Munoz, J. PabloBoger, RebeccaDexter, ScottLow, RussanneLi, Justin2017-12-282017-12-282018-01-03978-0-9981331-1-9http://hdl.handle.net/10125/50247We propose a system that assists infectious disease experts in the rapid identification of potential outbreaks resulting from arboviruses (mosquito, ticks, and other arthropod-borne viruses). The proposed system currently identifies mosquito larvae in images received from citizen scientists. Mosquito-borne viruses, such as the recent outbreak of Zika virus, can have devastating consequences in affected communities. We describe the first implemented prototype of our system, which includes modules for image collection, training of image classifiers, specimen recognition, and expert validation and analytics. The results of the recognition of specimens in images provided by citizen scientists can be used to generate visualizations of geographical regions of interest where the threat of an arbovirus may be imminent. Our system uses state-of-the-art image classification algorithms and a combination of mobile and desktop applications to ensure that crucial information is shared appropriately and accordingly among its users.10 pagesengAttribution-NonCommercial-NoDerivatives 4.0 InternationalGlobal Health IT StrategiesCitizen Science, Image Classification, Machine Learning, Mobile Systems, Virus OutbreakConference Paper10.24251/HICSS.2018.359