulation before confirmed diagnosis. However, Research such as NASA studies show the relationship between RFV outbreaks and environmental parameters such as there Nina to be able to predict the next outbreak. 
The objective of this project is to develop an early warning system for Rift Valley fever based on AI for prediction and detection. It consists of a data collection system based on IoT/Mobile applications and Cloud AI/Machine Learning service (Classification, Reinforcement Deep Learning, CNN, Computer Vision, …). Expected achievements are building incrementally datasets that can be used to provide Cloud AI/ML services with spatial and temporal correlations to recognize early the starting of outbreaks. Data are heterogeneous (images of abortions, vectors/mosquitos, official data sets, …), from various sources (WHO, ISRA, on site collection, as well as breeders), of different levels of validation (declaration of suspicion by breeders, confirmed analysis by laboratorian, …), bi-dimensional (special, and temporal). Mobile Application will help in on site collection. Thus, it is necessary to find ML models that adapt well to data analysis taking into account all these characteristics and learn incrementally. The consortium involves MITIC for AI and IoT services and CaPIC for Cloud services developments in FedGenHealth. We also have ISRA (Institut Sénégalaise de Recherche Agronomique) which is a technical partner for medical and vector related questions.

Keywords:

  • Research themes in digital science: Emerging diseases, Artificial Intelligence, early warning system, One Health, TinyML
  • Other research themes and application areas: Rift Valley Fever, Zoonosis,  outbreaks monitoring system, Deep Machine Learning, Cloud Services, IoT, FEDGEN Platform
By continuing your navigation on this site, you accept the use of cookies to allow us to offer you the best service.