SSSLAD: A-Structured-Sparse-Subspace-Learning-Algorithm-for-Anomaly-Detection-in-UAV-Flight-Data

Structured sparse subspace learning anomaly detection (SSSLAD) algorithm is an online anomaly data sources identification method for UAV flight data

Abstract

Health status monitoring of flight-critical sensors is crucial to the flight safety of unmanned aerial vehicles (UAVs). While many flight data anomaly detection algorithms have been proposed, most do not consider data source information and cannot identify which data sources contribute most to the anomaly, hindering proper fault mitigation. To address this challenge, a structured sparse subspace learning anomaly detection (SSSLAD) algorithm which reformulates anomaly detection as a structured sparse subspace learning problem is proposed.

Structured Sparse Subspace learning problem

Comming soon.....

Result

Comming soon.....

Code Details

A standalone implementation of the algorithm is available in SSSLAD.m. Demos illustrating SSSLAD for flightdata are provided in:

• SSSLAD_demo1.m

We implement SSSLAD with Matlab 2015b and perform all experiments on a laptop computer equipped with an Intel core i7-4710HQ 2.50-GHz CPU and 8 GB of memory.

The code in Matlab will be released soon.....

References

If you find the code useful, I appreciate it very much if you can cite my related paper:

Y. F. He , Y Peng, S. J. Wang, D. T. Liu, P. H. W Leong. A Structural Sparse Subspace Learning algorithm for Anomaly Detection in UAV Flight Data. IEEE Trans. Instrum. Meas. Ari. 2017. (Under Review)

This program is provided for research purposes only. Any commercial use is prohibited. If you are interested in a commercial use, please contact the authors.

Yongfu He's Personal Blog: https://yongfuhe2017.github.io/

Yongfu He's Personal Website: https://xriver007.github.io/