Public areas can have Internet of Things (IoT)-enabled sensing devices placed to keep track of possible security risks such as suspicious activity or misplaced possessions. In public areas, devices have the ability to gather information, but, in some cases, people must explicitly check out if they wish their data to be taken. This research presents an analysis of the IoT environment on Ganzhou’s public transportation, suggests a new IoT-based intelligent public transportation system framework, and shows how the communication network’s components are being applied. In this study, we detail the deployment of IoT sensors through the collection of data. We proposed a novel Salp Swarm weighted recurrent neural network (SS- WRNN) for prediction in Ganzhou’s public transport flow. The data were extracted using linear discriminate analysis (LDA) from high-dimensional sensor data into a lower-dimensional space. For resolving the dynamic bus scheduling and controlling issues, decision support algorithms are suggested. It can help decision-makers decrease passenger trip times, boost scheduling effectiveness, and raise the rate at which transportation resources are utilized.