Li_Chengang Lv-2020-Li (3).pdf (9.91 MB)
Abnormal events detection based on RP and inception network using distributed optical fiber perimeter system
journal contribution
posted on 2020-09-24, 09:21 authored by Chengang Lyu, Jianying Jiang, Baihua LiBaihua Li, Ziqiang Huo, Jiachen YangFor establishing an accurate and reliable distributed optical fiber perimeter security
system, this paper proposes a novel abnormity detection solution to security using Recurrent
Plot (RP) and deep learning technology. Take advantage of the temporal correlation of intrusion
signals, we encode the sensing signals into two-dimensional images through the RP algorithm.
The RP algorithm can extract the motion characteristics of the signal from the complex time
series, and it is robust to instrument noise. These encoded image signatures can reveal the
deeper temporal correlation of the intrusion signals’ motion. After that, Inception network can
adaptively extract the features of these images to complete the accurate identification of a series
of noisy intrusion signals. We conducted experiments on three most frequent natural events
and three representative man-made intrusion events, including heavy rain, light rain, wind
blowing, treading, slapping, and impacting. The results show that the detection accuracy has
reached 99.7%. This method can achieve 0.35 s real-time detection in the online detection of
abnormal events while ensuring accuracy, providing a new intrusion pattern identification idea
for perimeter security.
Funding
National Natural Science Foundation of China under Grants 61205075
History
School
- Science
Department
- Computer Science
Published in
Optics and Lasers in EngineeringVolume
137Pages
106377Publisher
ElsevierVersion
- AM (Accepted Manuscript)
Rights holder
© ElsevierPublisher statement
This paper was accepted for publication in the journal Optics and Lasers in Engineering and the definitive published version is available at https://doi.org/10.1016/j.optlaseng.2020.106377Acceptance date
2020-09-10Publication date
2020-09-16Copyright date
2021ISSN
0143-8166Publisher version
Language
- en
Depositor
Dr Baihua Li Deposit date: 16 September 2020Article number
106377Usage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC