Exploiting CNN-BiLSTM Model for Distributed Acoustic Sensing Event Recognition

DOI

10.2991/978-94-6463-512-6_36How to use a DOI?

Keywords

Distributed Acoustic Sensing; Artificial Intelligence; Signal Recognition

Abstract

Distributed acoustic sensing (DAS) can provide high sensitivity and spatial resolution remote positioning and monitoring capabilities, making it widely used by researchers for peripheral security applications. However, in daily use, complex environments can lead to low accuracy and poor real-time performance in event recognition. At present, research on DAS event recognition mainly focuses on the classification accuracy of different events, with limited discussion on noise interference. Even with a high event recognition rate of 95%, thousands of events occurring every day can still lead to hundreds of false positives, significantly reducing system availability. This study aims to improve the practicality of DAS by combining Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (LSTM), building on traditional artificial intelligence (AI) recognition models. By statistically analyzing and summarizing the recent events that occurred at adjacent points, this work proposes a secondary analysis method to reduce the frequency of false positives, effectively reducing potential daily false positives from hundreds to every 2–3 days, thereby improving the practicality of the model.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Zhiheng Li
PY  - 2024
DA  - 2024/09/23
TI  - Exploiting CNN-BiLSTM Model for Distributed Acoustic Sensing Event Recognition
BT  - Proceedings of the 2024 International Conference on Artificial Intelligence and Communication (ICAIC 2024)
PB  - Atlantis Press
SP  - 333
EP  - 341
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-512-6_36
DO  - 10.2991/978-94-6463-512-6_36
ID  - Li2024
ER  -