Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/586910
Title: Event Discrimination of Fiber Disturbance Based on Filter Bank in DMZI Sensing System
Authors: Xiangdong Huang;Yuedong Wang;Kun Liu;Tiegen Liu;Chunyu Ma;Qinnan Chen
subject: inter-channel interference|filter bank|feature extraction|Event discrimination
Year: 2016
Publisher: IEEE
Abstract: To meet the growing demand of event discrimination in a dual Mach-Zehnder Interferometry (DMZI) vibration sensing system, this paper proposes a novel scheme of distinguishing invasion events. This scheme consists of three stages: endpoint detection, filter-bank-based feature extraction, and radial-basis-function neural network classification. As the hard core, the proposed filter bank, which is derived from the classical frequency-sampling-based filter design method, greatly suppresses the interchannel interference and, thus, provides accurate feature description for the radial basis function (RBF)-based classifier. Moreover, we also derive the closed-form formula of the filter coefficients and, thus, design a pipeline structure for the filter bank, which brings the advantages of high accuracy, high flexibility, great rapidity, and low cost. Simulation verifies the proposed filter bank's superiority in separating different frequency bands. Field experiments also show that the proposed event discrimination scheme cannot only eliminate some false alarms caused by noninvasion events but can discriminate two common invasion events (climbing the fence and knocking the cable) with high recognition accuracy as well.
Description: 
URI: http://localhost/handle/Hannan/172121
http://localhost/handle/Hannan/586910
ISSN: 1943-0655
volume: 8
issue: 3
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7450616.pdf1.69 MBAdobe PDFThumbnail
Preview File
Title: Event Discrimination of Fiber Disturbance Based on Filter Bank in DMZI Sensing System
Authors: Xiangdong Huang;Yuedong Wang;Kun Liu;Tiegen Liu;Chunyu Ma;Qinnan Chen
subject: inter-channel interference|filter bank|feature extraction|Event discrimination
Year: 2016
Publisher: IEEE
Abstract: To meet the growing demand of event discrimination in a dual Mach-Zehnder Interferometry (DMZI) vibration sensing system, this paper proposes a novel scheme of distinguishing invasion events. This scheme consists of three stages: endpoint detection, filter-bank-based feature extraction, and radial-basis-function neural network classification. As the hard core, the proposed filter bank, which is derived from the classical frequency-sampling-based filter design method, greatly suppresses the interchannel interference and, thus, provides accurate feature description for the radial basis function (RBF)-based classifier. Moreover, we also derive the closed-form formula of the filter coefficients and, thus, design a pipeline structure for the filter bank, which brings the advantages of high accuracy, high flexibility, great rapidity, and low cost. Simulation verifies the proposed filter bank's superiority in separating different frequency bands. Field experiments also show that the proposed event discrimination scheme cannot only eliminate some false alarms caused by noninvasion events but can discriminate two common invasion events (climbing the fence and knocking the cable) with high recognition accuracy as well.
Description: 
URI: http://localhost/handle/Hannan/172121
http://localhost/handle/Hannan/586910
ISSN: 1943-0655
volume: 8
issue: 3
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7450616.pdf1.69 MBAdobe PDFThumbnail
Preview File
Title: Event Discrimination of Fiber Disturbance Based on Filter Bank in DMZI Sensing System
Authors: Xiangdong Huang;Yuedong Wang;Kun Liu;Tiegen Liu;Chunyu Ma;Qinnan Chen
subject: inter-channel interference|filter bank|feature extraction|Event discrimination
Year: 2016
Publisher: IEEE
Abstract: To meet the growing demand of event discrimination in a dual Mach-Zehnder Interferometry (DMZI) vibration sensing system, this paper proposes a novel scheme of distinguishing invasion events. This scheme consists of three stages: endpoint detection, filter-bank-based feature extraction, and radial-basis-function neural network classification. As the hard core, the proposed filter bank, which is derived from the classical frequency-sampling-based filter design method, greatly suppresses the interchannel interference and, thus, provides accurate feature description for the radial basis function (RBF)-based classifier. Moreover, we also derive the closed-form formula of the filter coefficients and, thus, design a pipeline structure for the filter bank, which brings the advantages of high accuracy, high flexibility, great rapidity, and low cost. Simulation verifies the proposed filter bank's superiority in separating different frequency bands. Field experiments also show that the proposed event discrimination scheme cannot only eliminate some false alarms caused by noninvasion events but can discriminate two common invasion events (climbing the fence and knocking the cable) with high recognition accuracy as well.
Description: 
URI: http://localhost/handle/Hannan/172121
http://localhost/handle/Hannan/586910
ISSN: 1943-0655
volume: 8
issue: 3
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7450616.pdf1.69 MBAdobe PDFThumbnail
Preview File