A Collaborative Multi-Granularity Architecture for Multi-Source IoT Sensor Data in Air Quality Evaluations

Air pollution (AP) is a significant environmental issue that poses potential threat to human health. Its adverse effects on health are diverse, ranging from sensory discomfort acute physiological reactions. As such, air quality evaluation (AQE) serves as crucial process involves the collection of samples environment and their analysis measure AP levels. With proliferation Internet Things (IoT) devices sensors, real-time continuous measurement pollutants in urban environments has become possible. However, data obtained multiple sources IoT sensors can be uncertain inaccurate, posing challenges effectively utilizing fusing this data. Meanwhile, differences opinions among decision-makers regarding AQE affect outcome final decision. To tackle these challenges, paper systematically investigates novel multi-attribute group decision-making (MAGDM) approach based hesitant trapezoidal fuzzy (HTrF) information discusses its application AQE. First, by combining HTrF sets (HTrFSs) with multi-granulation rough (MGRSs), new set model, named MGRSs, two-universe model proposed. Second, definition property presented studied. Third, background constructed via index (DMISs). Lastly, validity feasibility demonstrated case study conducted setting using experimental comparative analyses. The outcomes experiment demonstrate architecture owns ability handle multi-source sensor (MSIoTSD), providing sensible conclusion for In summary, MAGDM method article promising scheme solving problems, where HTrFSs possess excellent description capabilities adequately describe indecision uncertainty information. MGRSs serve an outstanding fusion tool improve level decision-making. DMISs better able analyze evaluate reduce impact disagreement decision outcomes. proposed architecture, therefore, provides viable solution MSIoTSD facing or hesitancy environment.