Abstract
Compared with the fixed fusion structure, the flexible fusion structure with mixed fusion methods has better adjustment performance for the complex air task network systems, and it can effectively help the system to achieve the goal under the given constraints. Because of the time-varying situation of the task network system induced by moving nodes and non-cooperative target, and limitations such as communication bandwidth and measurement distance, it is necessary to dynamically adjust the system fusion structure including sensors and fusion methods in a given adjustment period. Aiming at this, this paper studies the design of a flexible fusion algorithm by using an optimization learning technology. The purpose is to dynamically determine the sensors’ numbers and the associated sensors to take part in the centralized and distributed fusion processes, respectively, herein termed sensor subsets selection. Firstly, two system performance indexes are introduced. Especially, the survivability index is presented and defined. Secondly, based on the two indexes and considering other conditions such as communication bandwidth and measurement distance, optimization models for both single target tracking and multi-target tracking are established. Correspondingly, solution steps are given for the two optimization models in detail. Simulation examples are demonstrated to validate the proposed algorithms.
Highlights
The rapid development of some key technologies—for example, communication technology, sensor technology, data processing, and so on—have promoted the research into applications of wireless sensor network systems
Aiming at the above conditions and based on the earlier work [12], we focus on this popular research topic
Because this paper considers a kind of special air task network system which is strictly limited to communication among nodes, it only considers a simple approach
Summary
The rapid development of some key technologies—for example, communication technology, sensor technology, data processing, and so on—have promoted the research into applications of wireless sensor network systems. Designing multi-sensor data fusion algorithms in order to improve target tracking learning system performance has recently been one of the popular topics in the NIS area. The focus of this paper is mainly to design and solve an optimization model on sensor subsets selection, so only the traditional unscented Kalman filter (UKF) is used. A fixed fusion structure means that once the fusion method (e.g., centralized fusion or distributed fusion) is determined, neither the fusion method nor the sensors taking part in the fusion process are changed during the whole working time This approach does not satisfy the practical requirements of engineering applications.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call