Research Portal

Highly discriminative and adaptive feature extraction method based on NMF-MFCC for event recognition of Φ-OTDR

Research output: Contribution to journal › Article › peer-review

Standard Standard

Highly discriminative and adaptive feature extraction method based on NMF-MFCC for event recognition of Φ-OTDR. / Huang, Yi; Dai, Jingyi; Shen, Wei et al.
In: Applied Optics, Vol. 62, No. 35, 10.12.2023, p. 9326-9333.

Research output: Contribution to journal › Article › peer-review

HarvardHarvard

Huang, Y, Dai, J, Shen, W, Chen, X, Hu, C, Deng, C, Chen, L, Zhang, X, Jin, W, Tang, J & Wang, T 2023, 'Highly discriminative and adaptive feature extraction method based on NMF-MFCC for event recognition of Φ-OTDR', Applied Optics, vol. 62, no. 35, pp. 9326-9333. https://doi.org/10.1364/AO.506307

APA

Huang, Y., Dai, J., Shen, W., Chen, X., Hu, C., Deng, C., Chen, L., Zhang, X., Jin, W., Tang, J., & Wang, T. (2023). Highly discriminative and adaptive feature extraction method based on NMF-MFCC for event recognition of Φ-OTDR. Applied Optics, 62(35), 9326-9333. https://doi.org/10.1364/AO.506307

CBE

Huang Y, Dai J, Shen W, Chen X, Hu C, Deng C, Chen L, Zhang X, Jin W, Tang J, et al. 2023. Highly discriminative and adaptive feature extraction method based on NMF-MFCC for event recognition of Φ-OTDR. Applied Optics. 62(35):9326-9333. https://doi.org/10.1364/AO.506307

MLA

Huang, Yi et al. "Highly discriminative and adaptive feature extraction method based on NMF-MFCC for event recognition of Φ-OTDR". Applied Optics. 2023, 62(35). 9326-9333. https://doi.org/10.1364/AO.506307

VancouverVancouver

Huang Y, Dai J, Shen W, Chen X, Hu C, Deng C et al. Highly discriminative and adaptive feature extraction method based on NMF-MFCC for event recognition of Φ-OTDR. Applied Optics. 2023 Dec 10;62(35):9326-9333. Epub 2023 Dec 2. doi: 10.1364/AO.506307

Author

Huang, Yi ; Dai, Jingyi ; Shen, Wei et al. / Highly discriminative and adaptive feature extraction method based on NMF-MFCC for event recognition of Φ-OTDR. In: Applied Optics. 2023 ; Vol. 62, No. 35. pp. 9326-9333.

RIS

TY - JOUR

T1 - Highly discriminative and adaptive feature extraction method based on NMF-MFCC for event recognition of Φ-OTDR

AU - Huang, Yi

AU - Dai, Jingyi

AU - Shen, Wei

AU - Chen, Xiaofeng

AU - Hu, Chengyong

AU - Deng, Chuanlu

AU - Chen, Lin

AU - Zhang, Xiaobei

AU - Jin, Wei

AU - Tang, Jianming

AU - Wang, Tingyun

PY - 2023/12/10

Y1 - 2023/12/10

N2 - To enhance the capability of phase-sensitive optical time domain reflectometers (Φ-OTDR) to recognize disturbance events, an improved adaptive feature extraction method based on NMF-MFCC is proposed, which replaces the fixed filter bank used in the traditional method to extract the mel-frequency cepstral coefficient (MFCC) features by a spectral structure obtained from the Φ-OTDR signal spectrum using nonnegative matrix factorization (NMF). Three typical events on fences are set as recognition targets in our experiments, and the results show that the NMF-MFCC features have higher distinguishability, with the corresponding recognition accuracy reaching 98.47%, which is 7% higher than that using the traditional MFCC features.

AB - To enhance the capability of phase-sensitive optical time domain reflectometers (Φ-OTDR) to recognize disturbance events, an improved adaptive feature extraction method based on NMF-MFCC is proposed, which replaces the fixed filter bank used in the traditional method to extract the mel-frequency cepstral coefficient (MFCC) features by a spectral structure obtained from the Φ-OTDR signal spectrum using nonnegative matrix factorization (NMF). Three typical events on fences are set as recognition targets in our experiments, and the results show that the NMF-MFCC features have higher distinguishability, with the corresponding recognition accuracy reaching 98.47%, which is 7% higher than that using the traditional MFCC features.

U2 - 10.1364/AO.506307

DO - 10.1364/AO.506307

M3 - Article

C2 - 38108704

VL - 62

SP - 9326

EP - 9333

JO - Applied Optics

JF - Applied Optics

SN - 1559-128X

IS - 35

ER -