IoT Route Planning Based on Spatiotemporal Interactive Attention Neural Network

Millions of interconnected Internet of Things (IoT) sensors and devices collect tremendous amounts of data from real-world traffic scenarios. Route planning with IoT network could derive critical value for smart city and automatic vehicles. In the current route planning methods, the route weight only decays with time and distance separately, without considering the inherent spatiotemporal dependence. Besides, lacking of fine-grained traffic data interaction analysis in dynamic environment is another challenge for route planning. In this article, we propose a spatiotemporal interactive attention neural network for personalized route planning. First, we utilize an intelligent approach to route recommendation based on data collected by IoT under given spatial constraints. Next, we carry out traffic road network analysis with the spatial graph attention structure. Then, we develop a temporal self-attention mechanism to capture multilevel temporal relationship. In particular, we explore the influence of features, such as external attributes, the spatial correlation between different locations, and the temporal correlation between different time intervals. Finally, we build an aggregation network to allocate appropriate weights to measure these features for obtaining the potential best route selection. Route planning results show that the performance of our scheme is better than that of the baseline scheme, which proves that our method makes full use of attribute information and environmental changes. The IoT experimental results demonstrated that the presented system could be advantageous for tackling IoT scenarios in a cost-effective way.