Deep Learning Based Threat Classification for Fiber Optic Distributed Acoustic Sensing Using SNR Dependent Data Generation
Journal: Journal of Scientific Technology and Engineering Research (Vol.1, No. 2)Publication Date: 2020-12-21
Authors : Emre UZUNDURUKAN Ali KARA;
Page : 4-12
Keywords : Deep learning classification; Distributed acoustic sensing; Optical time-domain reflectometry; Threat classification.;
Abstract
In this study, a novel method is proposed to generate SNR dependent database and classify seismic events for fiber optic distributed acoustic sensing (DAS) systems. Optical time-domain reflectometry (OTDR) is used to acquire DAS signals. Proposed data creation method generates signals with different SNR values which is based on real channel noise characteristics. By this way, from the limited dataset, huge dataset consists of three different seismic events such as hammer hit, digging with pickaxe and digging with shovel is generated. In the classification part, two different Deep Learning algorithm (Convolutional Neural Network and fully connected neural networks) are used to identify three different seismic events. Results show that remarkable identification accuracy for the three different SNR ranges is achieved.
Other Latest Articles
- The Influence of Bodybuilding Training Sessions on the Functional State of the Body
- Influence of Physical Exercises with Different Amplitude on Power Capacities in the Process of Bodybuilding Training
- Influence of Gymnastics on Physical Fitness and Adaptive Capabilities of Cardiovascular System of 7-8 Years Old Boys
- Possibilities of Using Functional Products in the Process of Sport Training
- Genetic-Epidemiological Study of Urban and Rural Pediatric Populations in Kharkov Region through the Example of Zmiiv District
Last modified: 2020-12-03 18:53:12