Dew Computing enabled ANFIS Model for Accurate Classification of Season-Stratified Acute Respiratory Infections in High Altitude Region

Considerable research efforts have been devoted to delving into the realm of the Internet of Medical Things (IoMT) with the goal of enhancing healthcare services. The amalgamation of Internet of Things (IoT), medical devices, and the advances in cloud computing has enabled a collaborative approach, fostering improved prevention, diagnosis, treatment, and management of chronic illnesses This article explores the impact of ambient environmental factors on the incidence of acute respiratory infections (ARI) in the high-altitude region. The inconsistency in meteorological conditions has evolved into a major contributing factor to the severity of health issues, particularly for individuals dealing with Acute Respiratory Infections (ARI) like asthma. Limited studies in this geographically challenging area necessitate an in-depth investigation to understand the linkages between meteorological factors and consequent health adversities. The scarcity of specialized predictive solutions designed for individuals grappling with ARI can present a notable obstacle, contributing to both health and psychological challenges. In this study we propose a Dew Computing-enabled Adaptive Neuro-Fuzzy Inference System (ANFIS) model for precise classification of season-stratified ARIs. The proposed model aims to contribute valuable insights into measuring potential irregular health occurrences, by employing Weighted-Naïve Bayes modeling technique for the classification of the irregular events. Furthermore, the correlation between meteorological and health factors is assessed through the use of the Adaptive Neuro-Fuzzy Inference System (ANFIS). The proposed model aims to contribute valuable insights into the interplay of meteorological factors and respiratory health in high-altitude regions. The outcomes of the experiments illustrate that the model accurately predicts the severity of Asthma, achieving a precision level of 91.20%.