Abnormal signal detection in gas pipes using neural networks

Hwang Ki Min, Chung Yeol Lee, Jong Seok Lee, Cheol Hoon Park

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

In this paper, we present a real-time system to detect abnormal events on gas pipes, based on the signals which are observed through the audio sensors attached on them. First, features are extracted from this signal so that they are robust to noise and invariant to the distance between a sensor and a spot at which an abnormal event like an attack on the gas pipes occurs. Then, a classifier is constructed to detect abnormal events using neural networks. It is a combination of two neural network models, a Gaussian mixture model and a multi-layer perceptron, for the reduction of miss and false alarms. The former works for miss alarm prevention and the latter for false alarm prevention. The experimental result with real data from the actual gas system shows that the propose system is effective in detecting the dangerous events in real-time having an accuracy of 92.9%.

Original languageEnglish
Title of host publicationProceedings of the 33rd Annual Conference of the IEEE Industrial Electronics Society, IECON
Pages2503-2508
Number of pages6
DOIs
Publication statusPublished - 2007 Dec 1
Event33rd Annual Conference of the IEEE Industrial Electronics Society, IECON - Taipei, Taiwan, Province of China
Duration: 2007 Nov 52007 Nov 8

Other

Other33rd Annual Conference of the IEEE Industrial Electronics Society, IECON
CountryTaiwan, Province of China
CityTaipei
Period07/11/507/11/8

Fingerprint

Signal detection
Pipe
Neural networks
Gases
Sensors
Multilayer neural networks
Real time systems
Classifiers

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Min, H. K., Lee, C. Y., Lee, J. S., & Park, C. H. (2007). Abnormal signal detection in gas pipes using neural networks. In Proceedings of the 33rd Annual Conference of the IEEE Industrial Electronics Society, IECON (pp. 2503-2508). [4460266] https://doi.org/10.1109/IECON.2007.4460266
Min, Hwang Ki ; Lee, Chung Yeol ; Lee, Jong Seok ; Park, Cheol Hoon. / Abnormal signal detection in gas pipes using neural networks. Proceedings of the 33rd Annual Conference of the IEEE Industrial Electronics Society, IECON. 2007. pp. 2503-2508
@inproceedings{77e9e9d5a7014356a71d708c0c983eaa,
title = "Abnormal signal detection in gas pipes using neural networks",
abstract = "In this paper, we present a real-time system to detect abnormal events on gas pipes, based on the signals which are observed through the audio sensors attached on them. First, features are extracted from this signal so that they are robust to noise and invariant to the distance between a sensor and a spot at which an abnormal event like an attack on the gas pipes occurs. Then, a classifier is constructed to detect abnormal events using neural networks. It is a combination of two neural network models, a Gaussian mixture model and a multi-layer perceptron, for the reduction of miss and false alarms. The former works for miss alarm prevention and the latter for false alarm prevention. The experimental result with real data from the actual gas system shows that the propose system is effective in detecting the dangerous events in real-time having an accuracy of 92.9{\%}.",
author = "Min, {Hwang Ki} and Lee, {Chung Yeol} and Lee, {Jong Seok} and Park, {Cheol Hoon}",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/IECON.2007.4460266",
language = "English",
isbn = "1424407834",
pages = "2503--2508",
booktitle = "Proceedings of the 33rd Annual Conference of the IEEE Industrial Electronics Society, IECON",

}

Min, HK, Lee, CY, Lee, JS & Park, CH 2007, Abnormal signal detection in gas pipes using neural networks. in Proceedings of the 33rd Annual Conference of the IEEE Industrial Electronics Society, IECON., 4460266, pp. 2503-2508, 33rd Annual Conference of the IEEE Industrial Electronics Society, IECON, Taipei, Taiwan, Province of China, 07/11/5. https://doi.org/10.1109/IECON.2007.4460266

Abnormal signal detection in gas pipes using neural networks. / Min, Hwang Ki; Lee, Chung Yeol; Lee, Jong Seok; Park, Cheol Hoon.

Proceedings of the 33rd Annual Conference of the IEEE Industrial Electronics Society, IECON. 2007. p. 2503-2508 4460266.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Abnormal signal detection in gas pipes using neural networks

AU - Min, Hwang Ki

AU - Lee, Chung Yeol

AU - Lee, Jong Seok

AU - Park, Cheol Hoon

PY - 2007/12/1

Y1 - 2007/12/1

N2 - In this paper, we present a real-time system to detect abnormal events on gas pipes, based on the signals which are observed through the audio sensors attached on them. First, features are extracted from this signal so that they are robust to noise and invariant to the distance between a sensor and a spot at which an abnormal event like an attack on the gas pipes occurs. Then, a classifier is constructed to detect abnormal events using neural networks. It is a combination of two neural network models, a Gaussian mixture model and a multi-layer perceptron, for the reduction of miss and false alarms. The former works for miss alarm prevention and the latter for false alarm prevention. The experimental result with real data from the actual gas system shows that the propose system is effective in detecting the dangerous events in real-time having an accuracy of 92.9%.

AB - In this paper, we present a real-time system to detect abnormal events on gas pipes, based on the signals which are observed through the audio sensors attached on them. First, features are extracted from this signal so that they are robust to noise and invariant to the distance between a sensor and a spot at which an abnormal event like an attack on the gas pipes occurs. Then, a classifier is constructed to detect abnormal events using neural networks. It is a combination of two neural network models, a Gaussian mixture model and a multi-layer perceptron, for the reduction of miss and false alarms. The former works for miss alarm prevention and the latter for false alarm prevention. The experimental result with real data from the actual gas system shows that the propose system is effective in detecting the dangerous events in real-time having an accuracy of 92.9%.

UR - http://www.scopus.com/inward/record.url?scp=49949098791&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=49949098791&partnerID=8YFLogxK

U2 - 10.1109/IECON.2007.4460266

DO - 10.1109/IECON.2007.4460266

M3 - Conference contribution

SN - 1424407834

SN - 9781424407835

SP - 2503

EP - 2508

BT - Proceedings of the 33rd Annual Conference of the IEEE Industrial Electronics Society, IECON

ER -

Min HK, Lee CY, Lee JS, Park CH. Abnormal signal detection in gas pipes using neural networks. In Proceedings of the 33rd Annual Conference of the IEEE Industrial Electronics Society, IECON. 2007. p. 2503-2508. 4460266 https://doi.org/10.1109/IECON.2007.4460266