Service Recommendation for a Group of Users on the Internet of Things Using the Most Popular Service

With the emergence of the Internet of Things (IoT), advanced technologies like fog and cloud computing have been harnessed to create dynamic, real-time platforms addressing the needs of modern decision-makers. Crucial to this process is the recommendation of services tailored to each user's requirements in IoT settings, with the potential for improved Quality of Service (QoS) and Quality of Experience (QoE). The presented method in this paper leverages sensors, services, and fog computing within IoT systems to enhance QoS and adapt to user feedback. The approach involves ranking QoS of services based on Reliability, Availability, and Cost (RAC), and identifying the Most Popular Service (MPS) previously selected by the user. Comparison with Co-Scheduling System for Fog-node Recommendation and Load Management (CoS_FRLM) and User Characteristics-Collaborative Filtering (UCCF) demonstrates our method's effectiveness in maximizing recall, precision, and f-measure, as tested with the Network Simulator (NS3).