HIGHLIGHTS
SUMMARY
Thanks to prediction algorithms applied to data, the authors can participate in the LC by predicting the development or not of anopheles larvae. The authors will therefore present the IoT-based data acquisition architecture and the machine_learning-based larval presence prediction mechanism. The starting assumption is that the rate of presence of larvae rate is 49.409 percent, so all the parameters that will cause a variation of more than 50 percent are therefore determining for the presence of larvae. Speaking of prediction, this was done with data from the second collection, which had . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.