Adaptive Fuzzy Tree System for Target Tracking in Mission Critical Sensor Networks

The emergence of mobile sensors dramatically improves the availability of mission critical sensors and sensor networks (MC-SSN), enabling it to be utilized in more challenging tasks. However, current researches aimed to target tracking in mobile MC-SSN are very limited. This paper first proposes an adaptive fuzzy tree system (AFS) for target tracking in MC-SSN. To avoid oversimplifying the target mobile pattern, which is unrealistic in real tracking tasks, we introduce the target circle into the model considerations to add a bit of uncertainty about the target position. At each time step of the tracking process, strategy-selection layer will activate the pursuit strategy or the diffusion strategy for the specific situation, which makes the system more intelligent and can be applicable to various scenarios. The pursuit strategy is built by a two-layer fuzzy tree to select and mobilize sensors that have not detected target, while the diffusion strategy uses a fuzzy inference system to balance the density of detected sensors. And all the hyper-parameters are tuned by particle swarm optimization (PSO). We performed a large number of simulations with two target trajectories: line and irregular. The simulation results show that the AFS significantly outperforms the state-of-the-art algorithm. Moreover, it is highly robust to various target motion patterns, making it competent for a variety of real target tracking scenarios.