Citation

Jabidin, Hafiz Zulhazmi and Ibrahim@Ghazali, Siti Azlida and Dzulkefly Zan, Mohd Saiful and Musa, Siti Musliha Aishah and Mansoor, Amilia and Ngo, Hong Yeap and Abdul Aziz, Nurul Ain and Choo, Kan Yeep and A. Bakar, Ahmad Ashrif and Mokhtar, Mohd Ridzuan and Tee, Connie and Abdul Rashid, Hairul Azhar (2024) Review on Digital Signal Processing (DSP) Algorithm for Distributed Acoustic Sensing (DAS) for Ground Disturbance Detection. International Journal of Integrated Engineering, 16 (2). pp. 102-113. ISSN 2229-838X

Text 11.+15874+102-113.pdf - Published Version Restricted to Repository staff only Download (559kB)

Abstract

Fiber break because of third-party intrusion has become one of the challenges in maintaining the fiber-based communication link, especially those buried underground. Hence, we investigate the feasibility of using Distributed Acoustic Sensing (DAS) system to sense possible surrounding activities that might cause fiber break. This paper reviews the current digital signal processing (DSP) algorithm used in the DAS system designed to detect ground disturbance, highlighting the specific design parameters for each technique. These parameters include identification rate, classification accuracy, detection accuracy, training time, and signal-to-noise ratio (SNR). The algorithms used are near-field beamforming, phased-array beamforming, image edge detection, gaussian mixture model (GMM), gaussian mixture model -hidden Markov model (GMM-HMM), faster region-based convolutional neural networks (R-CNN), transfer learning, dual-stage recognition network, group convolutional neural network (100G-CNN), and support vector machine (SVM). By reviewing the existing techniques used in the DAS system for ground disturbance detection, we can determine the best DSP algorithm that should be implemented for fiber break prevention, enabling us to design a DAS system specifically for it in the near future.

Item Type:	Article
Uncontrolled Keywords:	Distributed Acoustic Sensing (DAS), digital signal processing (DSP), signal-to-noise ratio (SNR), Gaussian Mixture Model - Hidden Markov Model (GMMHMM), Faster Region-Based Convolutional Neural Networks (R-CNN), Group Convolutional Neural Networks (100G-CNN), support vector machine (SVM), Gaussian Mixture Model (GMM)
Subjects:	Q Science > QA Mathematics > QA150-272.5 Algebra
Divisions:	Faculty of Engineering (FOE) Faculty of Information Science and Technology (FIST)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	03 Jul 2024 03:32
Last Modified:	03 Jul 2024 03:32
URII:	http://shdl.mmu.edu.my/id/eprint/12600

Downloads

Edit (login required)