Neural network approach to improving fault location in local telephone networks

P Zhou; J Austin

Neural network approach to improving fault location in local telephone networks

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper reports an investigation into the possibilities offered by neural networks (NN), in particular, a multi-layer perceptron (MLP) and radial basis function (RBF) network, for improving fault location in local telephone networks. It shows that NN can model complex relationships between faults and line parameters measured more effectively, and a substantial increase in classification rate has been achieved on a large number of real fault cases. The paper also describes effective data pre-processing methods, including a novel technique for representing symbolic data. In addition the work has demonstrated methodology for using NN in the classification of line test data.

Original language	English
Title of host publication	NINTH INTERNATIONAL CONFERENCE ON ARTIFICIAL NEURAL NETWORKS (ICANN99), VOLS 1 AND 2
Place of Publication	EDISON
Publisher	INST ELECTRICAL ENGINEERS INSPEC INC
Pages	958-963
Number of pages	6
ISBN (Print)	0-85296-721-7
Publication status	Published - 1999
Event	9th International Conference on Artificial Neural Networks (ICANN99) - EDINBURGH Duration: 7 Sept 1999 → 10 Sept 1999

Conference

Conference	9th International Conference on Artificial Neural Networks (ICANN99)
City	EDINBURGH
Period	7/09/99 → 10/09/99

Cite this

@inproceedings{b4b36392bfb044cfaaf9d2d3e12bf37c,

title = "Neural network approach to improving fault location in local telephone networks",

abstract = "This paper reports an investigation into the possibilities offered by neural networks (NN), in particular, a multi-layer perceptron (MLP) and radial basis function (RBF) network, for improving fault location in local telephone networks. It shows that NN can model complex relationships between faults and line parameters measured more effectively, and a substantial increase in classification rate has been achieved on a large number of real fault cases. The paper also describes effective data pre-processing methods, including a novel technique for representing symbolic data. In addition the work has demonstrated methodology for using NN in the classification of line test data.",

author = "P Zhou and J Austin",

year = "1999",

language = "English",

isbn = "0-85296-721-7",

pages = "958--963",

booktitle = "NINTH INTERNATIONAL CONFERENCE ON ARTIFICIAL NEURAL NETWORKS (ICANN99), VOLS 1 AND 2",

publisher = "INST ELECTRICAL ENGINEERS INSPEC INC",

note = "9th International Conference on Artificial Neural Networks (ICANN99) ; Conference date: 07-09-1999 Through 10-09-1999",

}

TY - GEN

T1 - Neural network approach to improving fault location in local telephone networks

AU - Zhou, P

AU - Austin, J

PY - 1999

Y1 - 1999

N2 - This paper reports an investigation into the possibilities offered by neural networks (NN), in particular, a multi-layer perceptron (MLP) and radial basis function (RBF) network, for improving fault location in local telephone networks. It shows that NN can model complex relationships between faults and line parameters measured more effectively, and a substantial increase in classification rate has been achieved on a large number of real fault cases. The paper also describes effective data pre-processing methods, including a novel technique for representing symbolic data. In addition the work has demonstrated methodology for using NN in the classification of line test data.

AB - This paper reports an investigation into the possibilities offered by neural networks (NN), in particular, a multi-layer perceptron (MLP) and radial basis function (RBF) network, for improving fault location in local telephone networks. It shows that NN can model complex relationships between faults and line parameters measured more effectively, and a substantial increase in classification rate has been achieved on a large number of real fault cases. The paper also describes effective data pre-processing methods, including a novel technique for representing symbolic data. In addition the work has demonstrated methodology for using NN in the classification of line test data.

M3 - Conference contribution

SN - 0-85296-721-7

SP - 958

EP - 963

BT - NINTH INTERNATIONAL CONFERENCE ON ARTIFICIAL NEURAL NETWORKS (ICANN99), VOLS 1 AND 2

PB - INST ELECTRICAL ENGINEERS INSPEC INC

CY - EDISON

T2 - 9th International Conference on Artificial Neural Networks (ICANN99)

Y2 - 7 September 1999 through 10 September 1999

ER -