Citation

Abdul Aziz, Nurul Ain and Ngo, Hong Yeap and Choo, Kan Yeep and Tee, Connie and Jabidin, Hafiz Zulhazmi and Muniandy, Sithi Vinayakam (2025) LSTM: Anomaly Activity Type Classification Using Distributed Acoustic Sensing Based on MFCC Features. International Journal of Integrated Engineering, 17 (2). ISSN 2229-838X

Text View of LSTM_ Anomaly Activity Type Classification Using Distributed Acoustic Sensing Based on MFCC Features.pdf - Published Version Restricted to Repository staff only Download (3MB)

Abstract

The integrity and connectivity of the fibre optical network are important in preserving the quality of services and internet reliability between providers and end users. However, these networks are vulnerable to disruptions due to unintentional breaks and damage caused by physical disturbances such as construction activity. An accurate classification of anomalous activity at surrounding area plays a crucial role in monitoring the buried fibre optical network from harm which can lead to denial of services. Distributed acoustic sensing (DAS) with combination of deep learning-based technique have potential in targeting this issue, by leveraging the unique pattern of vibration signal measured by the DAS to classify and identify anomalous activities. This work demonstrated utilization of dark fibre buried along the road until the server room, then connected to the DAS interrogator unit (IU). The vibration signals induced by construction hand tools, including hoe, shovel, and sledgehammer, which are used to mimic anomalous activity, are measured by DAS IU and underwent pre-processing before the Mel frequency cepstral coefficient (MFCC) features extraction for long short-term memory (LSTM) model training. The average accuracy score using 13 MFCCs resulted up to 88%, indicating that the proposed method has great potential for anomalous activity monitoring for fibre break prevention

Item Type:	Article
Uncontrolled Keywords:	Deep learning
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions:	Faculty of Engineering (FOE) Faculty of Information Science and Technology (FIST)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	06 Oct 2025 02:27
Last Modified:	06 Oct 2025 04:11
URII:	http://shdl.mmu.edu.my/id/eprint/14672

Downloads

Edit (login required)