Overview / Usage

According to WHO(World Health Organization) reports, among all disease transmitting insects mosquito is the
most hazardous insect. In 2015 alone, 214 million cases of malaria were registered worldwide. Zika virus is another deadly disease transmitted from mosquitoes. According to CDC report, in 2016 62,500 suspected case of Zika were reported to the Puerto Rico Department of Health (PRDH) out of which 29,345 cases were found positive. There are 3500 different species of mosquitoes present in the world out of which 175 types is found in United States. But only few of them are responsible for these above mentioned fatal disease. Therefore classification between hazardous and regular mosquitoes are very important. For regular person with no expertise in this field would be almost
impossible to identify the difference. Even for the mosquito expert, identifying different species is a very tedious and time consuming job. Hence in this paper, we have tried to classify 7 different species of dead mosquitoes with total 60 samples collected from Hillsborough County Mosquito and Aquatic Weed Control Unit,Tampa Florida by capturing image from smart phone cameras. With our approach we want to enable nonexpert population to early identify the risk and act pro-actively. We pre-processed the image for removing noise and applied random forest classification algorithm to distinguish different species. Achieved good precision,recall,F1 measure and aggregate 83:3% accuracy. We are also planning to develop a smart-phone application which will leverage this learning model and help in empowering population to identify mosquito species without any knowledge in this field.