The Anomaly Detection Based on TBM Two-Level Fusion Architecture
WANG Xiao-hua1,2, ZOU Jie2, LI Li1,2, LIANG Yan1,2
1. School of Automation, Northwestern Polytechnical University, Xi'an, Shaanxi 710072, China;
2. Key Laboratory of Electrooptical Control Technology, Luoyang, Henan 471009, China
The track anomaly detection is the key issue to make sure flying anomaly detected in time for the route flight.Traditional probabilistic frameworks are always based on prior probabilities.Transferable belief model (TBM) theory can generalizes the Bayesian approach without prior probabilities and efficiently deal with heterogeneous data.However,the traditional TBM cannot deal with the discontinuity and uncertainty about the time.Considering the existence of unreliable evidence sources,an alternative anomaly detection method is proposed in the framework of transferable belief model (TBM) theory.A two-level architecture fusion system based on TBM is developed.The novelty of this work is that it can detect both unreliable evidence source and abnormal behavior of the targets within our architecture by using a temporal analysis and a new discounting coefficient through introducing the concept of contribution degrees of features.Detection of abnormal behavior is based on a prediction/observation process and the influence of the faulty sources is weakened through discounting coefficients.The simulations show the better accuracy of decision and precision of time compared with the dynamic evidence reasoning method.
[1] T Hossein,S Mita.Multi-sensor data fusion for autonomous vehicle navigation through adaptive particle filter[A].IEEE Intelligent Vehicles Symposium[C].San Diego,CA,USA:IEEE,2010.752-759.
[2] 王增福,潘泉,陈丽平,等.基于航路-航迹关联的天波超视距雷达航迹分类[J].系统工程与电子技术,2012,34(10):2018-2022 Wang Zengfu,Pan Quan,Chen Liping,et al.Tracks classification based on airway-track association for over-the-horizon radar[J].Systems Engineering and Electronics,2012,34(10):2018-2022.(in Chinese)
[3] M Grabisch,H Prade.The correlation problem in sensor fusion in a possibilistic framework[J].International Journal of Intelligent Systems,2001,16(11):1273-1283.
[4] T Hulnhagen,I Dengler,A Tamke,et al.Maneuver recognition using probabilistic finite-state machines and fuzzy logic[A].IEEE Intelligent Vehicles Symposium[C].San Diego,CA,USA:IEEE,2010.65-70.
[5] A Ayoun,P Smets.Data association in multi-target detection using the transferable belief model[J].International Journal of Intelligent Systems,2000,16(10):1167-1182.
[6] P Smets.The application of the transferable belief model to diagnostic problems[J].International Journal of Intelligent Systems,1998,13(2-3):127-157.
[7] A Debiolles,L Oukhellou,T Denoeux,P Aknin.Output coding of spatially dependent subclassifiers in evidential framework.Application to the diagnosis of railway track/vehicle transmission system[A].9th International Conference on Information Fusion[C].Florence,Italy:IEEE,2006.1-6.
[8] T Denoeux,G Govaert.Combined supervised and unsupervised learning for system diagnosis using Dempster-Shafer theory[A].IMACS Multi-conference,Computational Engineering in Systems Applications.Symposium on Control,Optimization and Supervision[C].Lille,France:CESA,1996.104-109.
[9] R Sadiq,H Najjaran,Y Kleiner.Investigating evidential reasoning for the interpretation of microbial water quality in a distribution network[J].Stochastic Environmental Research and Risk Assessment,2006,21(1):63-73.
[10] O Mengshoel,A Darwiche,S Uckun.Sensor validation using bayesian networks[A].9th International Symposium on Artificial Intelligence,Robotics,and Automation in Space[C].Los Angeles,CA,USA:i-SAIRAS,2008.
[11] Si X S,Hu C H,Yang J B,et al.On the dynamic evidential reasoning algorithm for fault prediction[J].Expert Systems with Applications,2011,38(5):5061-5080.
[12] Denoux T,El Zoghby N,Cherfaoui V,et al.Optimal object association in the Dempster-Shafer framework[J].IEEE Transactions on Cybernetics,2014,44(12):2521-2531.
[13] 王壮,郁文贤,庄钊文,等.C~3I系统中的目标综合识别技术[J].系统工程与电子技术,2001,23(1):5-8. Wang Zhuang,Yu Wenxian,Zhuang Zhaowen,et al.Fusion of multi-Source information for target identity estimation in C~3I system[J].Systems Engineering and Electronics,2001,23(1):5-8.(in Chinese)
[14] 李立,王文旭,梁彦.基于动态证据推理的异常航路目标检测[J].电子设计工程,2015,23(9):30-33 Li Li,Wang Wenxu,LIANG Yan.The detection of abnormal airline targets based on evidence theory[J].Electronic Design Engineering,2015,23(9):30-33.(in Chinese)