Machine Learning-Based Asthma Risk Prediction Using IoT and Smartphone Applications

In this paper, we present an asthma risk prediction tool based on machine learning (ML). The entire is implemented a smartphone as mobile-health (m-health) application using the resources of Internet-of-Things (IoT). Peak Expiratory Flow Rates (PEFR) are commonly measured external instruments such peak flow meters and well known asthama predictors. work, find correlation between particulate matter (PM) found indoors outside weather with PEFR. PEFR results classified into three categories ‘Green’ (Safe), ‘Yellow’ (Moderate Risk) ‘Red’ (High conditions in comparison to best value obtained by each individual. Convolutional neural network (CNN) architecture used map relationship indoor PM data values. proposed method compared state-of-the-art deep (DNN) techniques terms root mean square absolute error accuracy measures. These performance measures better for than other methods discussed literature. setup app. An IoT system including Raspberry Pi collect input data. This assistive can be cost-effective predicting attacks.