IoT based Schistosomiasis Monitoring for More Efficient Disease Prediction and Control Model

Abstract

The urinary and intestinal schistosomiasis are a significant public health problem in Senegal with a prevalence rate varying between 0.3% and 1%. After malaria, bilharzia (or Schistosomiasis) is the second disease that calls for admission to hospital. In Senegal, treatment is based on "Praziquantel" that is not effective and may aggravate symptoms. In fact, schistosoma that transmits the illness lives in water points. Firstly, our proposed Sensors-Based Bilharzia Detection (SB2D) architecture uses data collected by wireless sensors network that are deployed in natural environment. SB2D is able to collect in real time different physical and chemical parameters such as solar irradiation, water temperature, water point pH and then predicts whether the environmental factors are favourable to bilharzia life cycle transmission. Secondly, event detection algorithms were developed in order to assess the transmission contamination risk when anomalies are detected. The obtained results show that Support Vector Machines (SVM) gives good anomalies detection rate compared to other anomalies detection test.