Unmanned Aerial Vehicle Sensing Data Anomaly Detection by Relevance Vector Machine

In recent years, Unmanned Aerial Vehicle (UAV) has been gaining more and more attention for military and civilian utilization. How to monitor its condition is a crucial problem. The accuracy of the sensing data is one of the basic requirements to achieve its correct condition. Thus, one kind of data anomaly detection approaches by Relevance Vector machine (RVM) is proposed in this article. By utilizing the visual UAV simulator FlgihtGear, the sensing data with anomalous data are generated. The effectiveness of the proposed approach for detecting the anomalous data contained in the sensing data is evaluated.

[1]  Liang Zhang,et al.  Study of polynomial curve fitting algorithm for outlier elimination , 2011, 2011 International Conference on Computer Science and Service System (CSSS).

[2]  Yu Liu,et al.  A KNNS based anomaly detection method applied for UAV flight data stream , 2015, 2015 Prognostics and System Health Management Conference (PHM).

[3]  Martin Meckesheimer,et al.  Automatic outlier detection for time series: an application to sensor data , 2007, Knowledge and Information Systems.

[4]  Gary J. Balas,et al.  Model-Based and Data-Driven Fault Detection Performance for a Small UAV , 2013, IEEE/ASME Transactions on Mechatronics.

[5]  Meir Kalech,et al.  Online data-driven anomaly detection in autonomous robots , 2014, Knowledge and Information Systems.

[6]  George Eastman House,et al.  Sparse Bayesian Learning and the Relevan e Ve tor Ma hine , 2001 .

[7]  Eliahu Khalastchi,et al.  Detecting anomalies in unmanned vehicles using the Mahalanobis distance , 2010, 2010 IEEE International Conference on Robotics and Automation.

[8]  I. Colomina,et al.  Unmanned aerial systems for photogrammetry and remote sensing: A review , 2014 .

[9]  R. Walker,et al.  Sensor Fault Detection for UAVs using a Nonlinear Dynamic Model and the IMM-UKF Algorithm , 2007, 2007 Information, Decision and Control.

[10]  Raymond T. Ng,et al.  Algorithms for Mining Distance-Based Outliers in Large Datasets , 1998, VLDB.