One of the most challenging problems in unattended ground sensor (UGS) systems is the identification of moving targets on the battlefield. The recognition methods proposed in the past often fail to take into account the two advantages of high accuracy and low calculation. In order to improve the performance of mobile target recognition on the battlefield and reduce the complexity of the recognition method, this paper proposes a new method based on the naive Bayes classifier. This method analyzes the ground vibration signal to detect whether there is a moving target passing through the warning area. The method is composed of three parts: noise reduction algorithm, signal feature extraction and classification method. The seven signal features of vibration used for gearbox fault diagnosis are innovatively used for target recognition of ground vibration signals. Compared with other methods, this method has the advantages of simple algorithm and less calculation and the recognition accuracy is basically the same as other methods. After experimental verification, the recognition accuracy of this method is 94.30%.
Target Recognition Method for Mobile Persons and Vehicles Based on Naive Bayesian Classifier and Ground Vibration Signal
Lect. Notes Electrical Eng.
International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021
Proceedings of 2021 International Conference on Autonomous Unmanned Systems (ICAUS 2021) ; Chapter : 55 ; 551-559
2022-03-18
9 pages
Article/Chapter (Book)
Electronic Resource
English
British Library Conference Proceedings | 2022
|Flexible Augmented Naive Bayesian Classifier
British Library Online Contents | 2007
|Naive Bayesian Classifier Based on Multiple Discriminant Analysis
British Library Online Contents | 2005
|